Various types of tests related to patient diagnosis and therapy can be performed by analysis of the patient's microorganisms, or “microbes.” Microbes are microscopic living organisms such as bacteria, fungi, or viruses, which may be single-celled or multicellular. Biological samples containing the patient's microorganisms may be taken from a patient's infections, bodily fluids or abscesses and may be placed in test panels or arrays, combined with various reagents, incubated, and analyzed to aid in treatment of the patient. Automated biochemical analyzers have been developed to meet the needs of health care facilities and other institutions to facilitate analysis of patient samples and to improve the accuracy and reliability of assay results when compared to analysis using manual operations and aid in determining effectiveness of various antimicrobials. An antimicrobial is an agent that kills microorganisms or inhibits their growth, such as antibiotics which are used against bacteria and antifungals which are used against fungi. However, with ever changing bacterial genera and newly discovered antimicrobials, the demand for biochemical testing has increased in both complexity and volume.
An important family of automated microbiological analyzers function as a diagnostic tool for determining both the identity of an infecting microorganism and of an antimicrobic effective in controlling growth of the microorganism. Automated microbiological analyzers function as a diagnostic tool for determining both the identity of an infecting microorganism and of an antimicrobic effective in controlling growth of the microorganism. In performing the diagnostic tests, identification and in vitro antimicrobic susceptibility patterns of microorganisms isolated from biological samples are ascertained. Conventional versions of such analyzers may place a small sample to be tested into a plurality of small sample test wells in panels or arrays that contain different enzyme substrates or antimicrobics in serial dilutions. Identification (ID) testing of microorganisms, and antimicrobic susceptibility testing (AST) for determining Minimum Inhibitory Concentrations (MIC) of an antimicrobic effective against the microorganism may utilize color changes, fluorescence changes, the degree of cloudiness (turbidity) in the sample test wells created in the arrays, or other information derived from the testing. Both AST and ID measurements and subsequent analysis may be performed by computer controlled microbiological analyzers to provide advantages in reproducibility, reduction in processing time, avoidance of transcription errors and standardization for all tests run in the laboratory.
In ID testing of a microorganism, a standardized dilution of the patient's microorganism sample, known as an inoculum, is first prepared in order to provide a bacterial or cellular suspension having a predetermined known concentration. This inoculum is placed in a plurality of test wells that may contain or thereafter be supplied with predetermined test media. Depending on the species of microorganism present, this media will facilitate changes in color, turbidity, fluorescence, or other characteristics after incubation. These changes are used to identify the microorganism in ID testing.
In AST testing, a plurality of test wells are filled with inoculum and increasing concentrations of a number of different antimicrobial agents, for example antibiotics. The different antimicrobial agents may be diluted in a growth medium or liquid medium to concentrations that include those of clinical interest. After incubation, the turbidity will be increased or unchanged in test wells where growth has not been inhibited by the antimicrobics in those test wells. The MIC of each antimicrobial agent is measured by lack of growth with respect to each concentration of antimicrobial agent. It follows that the lowest concentration of antimicrobial agent displaying a lack of growth is the MIC.
While the specification concludes with claims which particularly point out and distinctly claim the invention, it is believed the present invention will be better understood from the following description of certain examples taken in conjunction with the accompanying drawings, in which like reference numerals identify the same elements and in which:
The drawings are not intended to be limiting in any way, and it is contemplated that various embodiments of the invention may be carried out in a variety of other ways, including those not necessarily depicted in the drawings. The accompanying drawings incorporated in and forming a part of the specification illustrate several aspects of the present invention, and together with the description serve to explain the principles of the invention; it being understood, however, that this invention is not limited to the precise arrangements shown.
The following description of certain examples of the invention should not be used to limit the scope of the present invention. Other examples, features, aspects, embodiments, and advantages of the invention will become apparent to those skilled in the art from the following description, which is by way of illustration, one of the best modes contemplated for carrying out the invention. As will be realized, the invention is capable of other different and obvious aspects, all without departing from the invention. Accordingly, the drawings and descriptions should be regarded as illustrative in nature and not restrictive.
It will be appreciated that any one or more of the teachings, expressions, versions, examples, etc. described herein may be combined with any one or more of the other teachings, expressions, versions, examples, etc. that are described herein. The following-described teachings, expressions, versions, examples, etc. should therefore not be viewed in isolation relative to each other. Various suitable ways in which the teachings herein may be combined will be readily apparent to those of ordinary skill in the art in view of the teachings herein. Such modifications and variations are intended to be included within the scope of the claims.
I. Biological Testing System Hardware
To operate biological testing system 1, the user first acquires an appropriate microbe sample. As shown in
Consumable preparation system 3 is loaded with magazines of test arrays 19, which may contain various antimicrobials or other agents required by biological testing system 1 disposed in a series of test wells 20. For example, test array 19 may comprise an antimicrobic dilution array or an identification array. Consumable preparation system 3 may also be loaded with bulk diluents (not shown) and/or various other elements for preparing and finalizing ID array holder 21 and AST array holder 23 and the inoculate therein. Primarily, consumable preparation system 3 operates to retrieve test arrays 19 as required and combine each retrieved test array 19 into either ID array holder 21 or AST array holder 23. Test arrays 19 may be selected and assembled by a robotic gripper (not shown) or other mechanical features as dictated by the prescribed testing. For example, a physician may order biological testing using the antibiotic amoxicillin. Test arrays 19 relating to amoxicillin testing are therefore retrieved and assembled into the appropriate ID array holder 21 and AST array holder 23. All or some portions of test array 19 may be formed of a styrene material to aid in reducing fluorescent crosstalk, fallout, and/or bubbles when digitally examining each test well 20.
