Methods and systems for predicting pediatric hemodynamic instability

Abstract

A method (100) for generating and presenting a pediatric patient hemodynamic instability risk score, comprising: receiving (120) patient information comprising at least (i) demographic information, and (ii) urine output for a first previous time period; extracting (130) a plurality of hemodynamic instability risk score features from the received patient information; analyzing (140), by a trained model, the extracted plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period; determining (150), by the trained model, a contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score; and providing (160), via a user interface (240) of the patient risk score system, the calculated pediatric patient hemodynamic instability risk score to a user.

Description

METHODS AND SYSTEMS FOR PREDICTING PEDIATRIC HEMODYNAMIC INSTABILITYField of the Disclosure

[0001] The present disclosure relates generally to methods and systems for generating and presenting a pediatric patient hemodynamic instability risk score using a patient risk score system.Background

[0002] For critically ill pediatric patients in intensive care, timely intervention - such as initiation of vasopressors - to treat or prevent hemodynamic instability is crucial to patient outcomes. Unfortunately, the early warning signs of hemodynamic instability can be easily missed. Clinical expertise to recognize these signs may be scarce, and early signs of instability may not be obvious from simple monitoring of individual vitals.

[0003] Existing methods for detecting hemodynamic instability are primarily focused on simple rules that can be easily used by busy clinicians without automated assistance. For example, the PALS (Pediatric Advanced Life Support) guidelines provide age-adjusted normal ranges for common vitals, including heart rate, respiratory rate, and blood pressure. Vitals outside of normal ranges are considered as a sign of potential hemodynamic instability, requiring additional clinical attention. However, rule-based methods and systems are typically unable to detect potential hemodynamic instability from the simple monitoring of individual vitals, and do a poor job distinguishing among age-dependent signs of instability.Summary of the Disclosure

[0004] Accordingly, there is a continued need for systems and methods that more accurate predict the risk of pediatric patient hemodynamic instability.

[0005] Various embodiments and implementations herein are directed to a method and system configured to generate a pediatric patient hemodynamic instability risk score using a patient risk score system. The system receives patient information comprising demographic information and urine output for a first previous time period, and extracts a plurality of hemodynamic instability risk score features from the received patient information. The patient risk score system analyzesthe extracted features to calculate a pediatric patient hemodynamic instability risk score, and determines the contribution of the extracted features to the calculated risk score. The system then provides the calculated pediatric patient hemodynamic instability risk score to a user.

[0006] Generally, in one aspect, a method for generating and presenting a pediatric patient hemodynamic instability risk score using a patient risk score system is provided. The method includes: (i) receiving, at the patient risk score system, patient information comprising at least (1) demographic information, and (2) urine output for a first previous time period; (ii) extracting, by a processor of the patient risk score system, a plurality of hemodynamic instability risk score features from the received patient information; (iii) analyzing, by a trained model of the patient risk score system, the extracted plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period; (iv) determining, by the trained model of the patient risk score system, a contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score; and (v) providing, via a user interface of the patient risk score system, the calculated pediatric patient hemodynamic instability risk score to a user.

[0007] In accordance with an embodiment, providing the calculated pediatric patient hemodynamic instability risk score to the user further comprises providing the determined contribution of the one or more extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score.

[0008] In accordance with an embodiment, the method further comprises repeating one or more iterations of the receiving, extracting, analyzing, and determining steps to generate one or more updated calculated pediatric patient hemodynamic instability risk scores, wherein providing the calculated pediatric patient hemodynamic instability risk score to the user further comprises providing a trend of the calculated pediatric patient hemodynamic instability risk scores over time.

[0009] In accordance with an embodiment, the method further comprises administering, in response to receiving the calculated pediatric patient hemodynamic instability risk score, a hemodynamic intervention to the pediatric patient. In accordance with an embodiment, the hemodynamic intervention administered to the pediatric patient is an intravenous vasoactive medication. In accordance with an embodiment, the hemodynamic intervention administered to the pediatric patient is one or more of dopamine, epinephrine, vasopressin, norepinephrine, dobutamine, phenylephrine, and milrinone.

[0010] In accordance with an embodiment, the method further comprises comparing the calculated pediatric patient hemodynamic instability risk score to a predetermined threshold, wherein the calculated pediatric patient hemodynamic instability risk score is presented to the user when it meets or exceeds the predetermine threshold.

