Disease risk index application across an intensive care unit stay

Abstract

A controller includes a memory that stores instructions and a processor that executes the instructions. When executed by the processor, the instructions cause the controller to repeatedly obtain patient data in real-time in a continuous window; and repeatedly apply a disease risk prediction model in the continuous window from before a clinical event predicted by the disease risk prediction model, during the clinical event, and after the clinical event predicted by the disease risk prediction model.

Description

DISEASE RISK INDEX APPLICATION ACROSS AN INTENSIVE CARE UNIT STAYCROSS-REFERENCE TO RELATED APPLICATIONSThis patent application claims the priority benefit under 35 U.S.C. § 119(e) of U.S. Provisional Application No. 63 / 532,751, filed on August 15, 2023, the contents of which are herein incorporated by reference.BACKGROUND

[0001] Disease risk prediction models have been developed to provide early prediction of acute clinical events, such as the hemodynamic stability index (HSI) developed to predict the onset of hemodynamic instability a few hours earlier, the sepsis prediction algorithms developed to predict the onset of sepsis, and the infection risk index (IRI) developed to predict the onset of hospital acquired infection. Acute clinical events such as these are often accompanied by severe hypotension that presents a risk of a shock state, and which may require treatment with a vasopressor. These risk prediction models may be applied before the onset of clinical events and result in a single score to indicate the patient state. Risk prediction models have been developed to provide early warnings before the onset of clinical events. The risk prediction models are naturally used before the clinical events predicted by the disease risk prediction models. However, patients may experience multiple clinical events in an intensive care unit, and risk prediction models are not standardly used during or after clinical events.

[0002] In practice, the onset of clinical events may be determined by the initiation of clinical interventions. For hemodynamic instability, onset time is determined by the start of hemodynamic interventions. Hemodynamic interventions may be aggressive in order to resuscitate a patient from a hypotension state, as these patients frequently are at risk cardiogenic shock if they have a history of cardiac arrest or loss of blood. Hemodynamic interventions may include providing large amounts of fluids, packed-red-blood-cells (PRBCs) and vasopressors. Vasopressors are substances used to raise low blood pressure. These clinical interventions may last for hours or even days depending on the patient’s response to the treatment. A patient can experience multiple episodes of clinical events during the entire intensive care unit (ICU) stay, such as multiple events of hemodynamic instability. Even if the patient’s hemodynamiccondition can be improved after an initial intervention, the patient might still experience more episodes of hemodynamic instability events. Disease risk index application across an intensive care unit stay is provided to improve monitoring and treatment of patients throughout an intensive care unit stay.SUMMARY

[0003] According to an aspect of the present disclosure, a controller includes a memory that stores instructions; and a processor that executes the instructions. When executed by the processor, the instructions cause the controller to repeatedly obtain patient data in real-time in a continuous window; and repeatedly apply a disease risk prediction model in the continuous window from before a clinical event predicted by the disease risk prediction model, during the clinical event, and after the clinical event predicted by the disease risk prediction model.

[0004] According to another aspect of the present disclosure, a method of continuously applying a disease risk prediction model includes repeatedly obtaining patient data in real-time in a continuous window; and repeatedly applying a disease risk prediction model in the continuous window from before a clinical event predicted by the disease risk prediction model, during the clinical event, and after the clinical event predicted by the disease risk prediction model.BRIEF DESCRIPTION OF THE DRAWINGS

[0005] The example embodiments are best understood from the following detailed description when read with the accompanying drawing figures. It is emphasized that the various features are not necessarily drawn to scale. In fact, the dimensions may be arbitrarily increased or decreased for clarity of discussion. Wherever applicable and practical, like reference numerals refer to like elements.

[0006] FIG. 1 A illustrates a patient monitor for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0007] FIG. IB illustrates a system for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0008] FIG. 2 illustrates another system for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0009] FIG. 3 illustrates a method for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0010] FIG. 4 illustrates an interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0011] FIG. 5 illustrates another interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0012] FIG. 6 illustrates another interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0013] FIG. 7 illustrates another interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0014] FIG. 8 illustrates another interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0015] FIG. 9 illustrates a computer system, on which a method for disease risk index application across an intensive care unit stay is implemented, in accordance with another representative embodiment.DETAILED DESCRIPTION

[0016] In the following detailed description, for the purposes of explanation and not limitation, representative embodiments disclosing specific details are set forth in order to provide a thorough understanding of embodiments according to the present teachings. However, other embodiments consistent with the present disclosure that depart from specific details disclosed herein remain within the scope of the appended claims. Descriptions of known systems, devices, materials, methods of operation and methods of manufacture may be omitted so as to avoid obscuring the description of the representative embodiments. Nonetheless, systems, devices, materials and methods that are within the purview of one of ordinary skill in the art are within the scope of the present teachings and may be used in accordance with the representative embodiments. It is to be understood that the terminology used herein is for purposes of describing particular embodiments only and is not intended to be limiting. Definitions and explanations for terms herein are in addition to the technical and scientific meanings of the terms as commonly understood and accepted in the technical field of the present teachings.