Once inoculum 17, inoculum 18, ID array holder 21, and AST array holder 23 are assembled, inoculating system 5 dispenses the generally undiluted inoculum from inoculum 17 into test wells 20 of ID array holder 21 and the diluted inoculum from inoculum 18 into test wells 20 of AST array holder 23. The time between applying inoculum 17 to ID array holder 21 or inoculum 18 to AST array holder 23 and the start of logarithmic growth of the microbes disposed therein is known as “lag time.” Lag time may be decreased by using enhanced broth such as a broth with yeast extract, vitamins, and/or minerals. Lag time may also be decreased by increasing the inoculum. In some versions of biological testing system 1, the amount of inoculum may be doubled to decrease the lag time by approximately 30 minutes without affecting the accuracy of the MIC determination. The dispensing may be accomplished via an elevator assembly 26 having an XY robot or XYZ robot (not shown) with a gripper (not shown) and pipettor (not shown), along with various circuitry, channels, and tubing as necessary. The XYZ robot is tasked with retrieving inoculum from inoculum racks 15 and dispensing the inoculum into test wells 20 of ID array holder 21 and AST array holder 23. Once ID array holder 21 and AST array holder 23 are sufficiently loaded with inoculum, each ID array holder 21 and AST array holder 23 are moved into incubator system 7 by way of an elevator assembly 26.
As shown in
As shown in
Referring now to
Computer system 49 may include a processor 51, a memory 53, a mass storage memory device 55, an input/output (I/O) interface 57, and a Human Machine Interface (HMI) 59. Computer system 49 may also be operatively coupled to one or more external resources 61 via a network 63 or I/O interface 57. External resources may include, but are not limited to, servers, databases, mass storage devices, peripheral devices, cloud-based network services, or any other suitable computer resource that may be used by computer system 49.
Processor 51 may include one or more devices selected from microprocessors, micro-controllers, digital signal processors, microcomputers, central processing units, field programmable gate arrays, programmable logic devices, state machines, logic circuits, analog circuits, digital circuits, or any other devices that manipulate signals (analog or digital) based on operational instructions that are stored in memory 53. Memory 53 may include a single memory device or a plurality of memory devices including, but not limited, to read-only memory (ROM), random access memory (RAM), volatile memory, non-volatile memory, static random access memory (SRAM), dynamic random access memory (DRAM), flash memory, cache memory, or any other device capable of storing information. Mass storage memory device 55 may include data storage devices such as a hard drive, optical drive, tape drive, non-volatile solid state device, or any other device capable of storing information.
Processor 51 may operate under the control of an operating system 65 that resides in memory 53. Operating system 65 may manage computer resources so that computer program code embodied as one or more computer software applications, such as an application 67 residing in memory 53, may have instructions executed by the processor 51. In an alternative embodiment, processor 51 may execute application 67 directly, in which case the operating system 65 may be omitted. One or more data structures 69 may also reside in memory 53, and may be used by processor 51, operating system 65, or application 67 to store or manipulate data.
The I/O interface 57 may provide a machine interface that operatively couples processor 51 to other devices and systems, such as network 63 or external resource 61. Application 67 may thereby work cooperatively with network 63 or external resource 61 by communicating via I/O interface 57 to provide the various features, functions, applications, processes, or modules comprising embodiments of the invention. Application 67 may also have program code that is executed by one or more external resources 61, or otherwise rely on functions or signals provided by other system or network components external to computer system 49. Indeed, given the nearly endless hardware and software configurations possible, persons having ordinary skill in the art will understand that different versions of the invention may include applications that are located externally to computer system 49, distributed among multiple computers or other external resources 61, or provided by computing resources (hardware and software) that are provided as a service over network 63, such as a cloud computing service.
HMI 59 may be operatively coupled to processor 51 of computer system 49 in a known manner to allow a user to interact directly with the computer system 49. HMI 59 may include video or alphanumeric displays, a touch screen, a speaker, and any other suitable audio and/or visual indicators capable of providing data to the user. HMI 59 may also include input devices and controls such as an alphanumeric keyboard, a pointing device, keypads, pushbuttons, control knobs, microphones, etc., capable of accepting commands or input from the user and transmitting the entered input to the processor 51.
A database 71 may reside on mass storage memory device 55, and may be used to collect and organize data used by the various systems and modules described herein. Database 71 may include data and supporting data structures that store and organize the data. In particular, database 71 may be arranged with any database organization or structure including, but not limited to, a relational database, a hierarchical database, a network database, or combinations thereof. A database management system in the form of a computer software application executing as instructions on processor 51 may be used to access the information or data stored in records of the database 71 in response to a query, where a query may be dynamically determined and executed by operating system 65, other applications 67, or one or more modules.
II. Optimized AST System and Method
In some versions, system 1 as discussed above may be used to facilitate some or all of the features provided in optimized AST method 101 such as shown in
In some conventional processes, MIC is determined through manual visual inspection of test wells after waiting a period to allow the microbes to grow. However, as shown in
Image analysis cycle 102 is generally depicted in
Image analysis cycle 102 begins with image capture step 111 and captures a raw image 119 (
As shown in
Image enhancement step 113 may apply image enhancements either statically, dynamically, or both. For example, the pixel radius for the median filter may be a statically set constant value or may be adaptively derived dynamically from characteristics of each raw image 119 captured through optics system 9. As shown in
As shown in
Image artifacts such as noise may be removed by applying a noise reduction filter prior to applying the segmentation algorithm. Segmentation can be obtained using static threshold value or using an adaptive image thresholding method such as the Otsu cluster based thresholding algorithm. In this algorithm, the gray-level samples are clustered in two parts as background and foreground (object), or alternatively are modeled as a mixture of two Gaussians. The threshold value for the particular image thresholding algorithm used may be determined dynamically, depending on the overall image provided to image segmentation step 115 and the relative grayscale levels of the image. For example, inoculating system 5 or another element of system 1 may be configured to apply nigrosin to each test well 20 to enhance the image, as nigrosin does not attach to certain microbes such as bacteria. This may alter the relative greyscale levels in raw image 119 and require a different threshold value for the segmentation algorithm, as compared to a raw image 119 without nigrosin. In some versions of optimized AST method 101, threshold values may be determined dynamically by searching for edges within several areas of the image. These edges are the transition point between the background and a microbe. Thus, the threshold value can then be calculated as the average greyscale value for pixels on each side of the located edge.
