Patent Application
20140236625
The present disclosure relates generally to the use of social networking techniques in a medical institution, more specifically identifying a team of clinicians from the clinicians at a medical institution using a social graph with a set of nodes and a set of edges that establish relationships between the nodes.
A traditional social graph is a social structure made of individuals, groups, entities, or organizations generally referred to as “nodes.” Which are connected by one or more specific types of interdependency. Social graph analysis views social relationships in terms of network theory consisting of nodes and edges. Nodes are the individual actors or data points and edges are the relationships between the nodes. The resulting network-based structures are often very complex. There can be many kinds of edges between nodes. In its simplest form, a social graph or social network is a map of all of the relevant edges between all the nodes being studied.
Social graphs are generally hosted on computer systems. The computer systems are connected to various local and wide area computer networks allowing users to interact with the information located on various computer systems. Users may enter personal information, view information about others, search for information, and update information about others.
This disclosure relates to a method, a system, and a program that use social networking techniques to identify teams of clinicians within a medical institution.
The method includes accessing a social graph with a computer system including a clinician node for each clinician in the institution. An edge is created for each organizational (formal) relationship and each professional (informal) relationship between the clinicians. Patient data is collected for each patient treated at the institution and entered into the computer system. The computer system associates each patient with a patient node in the social graph. Then the computer system creates an edge between each patient node and an element node which corresponds to each element of patient data corresponding to the patient. The computer system creates another edge between each patient node and the clinician node corresponding to the treating clinician. The computer system creates another edge between each element node of patient data and each clinician node corresponding to the treating clinician. The computer system also monitors each usage of the patient data by each clinician and creates an edge between each clinician node and the element node of patient data. Next, the computer system assigns a weight to each connection between the nodes. The weight of each connection relates to the number of edges connecting each node either directly or indirectly through intermediate nodes. The weighting may relate to the characteristics of each edge. The computer system can be configured to give greater weight to edges possessing certain characteristics. For example, formal organizational relationships may be weighted more heavily than informal professional relationships. The computer system creates a first data set that scores each clinician node that is connected to a chosen node. The computer system displays each clinician that corresponds to a clinician node with a score over a threshold score. Each displayed node may be ranked by the score.
The present disclosure can also be embedded in a computer program product, which comprises all the features enabling the implementation of the methods described herein, and which when loaded in a computer system is able to carry out these methods.
By identifying teams of clinicians, relationships between the clinicians may be improved from the identification of unknown similarities by particular clinicians. When a team of clinicians is identified, the team may be assembled as a clinical team for a given patient, a group of patients, an advisory board for a particular condition, a panel discussion, or more informal teams such as a luncheon. By identifying teams of clinicians and improving clinician relationships, either professional relationships or non-professional relationships, the communication between clinicians will be improved. The improvement in communication may result in improved clinical knowledge among the clinicians and ultimately improved patient outcomes. The dynamic and organic nature of the development of teams by these methods may result in the creation of teams that transcend formal organizational boundaries to provide a level of care that might otherwise be limited by those formal boundaries. The identification of these teams may provide valuable insights leading to revisions of an institution's formal organizational structure, resulting in new organizational structures that are optimized for patient care and improved outcomes. Identifying teams of clinicians may also allow patients to identify a team of clinicians which have experience or expertise with a particular element of patient data. This identified team may he used to form a specialized team to treat the patient or for the patient to seek a second opinion. Identifying a team of clinicians with experience or expertise with a particular element of patient data may also be used by the institution to form a research team for the element of patient data such as a specific disease.
Certain embodiments of the present disclosure may include some, all, or none of the above advantages. One or more other technical advantages may be readily apparent to those skilled in the art for the figures, descriptions, and claims included herein. Moreover, while specific advantages have been enumerated above, various embodiments may include all, some, or none of the enumerated advantages.
There are shown in the drawings embodiments, which are exemplary, it being understood that the disclosure is not limited to the precise arrangements and instrumentalities shown.
The disclosure herein provides among other things a method, system, and a program for identifying a team of clinicians in a medial institution. In this disclosure, the system can interpret the data streams sent from specified machines and transport the information contained within the data streams to a networked element. This networked element can transform the information into a machine-independent data schema. The information provided by medical devices monitoring or treating patients and other patient data, such as pharmacological data and laboratory results can be integrated within a single presentation device. For example, patient data can be physiologic, laboratory, pharmacy, and other patient-centric data for a given patient. Additionally, physiologic data can be analyzed by other health-related systems. For example, clinical research facilities can access stored patient data that has been sanitized so that patient privacy information and identification has been removed.
As used herein, bedside refers to an environment in close proximately to a patient being treated. Items placed within a bedside environment should be near enough to the patient that a physician treating the patient can access the items while treatment is being performed. It should be noted that a bedside environment need not include a bed. For example, instead of a bed, a patient can be contained within an incubator, an ambulance, a gurney, a cot, an operating table, and the like. Similarly, an apparatus that can provide information to an individual, such as a physician, located within the bedside environment can be considered bedside apparatus even if necessary portions of the apparatus are in a location remote from the patient (e.g., servers, databases, etc.). As used herein, clinician refers to any personal at a medial institution including but not limited to physicians, nurses, laboratory technicians, and administrators. As used herein, medical institution refers to any singular or group of medical providers providing medical services to patients including but not limited to hospitals, clinics, medical research facilities, or hospital networks.