[0017] It will be understood that, although the terms first, second, third etc. may be used herein to describe various elements or components, these elements or components should not be limited by these terms. These terms are only used to distinguish one element or component from another element or component. Thus, a first element or component discussed below could be termed a second element or component without departing from the teachings of the inventive concept.

[0018] As used in the specification and appended claims, the singular forms of terms ‘a’, ‘an’ and ‘the’ are intended to include both singular and plural forms, unless the context clearly dictates otherwise. Additionally, the terms "comprises", and / or "comprising," and / or similar terms when used in this specification, specify the presence of stated features, elements, and / or components, but do not preclude the presence or addition of one or more other features, elements, components, and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0019] Unless otherwise noted, when an element or component is said to be “connected to”, “coupled to”, or “adjacent to” another element or component, it will be understood that the element or component can be directly connected or coupled to the other element or component, or intervening elements or components may be present. That is, these and similar terms encompass cases where one or more intermediate elements or components may be employed to connect two elements or components. However, when an element or component is said to be “directly connected” to another element or component, this encompasses only cases where the two elements or components are connected to each other without any intermediate or intervening elements or components.

[0020] The present disclosure, through one or more of its various aspects, embodiments and / or specific features or sub-components, is thus intended to bring out one or more of the advantages as specifically noted below.

[0021] As described herein, a need exists to apply a disease risk index continuously on the same patient continuously during an entire intensive care unit stay, including after the onset of clinical events. The use of a disease risk index after the onset of clinical events may help clinicians determine how to treat a patient, but also to evaluate the effectiveness of the treatment. HSI is used as a running example to illustrate how HSI may be applied to 1) guide the clinical interventions during the clinical events; and 2) evaluate the effectiveness of the clinicalinterventions after the clinical events. This same analysis framework can be applied to other disease risk prediction models to determine their usefulness during the entire intensive care unit stay.

[0022] FIG. 1 A illustrates a patient monitor for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0023] In FIG. 1A, the patient monitor 110 includes a controller 150 and a display 180. The controller 150 includes a memory 151 that stores instructions and a processor 152 that executes the instructions. A computer that can be used to implement the patient monitor 110 is depicted in FIG. 9, though the patient monitor 110 may include more or fewer elements than depicted in FIG. 1A or FIG. 9.

[0024] The patient monitor 110 may be provided at a bedside in a medical facility of a hospital, and may show vital signs such as heart rate, blood pressure, ECG signals, or other information of the patient. The patient monitor 110 may also show a score in both real-time and as a curve over time as one component on the patient monitor 110. The patient monitor may show a current score compared to the lowest value of the score and / or the highest value of the score in the same continuous window. A time range for the curve displayed on the patient monitor 110 may also be customizable by a user, so that context for a current score can be obtained. The score may be used to trigger an alert for potential risk of, for example, hemodynamic instability within the next few hours.

[0025] The patient monitor 110 may include interfaces so as to be interfaced with medical devices such as sensors that generate the information displayed on the patient monitor 110. The interfaces may also interface the patient monitor 110 with user input devices by which users can input instructions such as mouses, keyboards, thumbwheels and so on. The controller 150 implemented in the patient monitor 110 may repeatedly obtain patient data in real-time in a continuous window. For example, during a patient hospitalization that includes time in an intensive care unit, sensors may generate and sent readings from the patient as patient data to the patient monitor 110 hundreds, thousands, tens of thousands, or even more times. The continuous window may be defined by a relatively arbitrary beginning and a relatively arbitrary end, as long as the continuous window begins before a clinical event endured by the patient, continues during the clinical event, and ends after the clinical event. The clinical event refers to a clinical eventpredicted by the disease risk prediction model, and typically involves treatment in a clinical intervention implemented for the clinical event.

[0026] The patient data may be received at the patient monitor 110 from the medical devices such as sensors. The controller 150 may repeatedly apply a disease risk prediction model in the continuous window from before the clinical event predicted by the disease risk prediction model starts, during the clinical event, and after the clinical event predicted by the disease risk prediction model ends. In other words, while the patient is being monitored by the patient monitor 110, the controller 150 may apply the disease risk prediction model before, during and after a clinical event predicted by the disease risk prediction model. The disease risk prediction model may be applied continuously, periodically, or intermittently at different rates which vary based on conditions during the continuous window. The disease risk prediction model may be applied immediately after admission to an intensive care unit, such as after vital signs have been obtained from a patient. The disease risk prediction model may have minimum input requirements such as heart rate and blood pressure, but may also accept other measurements such as temperature, blood gas, results from a blood panel, kidney functionality, renal system measurements, respiratory functionality, and more.

[0027] The display 180 may be connected to the controller 150 via a local wired interface in the patient monitor 110. The display 180 may display readings of the patient data in real-time so that readings are provided to clinicians, and over time so that trends in the patient data may be visualizable.