As shown in
Once image segmentation step 115 generates segmented image 143, image segmentation step 115 proceeds to data extraction step 117. In data extraction step 117, the background and foreground pixels are considered to derive information regarding the number of microbes in the sample (Count—C), the area occupied by the microbes in the sample (Area—A), and the ratio between the area occupied by the microbes and the number of microbes (A/C). In some versions of data extraction step 117, the actual microbe count is compared with an average microbe count to determine if an error occurred within the image capture process. The comparison may incorporate a standard deviation with the average microbe count to generalize the microbe comparison.
Data extraction step 117 may be configured to derive information regarding the number of microbes in the image. In some embodiments of data extraction step 117, the number of foreground pixels in segmented image 143 may be counted in accordance with a predefined width and/or length to determine the number of microbes in the imaged portion of the inoculum. The counting algorithm may be divided into two separate algorithms, one for counting rod shaped microbes and one for counting spherical shaped microbes as the profile of the underlying microbes provides a corresponding different foreground pixel shape in segmented image 143. For example, the counting algorithm may be configured to consider a square of 2×2 pixels a microbe for counting purposes for spherical shaped microbes, or may consider a rectangle of 1×4 pixels a microbe for counting purposes for rod shaped microbes. Further, the counting algorithm may be configured to process both algorithms in order to capture the different three-dimensional orientations of rod shaped microbes. For example, if an elongated rod is positioned endwise towards AST camera 35, it will have a much different profile when viewed in two dimensions through AST camera 35. Therefore, both of the counting algorithms may be used during the counting phase of image analysis cycle 102. Alternatively, the counting algorithm may be configured to consider and count any foreground pixels surrounded by background pixels as a microbe.
Data extraction step 117 may be configured to derive information regarding the total area occupied by all of the microbes in the image. In some versions of data extraction step 117, the total number of foreground pixels in segmented image 143 may be counted and compared to the total number of background pixels in segmented image 143. Data extraction step 117 may express the area count information in any format, including as a percent such as 30%, or as a literal number of pixels such as “138 foreground pixels out of 450 total pixels” or “138 foreground pixels and 312 background pixels.”
Data extraction step 117 may be configured to derive information regarding the ratio between the total count of microbes and the total area occupied by all of the microbes in the image. This information may be useful in determining whether the microbes are undergoing elongation over time. Elongation is a precursor to death and indicates the concentration of the antimicrobic dilution is negatively affecting the microbes. More specifically, elongation may occur when microbes such as bacteria encounter an effective amount of antibiotic drugs.
For example,
Once data extraction step 117 derives the desired information from segmented image 143, image analysis cycle 102 terminates. Optimized AST method 101 iteratively performs image analysis cycle 102 at set time intervals to determine how the microbes in each test well 20 are changing and reacting to the particular antimicrobic dilution pairing. Further, optimized AST method 101 iteratively performs image analysis cycle 102 on each test well 20 associated with the microbes to determine how the microbes are reacting to each concentration of the antimicrobic dilution. For example, presume the microbes being tested are E. coli bacteria and three test wells 20 are being tested, with each test well 20 having a 20-microliter solution therein. The first test well 20 may contain an antimicrobic dilution of 1 microgram per milliliter (μg/ml), the second test well 20 may contain an antimicrobic dilution of 2 μg/ml, and the third test well 20 may contain an antimicrobic dilution of 4 μg/ml. Optimized AST method 101 performs image analysis cycle 102 on each of the three test wells at each set time interval to determine (a) how each antimicrobic dilution is affecting the microbes; and (b) how each antimicrobic dilution is performing relative to the other antimicrobic dilutions. If the data indicates the 1 μg/ml antimicrobic dilution is as effective as the 2 and 4 μg/ml antimicrobic dilutions at neutralizing the microbes, the 1 μg/ml antimicrobic dilution is the MIC.
An exemplary version of optimized AST method 101 is illustrated in
In step 157, one iteration of image analysis cycle 102 is performed on a particular microbe with a selected test well 20. As discussed above, an iteration of image analysis cycle 102 derives data regarding the growth rate of the microbes within the selected test well 20. After an iteration of image analysis cycle 102 is performed, step 157 moves to a step 159. In step 159, the data collected in step 157 is stored and/or updated in memory, which may be in the form of a database, a flat file, or any other similar memory or storage device. In some embodiments of optimized AST method 101, step 159 stores the data collected in step 157 in database 71 (
In step 161, optimized AST method 101 determines whether enough data has been collected to determine a MIC. This could be done, for example, by determining whether the data collected regarding the test well matched the data used to train a machine learning classifier used in determining a MIC. If more data is needed to accurately determine a MIC, step 161 returns to step 155 and waits to perform another image analysis cycle 102 to collect more data at a future time interval. If step 161 determines a sufficient amount of data has been collected, step 161 proceeds to a step 163.
In step 163, the MIC is determined, and in step 165 it is reported (e.g., via HMI 59). The determination is based on the data collected during each iteration of image analysis cycle 102 for all of the antimicrobic dilutions for a microbial sample as well as for a control well where no antimicrobial agent was present. As described in the following section, this determination may involve applying the collected data to a machine learning classifier that had previously been trained to make growth predictions and then determining the MIC based on which of the test wells was predicted to exhibit growth or to be inhibited.
III. Machine Learning for Determining Minimum Inhibitory Concentration (MIC)
In general, the described approach can be used to create decision trees that would make growth predictions for a wide variety of microorganisms in the presence of varying concentrations of a wide variety of antimicrobial agents. Tables 1 and 2 list examples of classes of microorganisms and antimicrobials, as well as specific organisms and antimicrobials within those classes, that are believed to be suitable for use with decision tree classifiers of the types described above:
Aeromonas hydrophilia
Citrobacter freundii
Citrobacter koseri
Enterobacter aerogenes
Enterobacter cloacae
Eschericia coli
Klebsiella oxytoca
Klebsiella pneumoniae
Morganelle morganii
Proteus mirabilis
Proteus penneri
Proteus vulgaris
Providencia stuartii
Providendia rettgeri
Salmonella paratyphi
Salmonella typhi
Serratia marcescens
Shigella dysenteriae
Shigella.flexneri
Shigella sonnei
Vibrio chloerae
Yersinia enterocolitica
Acinetobacter baumannii
Acinetobacer haemolyticus
Acinetobacter lwoffii
Moraxella species
Pseudomonas aeruginosa
Pseudomonas alcaligenes
Pseudomonas fluorescens
Pseudomonas putida
Stenotrophamonas maltophilia
Staphylococcus aureus
Staphylococcus capitis
Staphylococcus epidermidis
Staphylococcus haemolyticus
Staphylococcus saprophyticus
Staphylococcus warneri
Staphylococcus simulans
Staphylococcus lugdenensis
Enterococcus avium
Enterococcus faecalis
Enterococcus faecium
Enterococcus gallinarum
Enterococcus raffinosus
Streptococcus bovis
Streptococcus pyogenes
Streptococcus pneumoniae
It is believed that the above approach can also be used with microbes and antimicrobials not listed in tables 1 and 2. For example, it is believed that decision tree classifiers such as described above could be used to make growth predictions for microorganisms in the enterobacteriaceae family, the pseudomonas family, the acinetobacter family, the micrococcacaeae family and/or the streptococcaceae family.