Referring now to
The system may include an interface which collects elements of clinician and patient data. The interface may be a keyboard, a touch screen, an integrated system 1105 (
Integrated system 1105 may automatically collect patient data and transmit the patient data to processor 1002. Integrated system 1105 may collect the patient data directly from medical or bedside devices 1205 which may be attached to patients. Integrated system 1105 may interface with medical devices 1205 manufactured or produced by different companies using different data protocols and convert the patient data from each medical device 1205 into machine independent data for the medical institution. The machine independent data may be stored in centralized data repository 1230.
The system may include a network 1200 and a network interface 1016 coupling processor 1002 to network 1200. Network 1200 may include a first trusted network 1210 and a second trusted network 1290 connected to first trusted network 1210 by a wide-area network 1260. Each component of the system may be part of either first trusted network 1210 or second trusted network 1290. In some embodiments, the data transmitted between first trusted network 1210 and second trusted network 1290 through wide-area network 1260 is encrypted or secured such that the data is only decipherable by components within each trusted network 1210, 1290.
Mass storage component 1018 may be coupled to processor 1002 and may store social graph 10. Mass storage component 1018 may be a single mass storage device such as a hard drive or a solid-state drive. Mass storage component 1018 may also be an array of mass storage devices. Mass storage component 1018 may be part of central data repository 1230. Mass storage component 1018 may be part of second trusted network 1290 and processor 1002 may be part of first trusted network 1210.
Like the clinicians 101-105, discussed above, each individual patient may also be associated with a patient node 201, 202. 203, as shown in
A method 300 may also be employed to create an edge between each element node 301-307 and each clinician node 101-105 corresponding to the clinician assigned or treating the patient as shown in
Edges may also be created by a method 500 shown in
In an embodiment of this disclosure, social graph 10 may be used to identify or create a team of clinicians associated with elements of patient data. Social graph 10 may contain edges between clinician nodes and edges between element nodes and clinician nodes that may not be readily apparent to the medical institution. By utilizing social graph 10 to identify or create teams of clinicians, patients treated by the medical institution may experience improved care and improved outcomes.
Referring now to
Next, each edge connecting the chosen node 302 to each clinician node 101-105 is identified. The edges may be grouped 621, 622, 623 representing each connection between chosen node 302 and each clinician node 101-105. A score 631, 632, 633, 634, 635 is then created to represent the relevance or strength of the connection between each clinician node 101-105 and chosen node 302. Each edge may be weighted by the relevance of the method 100, 200, 300, 500 which created the edge. A weight may be assigned, using computer system 1000, to each edge within the group of edges 621, 622, 623 connecting each of the plurality of nodes 101-105, 201-203, and 301-307. For example, the weight may be based on the number of edges between each of the plurality of nodes. Alternatively, the weight given to each edge may also account for the number of inquiries by a single clinician, the time that has elapsed from when the edge was created, or the type of usage that created the edge. The effect of this weighting may be represented in a graphic user interface (GUI) viewable by the clinician. For example, if the inquiry by the clinician is with respect to other treatments being employed in a particular medical facility, a treatment option (element node 301-307) that has multiple edges connecting many patients and other physicians may be given a greater weight, and therefore a higher ranking in the results to the inquiry.
In some embodiments, the chosen node 302 includes multiple chosen nodes of the plurality of nodes. The first data set 630 scores each connection between clinician nodes 101-105 and each of the multiple chosen nodes. The score is represents the relevance or strength of the connection between each clinician node 101-105 and each of the multiple chosen nodes. In certain embodiments, the algorithm performs the calculations in aggregate for each of the multiple chosen nodes in a single process which results in a single data set.
According to embodiments of the present disclosure, a factor may be used to weight each edge within a group of edges. The factor may reflect the relevance of the edge. An exemplary example is the amount of time that has passed since the edge was created. The factor may be reduced as the amount of time increases from a range of about 1 to about 0. The factor may be represented as a percentage with 1 or 100% being most relevant to 0 or 0% being not at all relevant. Different criteria may be used to determine a factor for each edge or group of edges. Again, this factor may alter the ordering or importance given to results from an inquiry of the system that may be presented to the clinician following such an inquiry. Alternatively, the GUI viewable by a clinician participating in the system described herein, may be more closely tied to depicting the social graph 10, in such instances the weight of a connection may be displayed by differing line types. Bold colored solid lines may depict connection of greater weight and therefore of greater relevance to the clinician, whereas dotted lines may depict only tangential or lower relevance connections between clinician, patient, and element (e.g., treatment regimen) nodes.