[0028] Using the patient monitor 110, a patient may be continuously monitored across the entire intensive care unit stay. The patient monitor 110 may be used to apply a disease risk model across the intensive care unit stay. Before the clinical event, the risk prediction score can be interpreted as the likelihood of the clinical event within the next few hours. The risk prediction score during and after the clinical event may be interpreted to provide guidance to the clinical interventions, such as 1) predicting the appropriate type of interventions; 2) the appropriate dosage of interventions; and 3) the appropriate duration of interventions. The risk prediction score may be inversely correlated with severity, so a high score corresponds to a lower severity and a lower score corresponds to a higher severity. After the clinical event, the risk index may be used to evaluate the effectiveness of the clinical interventions, such as associating the riskprediction score with 1) the need for another intervention; 2) remaining length of stay in the intensive care unit; and 3) intensive care unit mortality. The association between the risk prediction score and the target variables during the clinical intervention and long-term clinical outcomes after the clinical intervention may be established so that risk prediction models can be applied continuously across the entire intensive care unit stay.

[0029] FIG. IB illustrates a system 100 for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0030] The system 100 in FIG. IB is a system for disease risk index application across an intensive care unit stay and includes components that are distributed. The system 100 includes the patient monitor 110 as a first patient monitor, a second patient monitor 120, a third patient monitor 130, a network 101, and a medical facility system 140. The second patient monitor 120 and the third patient monitor 130 may be similar or identical to the first patient monitor 130.

[0031] The medical facility system 140 is representative of one or more computer each with a controller comprising a memory / processor combination. The medical facility system 140 may also include one or more monitor for use with the one or more computer. For example, the medical facility system 140 may comprise a server computer in a medical facility or otherwise provided for the medical facility. A computer that can be used to implement a server in the medical facility system 140 is depicted in FIG. 9, though a server in the medical facility system 140 may include more or fewer elements than depicted in FIG. IB or FIG. 9. The network 101 may comprise a local area network with wired and / or wireless elements that connect the medical facility system 140 to the patient monitor 110 as a first patient monitor, to the second patient monitor 120, and to the third patient monitor 103.

[0032] Although not shown in FIG. IB, the system 100 may include a display. A display in the system 100 may be provided within the medical facility system 140. Such a display may be a monitor such as a computer monitor, a display on a mobile device, an augmented reality display, a television, an electronic whiteboard, or another screen configured to display electronic imagery.

[0033] The medical facility system 140 may be used to apply a disease risk model across an intensive care unit stay. Before the clinical event, the risk prediction score may be interpreted as the likelihood of event within the next few hours. The risk prediction score during and after theclinical event may be interpreted to provide guidance to the clinical interventions, such as 1) predicting the type of interventions; 2) dosage of interventions; and 3) duration of interventions. After the clinical event, the risk index may be used to evaluate the effectiveness of the clinical interventions, such as associating the risk prediction score with 1) the need for another intervention; 2) remaining length of stay in the intensive care unit; and 3) intensive care unit mortality. The association between the risk prediction score and those target variables during the clinical intervention and long-term clinical outcomes after the clinical intervention may be established so that risk prediction models can be applied continuously across the entire intensive care unit stay.

[0034] A controller implemented in a computer of the medical facility system 140 may execute instructions to: repeatedly obtain patient data in real-time in a continuous window; and repeatedly apply a disease risk prediction model in the continuous window from before a clinical event predicted by the disease risk prediction model, during the clinical event, and after the clinical event predicted by the disease risk prediction model. In embodiments based on FIG. IB, the controller in the medical facility system 140 may separate execute instruction to perform processes for the patient monitor 110 as a first patient monitor, the second patient monitor 120 and / or the third patient monitor 130.

[0035] FIG. 2 illustrates another system for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0036] The system 200 includes the patient monitor 110 as a first patient monitor, the second patient monitor 120, the third patient monitor 130, and the network 101. In FIG. 2, the system 200 also includes the central computer 240. The central computer 240 includes a controller 250, and the controller 250 includes a memory 251 that stores instructions and a processor 252 that executes the instructions. A computer that can be used to implement the central computer 240 is depicted in FIG. 9, though the central computer 240 may include more or fewer elements than depicted in FIG. 2 or FIG. 9. In some embodiments, multiple different elements of the system 200 in FIG. 2 may include a controller such as the controller 250.

[0037] Although not shown in FIG. 2, the system 200 may include a display. A display in the system 200 may be local to the central computer 240 or may be remotely connected to the central computer 240. Such a display may be connected to the central computer 240 via a local wiredinterface such as an Ethernet cable or via a local wireless interface such as a Wi-Fi connection. A display in the system 200 may be a monitor such as a computer monitor, a display on a mobile device, an augmented reality display, a television, an electronic whiteboard, or another screen configured to display electronic imagery.

[0038] The controller 250 may include interfaces, such as a first interface, a second interface, a third interface, and a fourth interface. One or more of the interfaces may include ports, disk drives, wireless antennas, or other types of receiver circuitry that connect the controller 250 to other electronic elements. One or more of the interfaces may also include user interfaces such as buttons, keys, a mouse, a microphone, a speaker, a display, or other elements that users can use to interact with the controller 250 such as to enter instructions and receive output.