Variations on the above approach are also possible. For example, in some cases, rather than treating classifications directly as growth or inhibition predictions for the test well whose data is provided to a decision tree, they could be subjected to further processing to create a classification. For example, in some embodiments, when data is provided to a decision tree such as shown in
Other approaches are also possible, and will be immediately apparent to those of ordinary skill in the art. For example, in some embodiments, rather than training individual decision trees, training techniques such as XG Boost could be used to generate ensembles of multiple trees whose outputs could be combined to provide higher reliability predictions. There could be various numbers of trees in such an ensemble, from 2 trees to several hundred trees. During testing, when XG Boost software was used to create an ensemble of 500 decision trees that used the factors set forth in table 3 based on training data gathered using the gram negative bacteria of A. baumannii, C. freundii cplx, E. aerogenes, E. cloacae, E. coli, K. oxytoca, K. pneumoniae, P. aeruginosa, P. fluorescens, S. marcescens, Salmonella sp., P. mirabilis, P. rettgeri and the antibiotics of cefepime (a beta-lactam), cefotaxime, ceftazidime, gentamicin, levofloxacin, meropenem, and tetracycline, the predictions provided by the resulting ensemble after four hours were found to have the agreement set forth in table 4 with the actual growth/inhibition observations taken after 18 hours.
Unexpectedly, during this testing, it was found that this ensemble was suitable for making growth predictions for each of the microorganisms tested, rather than a separate ensemble or tree being necessary for each microorganism or for each antimicrobial. As a result, in some embodiments a biological testing system may be configured with an ensemble of decision trees that would be used for any kind of gram negative bacteria regardless of the antimicrobial being tested or the particular gram negative bacteria in a sample, rather than using different decision trees or ensembles for each microorganism and antimicrobial. Of course, it is also possible that individual decision trees or ensembles could be trained on data for, and used to provide MIC predictions for, specific combinations of microorganisms and antimicrobials. Accordingly, the discussion above of applying decision tree classifiers and ensembles and the unexpected result that an ensemble classifier trained to use the parameters specified in table 3 could be applied to multiple microorganisms and antimicrobials should be understood as being illustrative only and should not be treated as limiting.
Other types of machine learning models could also be used to make MIC predictions. For example, in some embodiments, rather than using a decision tree such as shown in
Variations are also possible in the way machine learning modules are used. For example, in some cases, rather than training a model to simply make a growth/inhibition prediction as described above, a model could be trained to make a MIC prediction directly.
In some embodiments, to use a neural network such as illustrated in
In some embodiments, rather than using values of the output nodes of a network such as shown in
During testing, it was unexpectedly found that using this approach allowed a single neural network having the input nodes, output nodes, hidden layer code, and response mapping code set forth in table 8 to be used to create MIC predictions that had the essential and absolute agreements set forth in table 9 for data covering the species of A. baumannii, C. freundii, E. aerogenes, E. cloacae, E. coli, K oxytoca, K. pneumonia, P. mirabilis, P. aeruginosa, P. fluorescens, P. mirabilis, P. rettgeri, S. marcescens, and Salmonella and the antimicrobials of Cefepime, Cefotaxime, Ceftazidime, Gentamicin, Levofloxacin, Meropenem, and Tetracycline.
As set forth above, neural networks can be used to model growth patterns of a bacterial isolate over time at various drug concentrations. As long as the bacteria grows in the well with no drug, then a neural network can be created to use the count and area of the growth well and at the various drug concentrations to make an early prediction of the MIC. Such networks can make predictions of MIC growth within the first six hours (or within the first 3.5-4 hours for the networks discussed in the context of tables 6 and 9) that had a high degree of agreement with actual MIC read at 16-24 hours. This can be applied to gram negative bacteria (including Enterobacteriaceae, Pseudomonas species, Acinetobacter species, Stenotrophamonas species, and Haemophilus species) and gram positive bacteria (including staphylococcus species, enterococcus species, and streptococcus species), and with drug classes of penicillins, beta-lactam, beta-lactam with inhibitor, carbapenems, cephalosporins, monobactams, tetracyclines, aminoglycosides, macrolides, glycopeptids, lincosamides, oxazolidinones, quinolones, folate inhibitors, and ansamycins.
After a model such as a decision tree classifier, ensemble of decision trees, neural network or other type of model has been created it, potentially with a plurality of other models (e.g., in embodiments in which specific models, such as the decision trees of
IV. Exemplary Combinations
The following examples relate to various non-exhaustive ways in which the teachings herein may be combined or applied. It should be understood that the following examples are not intended to restrict the coverage of any claims that may be presented at any time in this application or in subsequent filings of this application. No disclaimer is intended. The following examples are being provided for nothing more than merely illustrative purposes. It is contemplated that the various teachings herein may be arranged and applied in numerous other ways. It is also contemplated that some variations may omit certain features referred to in the below examples. Therefore, none of the aspects or features referred to below should be deemed critical unless otherwise explicitly indicated as such at a later date by the inventors or by a successor in interest to the inventors. If any claims are presented in this application or in subsequent filings related to this application that include additional features beyond those referred to below, those additional features shall not be presumed to have been added for any reason relating to patentability.