First data set 630 represents the weight of each group of edges 621, 622, 623 connecting each clinician node 101-105 to the chosen node 302. In this example, first data set 630 includes scores 631, 632, 633, 634, and 635 corresponding to clinician nodes 101, 102, 103, 104, and 105 as shown in
A clinician team is then formed using first data set 630. Each clinician having a score 631, 632, 633, 634, 635 over a threshold score is displayed. The threshold score may be selected and inputted by the searching individual or automatically selected by computer system 1000. The threshold score represents a required strength or relevance of the connection between each clinician and the chosen node 302. In this example, the threshold score is 1. Accordingly, only the clinicians corresponding to clinician nodes with scores over 1 in first data set 630 will be displayed.
The display may be in the form of a screen display 700 (
Some embodiments involve the use of an algorithm running on computer system 1000 to identify potential members of teams of clinicians for a particular purpose. It is contemplated that this will be particularly useful where the clinicians themselves have a low connection score between each other (i.e., clinician nodes 101-105), but have a high connection score with a chosen node (e.g., a patient node 201-203, or an element node 301-307). This may be particularly useful in instances where common or well known treatment options have been less than completely successful and research regarding further treatment options is desired. One way of conducting such research might be by searching for clinicians treating the identified disease, and then identifying different treatment regime nodes. The algorithm may run continually or run at specified times. In one embodiment the algorithm creates a second data set that scores each connection between each clinician node. The algorithm identifies a score in the second data set is below a desired score. The low score signifies a weak or non-existent relationship between a first clinician and a second clinician, for example they are associated with different medical facilities, in different countries, or are in different disciplines. The algorithm then searches social graph 10 for a chosen node (e.g., disease type) having a first data set 630 where both the first clinician and the second clinician have a sufficiently high score. In this embodiment, the first and second clinicians are displayed along with their connections to the chosen node.
It is contemplated that the formation of formal and informal organizational relationships that develop may also be particularly useful in the establishment of previously unidentified relationships between clinicians. Prior to identification by the algorithm these relationships may not be readily apparent to an observer but, if developed, may provide value in terms of patient care, the advancement of clinical knowledge, or the optimization of institutional structures. For example, an observer may assume that a strong relationship exists between one clinician and a second clinician because they practice in the same discipline and within the same division of an organizational structure. A third clinician may practice in a different discipline and within a different organizational division than the first clinician, leading an observer to assume a weak or non-existent relationship between the first and third clinicians. The algorithm may identify that the total score of a large number of low-weighted edges between nodes (e.g. treatment regimens, patients, and professional interests) shared by the first and third clinicians may exceed the score of the single high-weighted edge representing the existing formal organizational relationship shared by the first and second clinicians. This detection of a previously unknown relationship may be used to restructure the organization to bring the first and third clinicians, and other similarly related clinicians detected by the algorithm, into more formal relationships. This knowledge may also be used less formally, as when bringing the first and second clinicians, and other similarly related clinicians detected by the algorithm, into teams convened around a particular patient for the duration of a particular condition or treatment plan.
In some embodiments, method 600 is repeated with multiple chosen nodes of the plurality of nodes. Method 20 may be applied to identify a team of clinicians by displaying each clinician with a combined score from the multiple data sets that exceeds a threshold score, as described above. In certain embodiments, the algorithm performs the calculations involving the multiple chosen nodes in aggregate which results in a single data set.
As a result, networks of clinicians, patients, diseases, treatment options, and other elements can be correlated and made available to individual clinicians, administrators, and even patients. Other uses may include identifying other clinicians treating an individual patient, identifying clinicians who are particularly skilled with a treatment regimen, identifying connections based on schooling, discipline, alternative treatments, etc., automatically assigning clinician teams for a patient, developing larger multi-disciplined clinician networks and others as will be understood by those of skill in the art.
The various GUIs disclosed herein are shown for purposes of illustration only. Accordingly, the present disclosure is not limited by the particular GUI or data entry mechanisms contained within views of the GUI. Rather, those skilled in the art will recognize that any of a variety of different GUI types and arrangements of data entry, fields, selectors, and controls can be used to access system. Further, the computing devices depicted herein can be functionally and/or physically implemented with other computing devices and the disclosure should not be limited by the particular exemplary configuration shown.
The present disclosure can be realized in hardware, software, or a combination of hardware and software. The present disclosure can be realized in a centralized fashion in one computer system or in a distributed fashion where different elements are spread across several interconnected computer systems. Any kind of computer system or other apparatus adapted for carrying out the methods described herein is suited. A typical combination of hardware and software can be a general-purpose computer system with a computer program that, when being loaded and executed, controls the computer system such that it carries out the methods described herein.
The present disclosure also can be embedded in a computer program product, which comprises all the features enabling the implementation of the methods described herein, and which when loaded in a computer system is able to carry out these methods. Computer program in the present context means any expression, in any language, code or notation, of a set of instructions intended to cause a system having an information processing capability to perform a particular function either directly or after either or both of the following: a) conversion to another language, code or notation; b) reproduction in a different material form.
This disclosure can be embodied in other forms without departing from the spirit or essential attributes thereof. Accordingly, reference should be made to the following claims, rather than to the foregoing specification, as indicating the scope of the disclosure.