[0039] The controller 250 may perform some of the operations described herein directly and may implement other operations described herein indirectly. For example, the controller 250 may indirectly control operations such as by generating and transmitting content to be displayed on a display. The controller 250 may directly control other operations such as logical operations performed by the processor 252 executing instructions from the memory 251 based on input received from electronic elements and / or users via the interfaces. Accordingly, the processes implemented by the controller 250 when the processor 252 executes instructions from the memory 251 may include steps not directly performed by the controller 250.

[0040] The central computer 240 may be used to apply a disease risk model across an intensive care unit stay. Before the clinical event, the risk prediction score can be interpreted as the likelihood of event within the next few hours. The risk prediction score during and after the clinical event may be interpreted to provide guidance to the clinical interventions, such as 1) predicting the type of interventions; 2) dosage of interventions; and 3) duration of interventions. After the clinical event, the risk index may be used to evaluate the effectiveness of the clinical interventions, such as associating the risk prediction score with 1) the need for another intervention; 2) remaining length of stay in the intensive care unit; and 3) intensive care unit mortality. The association between the risk prediction score and those target variables during the clinical intervention and long-term clinical outcomes after the clinical intervention may be established so that risk prediction models can be applied continuously across the entire intensive care unit stay.

[0041] The patient monitor 110 in FIG. 1, the medical facility system 140 and / or the central computer 240 may be used to associate the risk prediction score with target variables during clinical events, such as intervention type, intervention dosage, and intervention duration. The patient monitor 110 in FIG. 1, the medical facility system 140 and / or the central computer 240 may be used to associate the risk prediction score with target variables after the clinical events, such as the need for another intervention, remaining length of stay in the intensive care unit, and intensive care unit mortality. Once an association between the risk prediction score and the target variables is established during clinical events, then the risk prediction score can be used to guide the clinical intervention during the clinical event. On the other hand, the association between the risk prediction score and target variables can be established after the clinical events, and then the risk prediction score can be used to evaluate the effectiveness of the clinical intervention. The teachings herein primarily use HSI as a running example to show how to conduct the analysis to determine the use of the risk prediction scores both during and after the clinical events. However, the analyses described herein are readily applicable to other risk prediction models.

[0042] FIG. 3 illustrates a method for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0043] The method of FIG. 3 may be performed by the patient monitor 110 including the controller 150, by the medical facility system 140, and / or by the central computer 240 including the controller 250.

[0044] At S310, a patient is monitored and patient data is obtained. The monitoring at S310 may be performed by any of the patient monitor 110 as a first patient monitor, the second patient monitor 120, and / or the third patient monitor 130. The patient monitor 110 in FIG. 1 A may perform the remainder of the method of FIG. 1A, or otherwise the remainder of the method may be performed by a computer in the medical facility system 140 in FIG. IB or the central computer 140 in FIG. 2.

[0045] At S320, a risk model is applied to the patient data. The risk model is a disease risk prediction model that is repeatedly applied in a continuous window starting from before a clinical event predicted by the disease risk prediction model, during the clinical event, and ending after the clinical event predicted by the disease risk prediction model.

[0046] At S330, a risk prediction score is generated. A risk prediction score may take anynumber of forms. For example, a risk prediction score may be a numerical likelihood of a clinical event happening in a predefined timeframe such as the next 2 hours or the next 4 hours.Alternatively, a risk prediction score may be a curve showing a numerical likelihood of the clinical event happening at various times in a predefined timeframe such as the next 2 hours or the next 4 hours. The risk prediction score may be generated using, for example, a trained machine learning model that takes sensor readings as patient data over time and is repeatedly applied to the patient data taken over time.

[0047] At S340, a risk prediction score is correlated with a predetermined association with one or more aspect(s) of one or more clinical event(s) and / or one or more clinical intervention(s). The risk prediction score may be correlated based on a predetermined association between risk prediction scores and aspects of clinical events and a predetermined association between risk prediction scores and aspects of clinical interventions. The correlation used at S340 may be retrieved from one or more table(s) or other memory arrangement(s).

[0048] If a clinical intervention is implemented for a clinical event predicted by the disease risk prediction model, the method of FIG. 3 may include evaluating effectiveness of the clinical intervention after the clinical event predicted by the disease risk prediction model ends. For example, the evaluation of effectiveness may be determined in whole or in part based on patient data obtained after the clinical intervention is performed.

[0049] At S350, a determination is made as to whether the patient is released. The release of the patient may mark a confirmable end of the continuous window described herein, though the continuous window may end upon the occurrence of other events.

[0050] If the patient is not released (S350 = No), the method returns to S310.

[0051] If the patient is released (S350 = Yes), at S360 a risk prediction score and corresponding recommended aspect(s) are output. The output at S360 may include at least one risk prediction score and a corresponding recommended aspect of a clinical intervention to a central computer that receives risk prediction scores. The central computer may also receive corresponding recommended aspects of clinical interventions from a plurality of controllers other than the controller which implements the method of FIG. 3. The risk prediction scores and corresponding recommended aspect(s) may be output to update the disease risk prediction model applied at S320, so that successes and failures are reflected going forward based on applications of riskmodels at S320.