A method comprising: (a) incubating a first plurality of test mixtures in a plurality of test wells 20 using an incubator subsystem 7 of a biological testing system 1, wherein: (i) each test mixture from the first plurality of test mixtures is inoculated using a first biological sample; (ii) each test mixture from the first plurality of test mixtures has a concentration of a first antimicrobial agent; (iii) in each test mixture from the first plurality of test mixtures, the concentration of the first antimicrobial solution in that test mixture differs from the concentration of the first antimicrobial solution in each other test mixture from the first plurality of test mixtures; (iv) the same first biological sample is used to inoculate each test mixture from the first plurality of test mixtures; and (v) the first plurality of test mixtures comprises a growth mixture having a concentration of the first antimicrobial agent of zero; (b) at a plurality of imaging times, wherein each of the imaging times takes place after incubation has begun, for each test mixture from the first plurality of test mixtures, capturing an image of that test mixture using an AST camera 35; (c) obtaining a plurality of machine learning outputs by a processor 51 of a computer system 49 performing steps comprising, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero: (i) determining a plurality of characteristic values for that test mixture, wherein: (A) each of the characteristic values corresponds to a parameter from a plurality of parameters; and (B) the plurality of characteristic values for that test mixture are determined based on images captured of that test mixture at the plurality of imaging times; and (ii) providing the plurality of characteristic values determined for that test mixture to a machine learning model; and (d) the processor 51 of the computer system 49 generating a MIC prediction for the first biological sample based on the plurality of machine learning outputs.
The method of Example 1, wherein: (a) the plurality of imaging times comprises an earliest imaging time separated from onset of incubation by a first duration; (b) each imaging time from the plurality of imaging times except for the earliest imaging time is separated from its preceding imaging time by a second duration; and (c) the second duration is shorter than the first duration.
The method of Example 2, wherein the first duration is 90 minutes, and the second duration is 30 minutes.
The method of any of Examples 1-3, wherein the plurality of imaging times comprises a latest imaging time separated from the onset of incubation by four hours.
The method of any of Examples 1-4, wherein, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero: (a) the plurality of characteristic values for that test mixture comprises a first set of characteristic values and a second set of characteristic values; (b) the first set of characteristic values is based on images captured at a first time from the plurality of imaging times; (c) the second set of characteristic values is based on images captured at a second time from the plurality of imaging times; and (d) the plurality of parameters comprises a set of parameters, wherein each parameter from the set of parameters corresponds to one value from the first set of characteristic values and to one value from the second set of characteristic values.
The method of Example 5, wherein, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, the plurality of characteristic values for that test mixture comprises, for each imaging time from the plurality of imaging times, a rate of change value for each parameter from the set of parameters.
The method of any of Examples 5-6, wherein, for each test mixture from the plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero: (a) the plurality of characteristic values comprises a growth set of characteristic values; (b) each parameter from the set of parameters corresponds to one characteristic value from the growth set of characteristic values for each imaging time from the plurality of imaging times; and (c) the characteristic values from the growth set of characteristic values are based on images captured of the growth mixture at the plurality of imaging times.
The method of any of Examples 5-7, wherein the set of parameters comprises microbial count.
The method of any of Examples 1-8, wherein: (a) the method further comprises: (i) incubating a second plurality of text mixtures, wherein: (A) each test mixture from the second plurality of test mixtures is inoculated using a second biological sample; (B) each test mixture from the second plurality of test mixtures has a concentration of a second antimicrobial agent; and (C) in each test mixture from the second plurality of text mixtures, the concentration of the second antimicrobial agent in that test mixture differs from the concentration of the second antimicrobial agent in each other test mixture from the second plurality of test mixtures; (ii) obtaining a second plurality of machine learning outputs by performing steps comprising, for each test mixture from the second plurality of test mixtures whose concentration of the second antimicrobial agent is greater than zero, providing a plurality of characteristic values determined for that test mixture to the machine learning model; and (b) for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero and each test mixture from the second plurality of test mixtures whose concentration of the second antimicrobial agent is greater than zero, the machine learning model to which the plurality of characteristic values determined for that test mixture is provided is the same machine learning model.
The method of Example 9, wherein the first antimicrobial agent and the second antimicrobial agent are different.
The method of any of Examples 9-10, wherein the first antimicrobial agent and the second antimicrobial agent are each classified in a group consisting of: (a) beta-lactam; (b) aminoglycoside; (c) fluoroquinolones; (d) carbapenems; and (e) tetracyclines.
The method of any of Examples 9-11, wherein the first antimicrobial agent and the second antimicrobial agent are each from a group consisting of: (a) cefepime; (b) cefotaxime; (c) ceftazidime; (d) gentamicin; (e) levofloxacin; (f) meropenem; and (g) tetracycline.
The method of any of Examples 9-12, wherein: (a) the first biological sample comprises a first microorganism; (b) the second biological sample comprises a second microorganism; and (c) the first microorganism is different from the second microorganism.
The method of any of Examples 9-13, wherein the first and second microorganisms are both gram-negative.
The method of any of Examples 9-14, wherein the first microorganism and the second microorganism are both from the group consisting of: (a) Acinetobacter baumannii; (b) Citrobacter freundii; (c) Enterobacter aerogenes; (d) Enterobacter cloacae; (e) Eschericia coli; (f) Klebsiella oxytoca; (g) Klebsiella pneumonia; (h) Proteus mirabilis; (i) Pseudomonas aeruginosa; (j) Pseudomonas fluorescens; (k) Providendia rettgeri; (l) Serratia marcescens; (m) Salmonella typhi; and (n) Salmonella paratyphi.
The method of any of Examples 1-15, wherein: (a) obtaining the plurality of machine learning outputs comprises, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, after providing the plurality of characteristic values determined for that test mixture to the machine learning model, obtaining an intermediate MIC prediction as a machine learning output for that test mixture; (b) generating the MIC prediction for the first biological sample comprises providing the plurality of machine learning outputs to a MIC creation function.
The method of Example 16, wherein the MIC prediction for the first biological sample is the median intermediate MIC prediction from the plurality of machine learning outputs.
The method of any of Examples 16-17, wherein, for at least one test mixture from the first plurality of test mixtures, the intermediate MIC prediction obtained as the machine learning output for that test mixture is a lower concentration of the first antimicrobial agent than the concentration of the first antimicrobial agent in that test mixture.
