The disclosure relates generally to medical visualization and in particular to a system and method that generates imagery for a state of the patient so that the state of the patient can be rapidly visualized.
Physicians are besieged with information overload and a lack of time to see patients. For example, a typical US office-based doctor can spend 7-10 minutes on average per patient, and may see 30 patients per day. In critical settings, such as the ICU, there may be more time spent per patient, but there is a flood of information from multiple sensors, monitors, and ventilators, for example, and often decisions of life-or-death importance must be made within minutes to seconds.
Today's electronic medical records systems present raw information to the doctor, such as a list of individual diagnoses, a list of current medications, and a list of individual lab results. This is wholly insufficient for time-pressed physicians who must read and interpret each individual data point into a mental picture of the state of the patient. This process is fraught with error and is humanly unscalable as the volume of information available for a patient grows without bound. Numbers and words grow exponentially without the ability to cross-correlate or interpret them in a simple, visualizable way that fosters insight into decision making.
Systems exist that provide an anatomical avatar that shows a body part and may have pieces of medical data, such as X-rays, etc. associated with the body part that a doctor/user can access. However, these anatomical avatar systems do not interpret the pieces of medical data nor provide a visual way to assess the state of the patient or the state of a body part/organ system of the patient.
Thus, it is desirable to provide a physiological imagery generating system and method by providing a visualization of the physiology, and it is to this end that the system and method are directed.
The system and method are particularly applicable to a web-based system and it is in this context that the system and method will be described. It will be appreciated, however, that the system and method has greater utility because: 1) the system and method can be implemented in various manners that are within the scope of the system so that the system and method are not limited to the example web-based system described below; and 2) the system and method can be used to generate various different types of physiological imagery and the system and method are not limited to the examples provided below.
The system and method abstracts all medical data points/medical parameters for a patient into visualizable physiologic parameters that are independent of any single data point, and represent the synthesis of multiple related data points into a coherent interpretation of physiology and derangement due to disease. Additionally, the synthesis is performed in real-time, so that the arrival of any single data point can change the entire visualization schema without any human intervention, research, or request. For example, arrival of a profoundly elevated liver function test which infers injury to the bile duct can change the entire interpretation of the function of the organ (in this case, the exocrine function of the liver). Moreover, the physiologic image can be decomposed into reasoned elements so that the doctor can understand the basis for the imagery in an intuitive fashion.
Each physician unit 102 may be a processing unit based device that has sufficient processing power, memory and wireless/wired connectivity circuitry to interact with the physiological imagery unit 104. For example, each physician unit 102 may be a personal computer, a terminal, a laptop computer, a mobile device, a pocket PC device, a smartphone (RIM Blackberry, Apple iPhone, etc.), tablet computer, a mobile phone, a mobile email device, etc. Each physician unit 102 may also include an local physiological image unit 111, such as units 111a, 111b, . . . , 111n, that may be, in the exemplary web-based client/server implementation, an physiological imagery application (a plurality of lines of computer code stored in the physician unit and executed by the processing unit of the physician unit) that generates and/or displays physiological imagery (See
The physiological imagery unit 104, in one implementation may be implemented as one or more well known server computers (with the typical well known server computer components) that execute one or more pieces of software. In the web-based example shown in
The system 109 may further include a data store 114, implemented as one or more databases hosted on one or more database servers in the illustrated implementation (that may be part of the unit 104 or remotely located from the unit 104), that includes a plurality of health records 106 for a plurality of patients (which may also be stored in an electronic medical record system that is remote from the system 109), an physiological image generator rules store 108 that stores that various physiological imagery and rules and the physiological images generated for each physiological condition with the understanding that additional physiological images for additional physiological conditions and additional rules for physiological images may be added into the store 108. The system 109 may also include a user portion 116 that may include various pieces of information about the users of the system. For example, the user portion may have a record associated with each physician/user that uses the system that includes, for example, the preferences for each physician/user of the system.