[0052] Although the method of FIG. 3 suggests that a single clinical event happens during the continuous window in which the disease risk prediction model is applied, more than one clinical event may occur during the continuous window. For example, the continuous window may include a first clinical event and a subsequent clinical event as a second clinical event. The second clinical event may also be predicted by the disease risk prediction model insofar as the method of FIG. 3 may be performed until the patient is released at S350, or at another time which ends the continuous window.

[0053] FIG. 4 illustrates an interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0054] In FIG. 4, the interventional timeline lasts from hour 0 to hour 76. The clinical interventional timeline in FIG. 4 illustrates one example patient experience with two episodes of hemodynamic instability events in an intensive care unit. The first event starts at hour 7 and lasts 5 hours. The second event starts at hour 55 and lasts 4 hours. As shown, the continuous window in FIG. 4 includes an unstable segment that lasts for 7 hours and ends when a first intervention is initiated. The first intervention segment lasts from hour 7 to hour 24, and the first intervention itself is discontinued at hour 12. The pre-unstable segment lasts from hour 24 to hour 31, and the second unstable segment starts at hour 31 and lasts until hour 55. The second intervention is initiated at hour 55. The second intervention segment starts at hour 55 and lasts until hour 71, with the second intervention being discontinued at hour 59. The stable segment at the end lasts from hour 71 to hour 76, and may mark the end of the continuous window insofar as this is the only segment in which the patient is stable.

[0055] FIG. 5 illustrates another interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0056] FIG. 5 illustrates a method of associating a HSI score with vasopressor dosage within the next few hours. In FIG. 5, the interventional timeline lasts from the time of ICU admission to beyond an offset time of a 1st intervention, and includes an onset time of the 1st intervention. For each patient, the method illustrated in FIG. 5 starts from the onset time of the clinical intervention. HSI score S i is collected and the maximal vasopressor dosage within the next H hours (denoted as V i) is calculated every five minutes. Five minutes is used as the periodbetween calculations because a period of five minutes corresponds to the frequency for computing HSI. Multiple (S i, V i ) pairs are collected from patients who receive vasopressors. These pairs are divided into multiple groups based on the value range of S i. The distribution of vasopressor dosage V i across different groups is compared. This analysis shows how the maximal vasopressor dosage within the next few hours changes with respect to the current HSI score. The method of FIG. 5 provides guidance to clinicians for the titration of vasopressor dosage.

[0057] Using the method of FIG. 5, the score is associated with the dosage of the vasopressor received by the patient within the next few hours. A lower score may be shown to be associated with a higher dosage of basal pressure received by the patient exam, such that the score may be used as a surrogate on the patient status even after the clinical intervention starts. The higher dosage of the vasopressor means more intensive, more aggressive treatment, and the patient needs that treatment when the patient hasn’t responded well to the intervention. Because the score contains information from blood pressure and other vital signs and also labs, the score may be more accurate in characterizing the patient state, and may be useful for a clinician to make a decision such as for the dosage of vasopressor to give to the patient in the next few hours. As an example, in the case of HSI, since lower HSI score indicates more unstable hemodynamic conditions, lower HSI scores may be associated with higher dosage of vasopressors within the next few hours.

[0058] In Fig 5, the current score (S i) measured at the current time point is used to predict the maximal vasopressor dosage within the next few hours, which is denoted as V i. Here (S_1,V_1), (S_2, V_2) and (S_3, V_3) all convey the same information, and three timelines are used to illustrate how these data were collected continuously over time, i.e. (S_2, V_2) following (S_l, V_l) and (S_3, V_3) following (S_2,V2). In practice, after the start of vasopressor administration, the user (clinician) can continuously use the current score S i to predict the maximal dosage within the next few hours.

[0059] FIG. 6 illustrates another interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0060] FIG. 6 illustrates a method of associating a HSI score with remaining intervention durations. In FIG. 6, the interventional timeline lasts from the time of ICU admission to beyondan offset time of the 1st intervention, and includes an onset time of the 1st intervention. For each patient, the method using FIG. 6 starts from the onset time of the clinical intervention. The HSI score S i is collected and the remaining duration of the clinical intervention segment T_i is calculated every 5 minutes. Multiple (S_i,T_i ) pairs are collected from all unstable patients, which are divided into multiple groups based on the values of S i. The distribution of T_i across different groups is computed. The analysis of FIG. 6 shows how intervention duration changes with respect to the HSI score. For example, lower HSI scores may be associated with longer intervention durations. The method of FIG. 6 provides guidance to clinicians on when to stop the use of interventions.

[0061] As reflected in FIG. 6, HSI may be associated with intervention types during clinical events. For hemodynamic interventions, the patient often first receives fluids or packed-red- blood-cells. The administration of vasopressors depends on the patient’s response to these treatments. HSI score may be associated with the type of interventions received by the patient using methods similar to the methods used in FIG. 5 and FIG. 6. The patient is likely to receive vasopressors if the HSI score does not improve significantly in response to fluids or packed-red- blood-cells. The association between HSI and intervention types provides guidance to clinicians on choosing which type of interventions to apply to patients.