The method of any of Examples 16-18, wherein: (a) the machine learning model is a neural network having a plurality of output nodes; (b) each output node from the plurality of output nodes corresponds to a potential MIC; and (c) for each test mixture from the first plurality of test mixtures, the intermediate MIC prediction obtained as the machine learning output for that test mixture is the potential MIC corresponding to the output node having a highest value when the plurality of characteristic values determined for that test mixture are provided to the neural network.
The method of any of Examples 1-19, wherein, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, an identification of the first antimicrobial agent is provided to the machine learning model along with the plurality of characteristic values determined for that test mixture.
The method of any of Examples 1-14, wherein: (a) obtaining the plurality of machine learning outputs comprises, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, after providing the plurality of characteristic values determined for that test mixture to the machine learning model, obtaining a growth prediction as a machine learning output for that test mixture; (b) generating the MIC prediction for the first biological sample comprises identifying the test mixture with a lowest concentration of the first antimicrobial agent for which a growth prediction of inhibition was obtained as the machine learning output for that test mixture.
The method of Example 21, wherein: (a) the machine learning model is an ensemble comprising one or more decision trees, each having a plurality of leaf nodes, each leaf node connected to a parent node by a branch specifying growth or inhibition; and (b) for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, obtaining the growth prediction for that test mixture comprises predicting growth or inhibition based on whether there are more leaf nodes connected to parent nodes by branches specifying growth or whether there are more leaf nodes connected to parent nodes by branches specifying inhibition when the plurality of characteristic values for that test mixture are provided to the machine learning model.
The method of Example 21, wherein the machine learning model is a machine learning model trained to provide the growth prediction on an output node.
The method of any of Examples 9-14, wherein the first microorganism and the second microorganism are both from the group consisting of: (a) Acinetobacter baumannii; (b) Citrobacter freundii; (c) Enterobacter cloacae; (d) Eschericia coli; (e) Klebsiella oxytoca; (f) Pseudomonas aeruginosa; (g) Pseudomonas fluorescens; (h) Serratia marcescens; (i) Salmonella typhi; (j) Salmonella paratyphi; (k) Proteus mirabilis; and (l) Providencia rettgeri.
The method of any of Examples 1-21 or 23-24, wherein the set of parameters comprises: (a) microbial area; and (b) ratio of microbial area to microbial count.
The method of any of Examples 1-4 or 21, wherein: (a) the machine learning model is a decision tree classifier; (b) the method comprises: (i) determining an identification of a microbe comprised by the first biological sample; and (ii) selecting the decision tree classifier from a plurality of decision tree classifiers based on the identification of the microbe.
The method of Example 26, wherein the microbe comprised by the first biological sample has a type selected from a group of microbe types consisting of: (a) gram negative fermenters; (b) gram negative non-fermenters; (c) gram positive micrococcacaeae; and (d) gram-positive streptococcaceae.
The method of Example 27, wherein: (a) the type of the microbe comprised by the first biological sample is gram negative fermenters; and (b) the microbe comprised by the first biological sample is selected from a group of microbes consisting of: (i) Aeromonas hydrophilia; (ii) Citrobacter freundii; (iii) Citrobacter koseri; (iv) Enterobacter aerogenes; (v) Enterobacter cloacae; (vi) Eschericia coli; (vii) Klebsiella oxytoca; (viii) Klebsiella pneumoniae; (ix) Morganelle morganii; (x) Proteus mirabilis; (xi) Proteus penneri; (xii) Proteus vulgaris; (xiii) Providencia stuartii; (xiv) Providencia rettgeri; (xv) Salmonella paratyphi; (xvi) Salmonella typhi; (xvii) Serratia marcescens; (xviii) Shigella dysenteriae; (xix) Shigella flexneri; (xx) Shigella sonnei; (xxi) Vibrio cholerae; and (xxii) Yersinia enterocolitica.
The method of Example 27, wherein: (a) the type of the microbe comprised by the first biological sample is gram negative non-fermenter; and (b) the microbe comprised by the first biological sample is selected from a group of microbes consisting of: (i) Acinetobacter baumannii; (ii) Acinetobacer haemolyticus; (iii) Acinetobacter lwoffii; (iv) Moraxella species; (v) Pseudomonas aeruginosa; (vi) Pseudomonas alcaligenes; (vii) Pseudomonas fluorescens; (viii) Pseudomonas putida; and (ix) Stenotrophamonas maltophilia.
The method of Example 27, wherein: (a) the type of the microbe comprised by the first biological sample is gram-positive micrococcacaeae; and (b) the microbe comprised by the first biological sample is selected from a group of microbes consisting of: (i) Staphylococcus aureus; (ii) Staphylococcus capitis; (iii) Staphylococcus epidermidis; (iv) Staphylococcus haemolyticus; (v) Staphylococcus saprophyticus; (vi) Staphylococcus warneri; (vii) Staphylococcus simulans; and (viii) Staphylococcus lugdenensis.
The method of Example 27, wherein: (a) the type of the microbe comprised by the first biological sample is gram-positive streptococcaceae; and (b) the microbe comprised by the first biological sample is selected from a group of microbes consisting of: (i) Enterococcus avium; (ii) Enterococcus faecalis; (iii) Enterococcus faecium; (iv) Enterococcus gallinarum; (v) Enterococcus raffinosus; (vi) Streptococcus bovis; (vii) Streptococcus pyogenes; and (viii) Streptococcus pneumoniae.
The method of Example 26, wherein the microbe comprised by the first biological sample has a type selected from a group of microbe types consisting of: (a) enterobacteriaceae family; (b) pseudomonas family; (c) acinetobacter family; (d) micrococcacaeae family; and (e) streptococcaceae family.
The method of Example 26, wherein the first antimicrobial agent has a type selected from a group of antimicrobial types consisting of: (a) aminoglycoside; (b) ansamycin; (c) beta-lactam, penicillin class; (d) beta-lactam plus inhibitor combination; (e) carbapenems; (f) cephem; (g) fluoroquinolones; (h) folate pathway inhibitor; (i) fosfomycin; (j) glycopeptide; (k) lincosamide; (l) lipopeptide; (m) macrolide; (n) oxazolidinone; and (o) tetracyclines.