In addition to the web-based implementation described above, the system may also be implemented as a client/server model, a hosted system model, a standalone computer executing a piece of physiological imagery software (that may be loaded onto a piece of media) or software as a service model in which a physician may send the one or more parameters to the physiological imagery unit 104 that then sends the generated physiological imagery back to the physician unit.
The system 109 may be used to generate physiological imagery in various medical areas. For example, the system 109 may be used to generate physiological imagery to visualize: (1) instantaneous health risk (IHR) according to an organ system, (2) a modifiable health risk (MHR) according to an organ system, (3) a therapeutic analysis of the value of current medications, and (4) an alternative diagnosis probability system. By way of example, an color coded image of an organ might intensify when a combination of lab results appear within a specified time interval. Alternatively, an image might abstract the tolerability of a medication by numerically amalgamating the number and severity of multiple side effects into a single score that can be visualized in a graphical, colorized format. The seminal aspect is therefore consolidation of individual data points into a physiologically interpreted view of the whole.
In operation, the system 109 synthesizes disparate information about a physiological condition in real time into a visual image (the physiological imagery) that is understandable within seconds without the need to read any numbers or text. This interpretive speed does not exist in current electronic medical records and makes the current practice of medicine highly inefficient and riskier due to the time and mental effort required by the physician to create a mental abstraction of the state of the patient. In contrast, the system 109 synthesizes the disparate data about the state of the patient and generates the physiological imagery that visually conveys the state of the patient. Now, several examples of the physiological imagery and the rules to generate the particular physiological imagery are described below. However, the physiological imagery system is not limited to the examples described below nor to the particular states of the patient shown in the examples.
In the system 109, a characteristic of the physiological imagery may be changed to denote different states of the patient or the organ, etc that allow a user to quickly look at the physiological imagery and determine the state of the patient. The characteristic may be any feature that can be changed to allow someone to visually distinguish between the different states of the patient or the organ, body part, etc. For example, the characteristic may be a color change, a size change, a contrast change, etc. . . . . In one implementation, the characteristic of the physiological image may be the color of the physiological image wherein a first color 124a indicates a first state of the patient (such as mild injury to the organ as shown in
The system may have one or more sets of rules (stored in the store 108) for each physiological imagery that determines how the characteristic of the physiological imagery is changed to reflect the different states of the patient, body part, organ system, etc. Each rule may use one or more parameters of the patient state or organ system state, such as alkaline phosphatase (AP) for the bile duct and gall bladder, to determine the characteristic of the physiological imagery. For example, for the gallbladder and bile duct organ system shown in
Light red=(AP 2-3× normal) AND (GGT 2-3× normal) AND (CB<2 times normal) which indicates mild injury of the gallbladder and bile duct organ system;
Medium red=(AP 3-4× normal) AND (GGT 3-4× normal) AND (CB<2 times normal) which indicates moderate injury of the gallbladder and bile duct organ system; and
Bright red=(AP>4× normal) AND (GGT>4× normal) AND (CB<2 times normal) which indicates severe injury of the gallbladder and bile duct organ system.