[0062] HSI may also be associated with the need of another intervention after clinical events. To evaluate the effectiveness of the clinical intervention, HSI score observed at the offset time of each intervention may be associated with the target variable indicating whether the patient still needs another intervention. Specifically, for each intervention segment of the patient, the HSI score observed at the end of the clinical intervention, denoted as S, may be taken. For the clinical intervention segment, a check may be made if the patient will receive another intervention in the same intensive care unit stay, denoted as I. All unstable patients may be divided into multiple groups using S. The percentage of patients receiving another intervention in the same intensive care unit across different patient groups may be compared. This analysis can help quantify the effectiveness of the clinical intervention segment. If the clinical intervention is effective, then there is less likelihood that the patient will need another intervention. A higher HSI score (more stable hemodynamic condition) after the end the clinical intervention may be associated with lower likelihood of receiving another intervention.

[0063] FIG. 7 illustrates another interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0064] In FIG. 7, the interventional timeline lasts from the time of ICU admission to the time of ICU discharge, and includes an onset time of a 1st intervention, an offset time of / from the 1st intervention. A method to associate HSI after clinical events may be associated with remaining length of stay in the intensive care unit using a method based on FIG. 7. For each patient, a HSI score observed at the end of the clinical intervention, denoted as S, may be taken. For each patient, remaining length of stay of the patient in the intensive care unit, denoted as T, may be computed. All patients may be divided into multiple groups using S. The distribution of T across different patient groups may be compared. The method based on FIG. 7 shows how the remaining length of stay changes with respect to the HSI score. Lower HSI scores (worse hemodynamic condition) may be associated with longer remaining stay in the intensive care unit.

[0065] FIG. 8 illustrates another interventional timeline for disease risk index application across an intensive care unit stay, in accordance with a representative embodiment.

[0066] In FIG. 8, the interventional timeline lasts from the time of ICU admission to the time of ICU discharge, and includes an onset time of a 1st intervention and an offset time of / from the 1st intervention. The clinical interventional timeline in FIG. 8 corresponds to a method of associating HSI after clinical events with intensive care unit mortality. For each patient, the method takes HSI score observed at the end of the first intervention, denoted as S. For each patient, the intensive care unit mortality status at intensive care unit discharge is checked. All patients are divided into multiple groups using S. The mortality rate of different groups are compared. FIG. 8 shows how the intensive care unit mortality rate changes with respect to the HSI score observed at the end of the clinical intervention.

[0067] FIG. 9 illustrates a computer system, on which a method for disease risk index application across an intensive care unit stay is implemented, in accordance with another representative embodiment.

[0068] Referring to FIG. 9, the computer system 900 includes a set of software instructions that can be executed to cause the computer system 900 to perform any of the methods or computer- based functions disclosed herein. The computer system 900 may operate as a standalone device or may be connected, for example, using a network 901, to other computer systems or peripheraldevices. In embodiments, a computer system 900 performs logical processing based on digital signals received via an analog-to-digital converter.

[0069] In a networked deployment, the computer system 900 operates in the capacity of a server or as a client user computer in a server-client user network environment, or as a peer computer system in a peer-to-peer (or distributed) network environment. The computer system 900 can also be implemented as or incorporated into various devices, such as a patient monitor that includes a controller, a server that includes a controller, a workstation that includes a controller, a stationary computer that includes the controller, or any other machine capable of executing a set of software instructions (sequential or otherwise) that specify actions to be taken by that machine. The computer system 900 can be incorporated as or in a device that in turn is in an integrated system that includes additional devices. In an embodiment, the computer system 900 can be implemented using electronic devices that provide voice, video or data communication. Further, while the computer system 900 is illustrated in the singular, the term “system” shall also be taken to include any collection of systems or sub-systems that individually or jointly execute a set, or multiple sets, of software instructions to perform one or more computer functions.

[0070] As illustrated in FIG. 9, the computer system 900 includes a processor 910. The processor 910 may be considered a representative example of a processor of a controller and executes instructions to implement some or all aspects of methods and processes described herein. The processor 910 is tangible and non-transitory. As used herein, the term “non- transitory” is to be interpreted not as an eternal characteristic of a state, but as a characteristic of a state that will last for a period. The term “non-transitory” specifically disavows fleeting characteristics such as characteristics of a carrier wave or signal or other forms that exist only transitorily in any place at any time. The processor 910 is an article of manufacture and / or a machine component. The processor 910 is configured to execute software instructions to perform functions as described in the various embodiments herein. The processor 910 may be a general- purpose processor or may be part of an application specific integrated circuit (ASIC). The processor 910 may also be a microprocessor, a microcomputer, a processor chip, a controller, a microcontroller, a digital signal processor (DSP), a state machine, or a programmable logic device. The processor 910 may also be a logical circuit, including a programmable gate array (PGA), such as a field programmable gate array (FPGA), or another type of circuit that includesdiscrete gate and / or transistor logic. The processor 910 may be a central processing unit (CPU), a graphics processing unit (GPU), or both. Additionally, any processor described herein may include multiple processors, parallel processors, or both. Multiple processors may be included in, or coupled to, a single device or multiple devices.