The method of Example 33, wherein: (a) the type of the first antimicrobial agent is aminoglycoside; and (b) the first antimicrobial agent is selected from a group of antimicrobial agents consisting of: (i) amikacin; (ii) gentamicin; and (iii) tobramycin.
The method of Example 33, wherein: (a) the type of the first antimicrobial agent is beta-lactam, penicillin class; and (b) the first antimicrobial agent is selected from a group of antimicrobial agents consisting of: (i) penicillin; and (ii) oxacillin.
The method of Example 33, wherein: (a) the type of the first antimicrobial agent is beta-lactam plus inhibitor combination; and (b) the first antimicrobial agent is selected from a group of antimicrobial agents consisting of: (i) amoxicillin+clavulanic acid; (ii) ampicillin+sulbactam; (iii) ceftazidime+avibactam; (iv) ceftolozane+tazobactam; (v) piperacillin+tazobactam; and (vi) ticarcillin+clavulanic acid.
The method of Example 33, wherein: (a) the type of the first antimicrobial agent is carbapenems; and (b) the first antimicrobial agent is selected from a group of antimicrobial agents consisting of: (i) doripenem; (ii) ertapenem; (iii) imipenem; and (iv) meropenem.
The method of Example 33, wherein: (a) the type of the first antimicrobial agent is cephem; and (b) the first antimicrobial agent is selected from a group of antimicrobial agents consisting of: (i) cefazolin; (ii) cefepime; (iii) cefotaxime; (iv) cefoxitin; (v) ceftaroline; (vi) ceftazidime; (vii) ceftriaxone; (viii) ceftizoxime; and (ix) cefuroxime.
The method of Example 33, wherein: (a) the type of the first antimicrobial agent is fluoroquinolones; and (b) the first antimicrobial agent is selected from a group of antimicrobial agents consisting of: (i) ciprofloxacin; and (ii) levofloxacin.
The method of Example 26, wherein: (a) the plurality of parameters consists of: (i) microbial area; (ii) difference in microbial area; and (iii) microbial growth; (b) the plurality of characteristic values comprises: (i) microbial area at a last imaging time from the plurality of imaging times; (ii) difference in microbial area from a second to last imaging time to the last imaging time; and (iii) microbial growth at the last imaging time.
A non-transitory computer readable medium encoding instructions for performing the method of any of Examples 1-40.
A computer system 49 configured with instructions for causing a biological testing system 1 to perform the method of any of Examples 1-40.
A biological testing system (1) comprising a processor (51) configured with a set of computer instructions operable, when executed, to cause the system (1) to perform a method comprising: (a) incubating a first plurality of test mixtures in a plurality of test wells (20) using an incubator subsystem (7) of the biological testing system (1), wherein: (i) each test mixture from the first plurality of test mixtures is inoculated using a first biological sample; (ii) each test mixture from the first plurality of test mixtures has a concentration of a first antimicrobial agent; (iii) in each test mixture from the first plurality of test mixtures, the concentration of the first antimicrobial solution in that test mixture differs from the concentration of the first antimicrobial solution in each other test mixture from the first plurality of test mixtures; (iv) the same first biological sample is used to inoculate each test mixture from the first plurality of test mixtures; and (v) the first plurality of test mixtures comprises a growth mixture having a concentration of the first antimicrobial agent of zero; (b) at a plurality of imaging times, wherein each of the imaging times takes place after incubation has begun, for each test mixture from the first plurality of test mixtures, capturing an image of that test mixture using an AST camera (35); (c) obtaining a plurality of machine learning outputs by the processor (51) performing steps comprising, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero: (i) determining a plurality of characteristic values for that test mixture, wherein: (A) each of the characteristic values corresponds to a parameter from a plurality of parameters; and (B) the plurality of characteristic values for that test mixture are determined based on images captured of that test mixture at the plurality of imaging times; and (ii) providing the plurality of characteristic values determined for that test mixture to a machine learning model; and (d) the processor (51) generating a MIC prediction for the first biological sample based on the plurality of machine learning outputs.
The biological testing system (1) of Example 43, wherein: (a) the plurality of imaging times comprises an earliest imaging time separated from onset of incubation by a first duration; (b) each imaging time from the plurality of imaging times except for the earliest imaging time is separated from its preceding imaging time by a second duration; and (c) the second duration is shorter than the first duration.
The biological testing system (1) of Example 44, wherein, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero: (a) the plurality of characteristic values for that test mixture comprises a first set of characteristic values and a second set of characteristic values; (b) the first set of characteristic values is based on images captured at a first time from the plurality of imaging times; (c) the second set of characteristic values is based on images captured at a second time from the plurality of imaging times; and (d) the plurality of parameters comprises a set of parameters, wherein each parameter from the set of parameters corresponds to one value from the first set of characteristic values and to one value from the second set of characteristic values.
The biological testing system of Example 45, wherein, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, the plurality of characteristic values for that test mixture comprises, for each imaging time from the plurality of imaging times, a rate of change value for each parameter from the set of parameters.
The biological testing system (1) of any of Examples 45-46, wherein, for each test mixture from the plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero: (a) the plurality of characteristic values comprises a growth set of characteristic values; (b) each parameter from the set of parameters corresponds to one characteristic value from the growth set of characteristic values for each imaging time from the plurality of imaging times; and (c) the characteristic values from the growth set of characteristic values are based on images captured of the growth mixture at the plurality of imaging times.
The biological testing system (1) of any of Examples 43-47, wherein: (a) the method further comprises: (i) incubating a second plurality of text mixtures, wherein: (A) each test mixture from the second plurality of test mixtures is inoculated using a second biological sample; (B) each test mixture from the second plurality of test mixtures has a concentration of a second antimicrobial agent; and (C) in each test mixture from the second plurality of text mixtures, the concentration of the second antimicrobial agent in that test mixture differs from the concentration of the second antimicrobial agent in each other test mixture from the second plurality of test mixtures; (ii) obtaining a second plurality of machine learning outputs by performing steps comprising, for each test mixture from the second plurality of test mixtures whose concentration of the second antimicrobial agent is greater than zero, providing a plurality of characteristic values determined for that test mixture to the machine learning model; and (b) for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero and each test mixture from the second plurality of test mixtures whose concentration of the second antimicrobial agent is greater than zero, the machine learning model to which the plurality of characteristic values determined for that test mixture is provided is the same machine learning model.