Using the system, a physician can quickly look at the physiological imagery to determine the state of the patient or an organ system of the patient as shown in
When the physiological imagery is displayed, the physician may click or ‘mouse-over’ the physiological imagery to see the underlying reasoning, the rules for the physiological imagery and the one or more parameters used to generate the physiological imagery (shown in
As another example of the analysis of drug therapy, if the patient were to suddenly have the arrival of a positive pregnancy test results (a parameter that is received by the system 109), the bar for drug safety would become 100 (long and bright red for example) because lisinopril is very dangerous (teratogenic leading to mutations) for a fetus. As above, the physiological imagery is rendered in real-time for the patient and are most commonly multi-factorial Boolean logic expressions (e.g., A or B and not C within time X) which provide a weighted, interpretive image of the potential to beneficially improve care for the example shown in
In the example shown in
In the above examples, it can be seen that a doctor caring for a patient with multiple co-morbidities and/or taking multiple medications and/or having multiple surgeries can be assessed in a matter of seconds without reading of raw text or numbers. The specifics of the formulas used underneath each imagery rule (e.g., the combination of lab ranges, physical findings, and patterns for bile duct injury in
The categories of interest described above are basic to the practice of medicine. For example, for any disease the broadest scope of possible interventions are (1) medications, (2) procedures including surgery, (3) lifestyle changes, and (4) monitoring (by office visits and/or lab tests). There are no other fundamental treatment categories, so virtually all diseases can be represented using this visually interpretative fashion. In addition, similar universal categories are standards for medication analysis, regardless of location. That is, all medications are intrinsically evaluated by physicians for (1) efficacy, (2) safety, (3) tolerability, and (4) affordability in every case they are used. What has been missing to date is the rapid, real-time synthesis of all pertinent information to distill these analyses down to simple, visualizable abstract images which support and display the underlying physiologic reasoning as to how they were generated, instantly and without physician effort.
In summary, the physiological imagery system and method allows a physician or other medical health care worker to quickly visualize (based on multiple different pieces of medical information/parameters in real-time) a possible new problem with an organ system (an example of which is shown in
While the foregoing has been with reference to a particular embodiment of the system and method, it will be appreciated by those skilled in the art that changes in this embodiment may be made without departing from the principles and spirit of the system and method, the scope of which is defined by the appended claims.
This application claims the benefit under 35 USC 119(e) and the priority under 35 USC 120 to U.S. Provisional Patent Application Ser. No. 61/171,628 filed on Apr. 22, 2009 and entitled “Physiological Imagery Generator System and Method”, the entirety of which is incorporated by reference herein.
Number | Name | Date | Kind |
---|---|---|---|
6032119 | Brown et al. | Feb 2000 | A |
6584445 | Papageorge | Jun 2003 | B2 |
6692258 | Kurzweil et al. | Feb 2004 | B1 |
7120298 | Staehle | Oct 2006 | B1 |
8032394 | Ghouri | Oct 2011 | B1 |
20020107705 | Boucher | Aug 2002 | A1 |
20030018245 | Kaufman et al. | Jan 2003 | A1 |
20040122787 | Avinash et al. | Jun 2004 | A1 |
20060085223 | Anderson et al. | Apr 2006 | A1 |
20060089543 | Kim et al. | Apr 2006 | A1 |
20070088525 | Fotiades et al. | Apr 2007 | A1 |
20070106535 | Matsunaga | May 2007 | A1 |
20070118399 | Avinash et al. | May 2007 | A1 |
20080015893 | Miller et al. | Jan 2008 | A1 |
20080015894 | Miller et al. | Jan 2008 | A1 |
20080077019 | Xiao et al. | Mar 2008 | A1 |
20080088629 | Lorenz et al. | Apr 2008 | A1 |
20080097784 | Miller et al. | Apr 2008 | A1 |
20080126117 | Miller et al. | May 2008 | A1 |
20080130968 | Daw et al. | Jun 2008 | A1 |
20080235049 | Morita et al. | Sep 2008 | A1 |
20080253628 | Matsue et al. | Oct 2008 | A1 |
20080306353 | Douglas et al. | Dec 2008 | A1 |
20090054755 | Shiibashi | Feb 2009 | A1 |
20090192821 | Park et al. | Jul 2009 | A9 |
20090264814 | Krijnsen et al. | Oct 2009 | A1 |
20090299767 | Michon et al. | Dec 2009 | A1 |
20090315259 | Riley | Dec 2009 | A1 |
20100010827 | Fueyo et al. | Jan 2010 | A1 |
20100049547 | Mirza et al. | Feb 2010 | A1 |
20100092055 | Matsuda | Apr 2010 | A1 |
20110298806 | Rasmussen | Dec 2011 | A1 |
Number | Date | Country | |
---|---|---|---|
61171628 | Apr 2009 | US |