[0071] The term “processor” as used herein encompasses an electronic component able to execute a program or machine executable instruction. References to a computing device comprising “a processor” should be interpreted to include more than one processor or processing core, as in a multi-core processor. A processor may also refer to a collection of processors within a single computer system or distributed among multiple computer systems. The term computing device should also be interpreted to include a collection or network of computing devices each including a processor or processors. Programs have software instructions performed by one or multiple processors that may be within the same computing device or which may be distributed across multiple computing devices.

[0072] The computer system 900 further includes a main memory 920 and a static memory 930, where memories in the computer system 900 communicate with each other and the processor 910 via a bus 908. Either or both of the main memory 920 and the static memory 930 may be considered representative examples of a memory of a controller, and store instructions used to implement some or all aspects of methods and processes described herein. Memories described herein are tangible storage mediums for storing data and executable software instructions and are non-transitory during the time software instructions are stored therein. As used herein, the term “non-transitory” is to be interpreted not as an eternal characteristic of a state, but as a characteristic of a state that will last for a period. The term “non-transitory” specifically disavows fleeting characteristics such as characteristics of a carrier wave or signal or other forms that exist only transitorily in any place at any time. The main memory 920 and the static memory 930 are articles of manufacture and / or machine components. The main memory 920 and the static memory 930 are computer-readable mediums from which data and executable software instructions can be read by a computer (e.g., the processor 910). Each of the main memory 920 and the static memory 930 may be implemented as one or more of random access memory (RAM), read only memory (ROM), flash memory, electrically programmable read only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, a harddisk, a removable disk, tape, compact disk read only memory (CD-ROM), digital versatile disk (DVD), floppy disk, blu-ray disk, or any other form of storage medium known in the art. The memories may be volatile or non-volatile, secure and / or encrypted, unsecure and / or unencrypted.

[0073] “Memory” is an example of a computer-readable storage medium. Computer memory is any memory which is directly accessible to a processor. Examples of computer memory include, but are not limited to RAM memory, registers, and register files. References to “computer memory” or “memory” should be interpreted as possibly being multiple memories. The memory may for instance be multiple memories within the same computer system. The memory may also be multiple memories distributed amongst multiple computer systems or computing devices.

[0074] As shown, the computer system 900 further includes a video display unit 950, such as a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid-state display, or a cathode ray tube (CRT), for example. Additionally, the computer system 900 includes an input device 960, such as a keyboard / virtual keyboard or touch-sensitive input screen or speech input with speech recognition, and a cursor control device 970, such as a mouse or touch-sensitive input screen or pad. The computer system 900 also optionally includes a disk drive unit 980, a signal generation device 990, such as a speaker or remote control, and / or a network interface device 940.

[0075] In an embodiment, as depicted in FIG. 9, the disk drive unit 980 includes a computer- readable medium 982 in which one or more sets of software instructions 984 (software) are embedded. The sets of software instructions 984 are read from the computer-readable medium 982 to be executed by the processor 910. Further, the software instructions 984, when executed by the processor 910, perform one or more steps of the methods and processes as described herein. In an embodiment, the software instructions 984 reside all or in part within the main memory 920, the static memory 930 and / or the processor 910 during execution by the computer system 900. Further, the computer-readable medium 982 may include software instructions 984 or receive and execute software instructions 984 responsive to a propagated signal, so that a device connected to a network 901 communicates voice, video or data over the network 901. The software instructions 984 may be transmitted or received over the network 901 via the network interface device 940.

[0076] In an embodiment, dedicated hardware implementations, such as application-specificintegrated circuits (ASICs), field programmable gate arrays (FPGAs), programmable logic arrays and other hardware components, are constructed to implement one or more of the methods described herein. One or more embodiments described herein may implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through the modules. Accordingly, the present disclosure encompasses software, firmware, and hardware implementations. Nothing in the present application should be interpreted as being implemented or implementable solely with software and not hardware such as a tangible non-transitory processor and / or memory.

[0077] In accordance with various embodiments of the present disclosure, the methods described herein may be implemented using a hardware computer system that executes software programs. Further, in an exemplary, non-limited embodiment, implementations can include distributed processing, component / object distributed processing, and parallel processing. Virtual computer system processing may implement one or more of the methods or functionalities as described herein, and a processor described herein may be used to support a virtual processing environment.

[0078] Accordingly, disease risk index application across an intensive care unit stay enables application of a disease risk index continuously on the same patient during an entire intensive care unit stay, including after the onset of clinical events. The analysis framework described herein supports the use of a disease risk index after the onset of clinical events. This same analysis framework can be applied to HSI and other disease risk prediction models to determine their usefulness during the entire intensive care unit stay. Moreover, the teachings are not limited to the context of HIS, and instead may be applied in other contexts such as the use of mechanical ventilators in clinical interventions for patients with respiratory problems.

[0079] Although disease risk index application across an intensive care unit stay has been described with reference to several exemplary embodiments, it is understood that the words that have been used are words of description and illustration, rather than words of limitation. Changes may be made within the purview of the appended claims, as presently stated and as amended, without departing from the scope and spirit of disease risk index application across an intensive care unit stay in its aspects. Although disease risk index application across an intensive care unit stay has been described with reference to particular means, materials and embodiments, diseaserisk index application across an intensive care unit stay is not intended to be limited to the particulars disclosed; rather disease risk index application across an intensive care unit stay extends to all functionally equivalent structures, methods, and uses such as are within the scope of the appended claims.