The biological testing system (1) of Example 48, wherein the first antimicrobial agent and the second antimicrobial agent are different.
The biological testing system (1) of any of Examples 48-49, wherein: (a) the first biological sample comprises a first microorganism; (b) the second biological sample comprises a second microorganism; and (c) the first microorganism is different from the second microorganism.
The biological testing system (1) of any of Examples 43-50, wherein: (a) obtaining the plurality of machine learning outputs comprises, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, after providing the plurality of characteristic values determined for that test mixture to the machine learning model, obtaining an intermediate MIC prediction as a machine learning output for that test mixture; (b) generating the MIC prediction for the first biological sample comprises providing the plurality of machine learning outputs to a MIC creation function.
The biological testing system (1) of Example 51, wherein, for at least one test mixture from the first plurality of test mixtures, the intermediate MIC prediction obtained as the machine learning output for that test mixture is a lower concentration of the first antimicrobial agent than the concentration of the first antimicrobial agent in that test mixture.
The biological testing system (1) of any of Examples 51-52, wherein: (a) the machine learning model is a neural network having a plurality of output nodes; (b) each output node from the plurality of output nodes corresponds to a potential MIC; and (c) for each test mixture from the first plurality of test mixtures, the intermediate MIC prediction obtained as the machine learning output for that test mixture is the potential MIC corresponding to the output node having a highest value when the plurality of characteristic values determined for that test mixture are provided to the neural network.
The biological testing system (1) of any of Examples 43-53, wherein, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, an identification of the first antimicrobial agent is provided to the machine learning model along with the plurality of characteristic values determined for that test mixture.
The biological testing system (1) of any of Examples 43-54, wherein: (a) obtaining the plurality of machine learning outputs comprises, for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, after providing the plurality of characteristic values determined for that test mixture to the machine learning model, obtaining a growth prediction as a machine learning output for that test mixture; (b) generating the MIC prediction for the first biological sample comprises identifying the test mixture with a lowest concentration of the first antimicrobial agent for which a growth prediction of inhibition was obtained as the machine learning output for that test mixture.
The biological testing system (1) of Example 55, wherein: (a) the machine learning model is an ensemble comprising one or more decision trees, each having a plurality of leaf nodes, each leaf node connected to a parent node by a branch specifying growth or inhibition; and (b) for each test mixture from the first plurality of test mixtures whose concentration of the first antimicrobial agent is greater than zero, obtaining the growth prediction for that test mixture comprises predicting growth or inhibition based on whether there are more leaf nodes connected to parent nodes by branches specifying growth or whether there are more leaf nodes connected to parent nodes by branches specifying inhibition when the plurality of characteristic values for that test mixture are provided to the machine learning model.
The biological testing system (1) of Example 55, wherein the machine learning model is a machine learning model trained to provide the growth prediction on an output node.
The biological testing system (1) of Example 43 wherein: (a) the machine learning model is a decision tree classifier; (b) the method comprises: (i) determining an identification of a microbe comprised by the first biological sample; and (ii) selecting the decision tree classifier from a plurality of decision tree classifiers based on the identification of the microbe.
The biological testing system (1) of Example 58, wherein: (a) the plurality of parameters consists of: (i) microbial area; (ii) difference in microbial area; and (iii) microbial growth; (b) the plurality of characteristic values comprises: (i) microbial area at a last imaging time from the plurality of imaging times; (ii) difference in microbial area from a second to last imaging time to the last imaging time; and (iii) microbial growth at the last imaging time.
V. Miscellaneous
It should be understood that, in the above examples and the claims, a statement that something is “based on” something else should be understood to mean that it is determined at least in part by the thing that it is indicated as being based on. To indicate that something must be completely determined based on something else, it is described as being “based EXCLUSIVELY on” whatever it must be completely determined by.
It should be understood that any of the examples described herein may include various other features in addition to or in lieu of those described above. By way of example only, any of the examples described herein may also include one or more of the various features disclosed in any of the various references that are incorporated by reference herein.
It should be understood that any one or more of the teachings, expressions, embodiments, examples, etc. described herein may be combined with any one or more of the other teachings, expressions, embodiments, examples, etc. that are described herein. The above-described teachings, expressions, embodiments, examples, etc. should therefore not be viewed in isolation relative to each other. Various suitable ways in which the teachings herein may be combined will be readily apparent to those of ordinary skill in the art in view of the teachings herein. Such modifications and variations are intended to be included within the scope of the claims.
It should be appreciated that any patent, publication, or other disclosure material, in whole or in part, that is said to be incorporated by reference herein is incorporated herein only to the extent that the incorporated material does not conflict with existing definitions, statements, or other disclosure material set forth in this disclosure. As such, and to the extent necessary, the disclosure as explicitly set forth herein supersedes any conflicting material incorporated herein by reference. Any material, or portion thereof, that is said to be incorporated by reference herein, but which conflicts with existing definitions, statements, or other disclosure material set forth herein will only be incorporated to the extent that no conflict arises between that incorporated material and the existing disclosure material.
Having shown and described various versions of the present invention, further adaptations of the methods and systems described herein may be accomplished by appropriate modifications by one of ordinary skill in the art without departing from the scope of the present invention. Several of such potential modifications have been mentioned, and others will be apparent to those skilled in the art. For instance, the examples, versions, geometrics, materials, dimensions, ratios, steps, and the like discussed above are illustrative and are not required. Accordingly, the scope of the present invention should be considered in terms of the following claims and is understood not to be limited to the details of structure and operation shown and described in the specification and drawings.
Number | Date | Country | |
---|---|---|---|
62894000 | Aug 2019 | US | |
62786678 | Dec 2018 | US |
Number | Date | Country | |
---|---|---|---|
Parent | PCT/US19/67903 | Dec 2019 | US |
Child | 17361781 | US |