[0080] The illustrations of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments. The illustrations are not intended to serve as a complete description of all of the elements and features of the disclosure described herein. Many other embodiments may be apparent to those of skill in the art upon reviewing the disclosure. Other embodiments may be utilized and derived from the disclosure, such that structural and logical substitutions and changes may be made without departing from the scope of the disclosure. Additionally, the illustrations are merely representational and may not be drawn to scale. Certain proportions within the illustrations may be exaggerated, while other proportions may be minimized. Accordingly, the disclosure and the figures are to be regarded as illustrative rather than restrictive.

[0081] One or more embodiments of the disclosure may be referred to herein, individually and / or collectively, by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any particular invention or inventive concept. Moreover, although specific embodiments have been illustrated and described herein, it should be appreciated that any subsequent arrangement designed to achieve the same or similar purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all subsequent adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the description.

[0082] The Abstract of the Disclosure is provided to comply with 37 C.F.R. §1.72(b) and is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, various features may be grouped together or described in a single embodiment for the purpose of streamlining the disclosure. This disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter may be directed to less than all of the featuresof any of the disclosed embodiments. Thus, the following claims are incorporated into the Detailed Description, with each claim standing on its own as defining separately claimed subject matter.

[0083] The preceding description of the disclosed embodiments is provided to enable any person skilled in the art to practice the concepts described in the present disclosure. As such, the above disclosed subject matter is to be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments which fall within the true spirit and scope of the present disclosure. Thus, to the maximum extent allowed by law, the scope of the present disclosure is to be determined by the broadest permissible interpretation of the following claims and their equivalents and shall not be restricted or limited by the foregoing detailed description.

Claims

CLAIMS:

1. A controller, comprising: a memory that stores instructions; and a processor that executes the instructions, wherein, when executed by the processor, the instructions cause the controller to: repeatedly obtain patient data in real-time in a continuous window; and repeatedly apply a disease risk prediction model in the continuous window from before a clinical event predicted by the disease risk prediction model, during the clinical event, and after the clinical event predicted by the disease risk prediction model.

2. The controller of claim 1 , wherein the controller is implemented in a patient monitor.

3. The controller of claim 1, wherein the disease risk prediction model comprises a hemodynamic stability index (HSI).

4. The controller of claim 1 , wherein, when executed by the processor, the instructions cause the controller further to: evaluate effectiveness of a clinical intervention implemented for the clinical event after the clinical event predicted by the disease risk prediction model ends.

5. The controller of claim 1, wherein the continuous window in which the disease risk prediction model is applied includes the clinical event as a first clinical event and a subsequent clinical event as a second clinical event.

6. The controller of claim 1 , wherein, when executed by the processor, the instructions cause the controller further to: repeatedly generate a risk prediction score based on applying the disease risk prediction model, including during the clinical event.

7. The controller of claim 6, wherein, when executed by the processor, the instructions cause the controller further to: recommend an aspect of a clinical intervention implemented for the clinical event during based on repeatedly generating the risk prediction score.

8. The controller of claim 6, wherein, when executed by the processor, the instructions cause the controller further to: output at least one risk prediction score and a corresponding recommended aspect of a clinical intervention to a central computer that receives risk prediction scores and corresponding recommended aspects of clinical interventions from a plurality of controllers including the controller.

9. The controller of claim 6, wherein the risk prediction score is generated based on a predetermined association between risk prediction scores and aspects of clinical events and a predetermined association between risk prediction scores and aspects of clinical interventions.

10. A method of continuously applying a disease risk prediction model, comprising: repeatedly obtaining patient data in real-time in a continuous window; and repeatedly applying a disease risk prediction model in the continuous window from before a clinical event predicted by the disease risk prediction model, during the clinical event, and after the clinical event predicted by the disease risk prediction model.

11. The method of claim 10, wherein the method is performed by a controller of a patient monitor.

12. The method of claim 10, wherein the disease risk prediction model comprises a hemodynamic stability index (HSI).

13. The method of claim 10, further comprising: evaluating effectiveness of a clinical intervention implemented for the clinical event after the clinical event predicted by the disease risk prediction model ends.

14. The method of claim 10, wherein the continuous window in which the disease risk prediction model is applied includes the clinical event as a first clinical event and a subsequent clinical event as a second clinical event.

15. The method of claim 10, further comprising: repeatedly generating a risk prediction score based on applying the disease risk prediction model, including during the clinical event.

16. The method of claim 15, further comprising: recommending an aspect of a clinical intervention implemented for the clinical event during based on repeatedly generating the risk prediction score.

17. The method of claim 15, further comprising: outputting at least one risk prediction score and a corresponding recommended aspect of a clinical intervention to a central computer that receives risk prediction scores and corresponding recommended aspects of clinical interventions from a plurality of controllers including the controller.

18. The method of claim 15, wherein the risk prediction score is generated based on a predetermined association between risk prediction scores and aspects of clinical events and a predetermined association between risk prediction scores and aspects of clinical interventions.

Images