[0011] In accordance with an embodiment, the calculated pediatric patient hemodynamic instability risk score is a prediction of whether the pediatric patient will receive a hemodynamic intervention during the predetermined future time period.

[0012] In accordance with an embodiment, the patient information further comprises one or more vital signs for the patient.

[0013] In accordance with an embodiment, patient information further comprises one or more lab test results for the patient, and / or a setting for a care device associated with the patient.

[0014] In accordance with an embodiment, the patient information is received from one or more of an electronic medical record system and a patient monitor.

[0015] According to another aspect is a system for generating and presenting a pediatric patient hemodynamic instability risk score. The system includes: a trained pediatric patient risk score model trained to analyze a plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period; a user interface; and a processor configured to: (i) receive patient information comprising at least (1) demographic information, and (2) urine output for a first previous time period; (ii) extract a plurality of hemodynamic instability risk score features from the received patient information; (iii) analyze, by the trained pediatric patient risk score model, the extracted plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period; (iv) determine, by the trained pediatric patient risk score model, a contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score; and (vi) provide, via the user interface, the calculated pediatric patient hemodynamic instability risk score to a user.

[0016] In accordance with an embodiment, providing the calculated pediatric patient hemodynamic instability risk score to the user further comprises providing the determined contribution of the one or more extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score.

[0017] In accordance with an embodiment, the system further comprises an administration, in response to receiving the calculated pediatric patient hemodynamic instability risk score, a hemodynamic intervention to the pediatric patient, wherein the hemodynamic intervention administered to the pediatric patient is an intravenous vasoactive medication. In accordance with an embodiment, the hemodynamic intervention administered to the pediatric patient is one or more of dopamine, epinephrine, vasopressin, norepinephrine, dobutamine, phenylephrine, and milrinone.

[0018] It should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein. It should also be appreciated that terminology explicitly employed herein that also may appear in any disclosure incorporated by reference should be accorded a meaning most consistent with the particular concepts disclosed herein.

[0019] These and other aspects of the various embodiments will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.Brief Description of the Drawings

[0020] In the drawings, like reference characters generally refer to the same parts throughout the different views. The figures showing features and ways of implementing various embodiments and are not to be construed as being limiting to other possible embodiments falling within the scope of the attached claims. Also, the drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the various embodiments.

[0021] FIG. 1 is a flowchart of a method for determining a pediatric patient hemodynamic instability risk score, in accordance with an embodiment.

[0022] FIG. 2 is a schematic representation of a patient risk score system, in accordance with an embodiment.

[0023] FIG. 3 is a flowchart of a method for training a pediatric patient hemodynamic instability risk score model, in accordance with an embodiment.

[0024] FIG. 4 is a graph of a ROC (receiver operating characteristic) curve, in accordance with an embodiment.Detailed Description of Embodiments

[0025] The present disclosure describes various embodiments of a system and method configured to generate and provide a pediatric patient hemodynamic instability risk score. More generally, Applicant has recognized and appreciated that it would be beneficial to monitor a pediatric patient’s risk of hemodynamic instability. Accordingly, a patient risk score system receives patient information comprising demographic information and urine output for a first previous time period, and extracts a plurality of hemodynamic instability risk score features from the received patient information. The patient risk score system analyzes the extracted features to calculate a pediatric patient hemodynamic instability risk score, and determines the contribution of the extracted features to the calculated risk score. The system then provides the calculated pediatric patient hemodynamic instability risk score to a user.

[0026] According to an embodiment, as automated risk score that identifies patients likely to require hemodynamic intervention in the near future (for example, during the next 1-6 hours although shorter and longer time periods are possible) is a valuable tool and can potentially save lives. The tool identifies pediatric patients in need of clinician attention, thus leading to improvement in patient outcomes (including but not limited to decreased mortality rates) as well as reducing clinician burden.

[0027] The automated risk score system is also valuable in tele-ICU settings, where a remote nurse or other provider may be responsible for monitoring several patients in cooperation with bedside providers. In this scenario, the risk score helps the remote provider more easily direct attention to higher-risk patients, such as via alerts or a visual display.

[0028] According to an embodiment, the systems and methods described or otherwise envisioned herein can, in some non-limiting embodiments, be implemented as an element for a commercial product for patient analysis or monitoring, such as the Philips® Patient Flow Capacity Suite (PFCS) (available from Koninklijke Philips NV, the Netherlands), or any suitable system. For example, the system and method can be implemented within existing or future clinical decision support systems (CDS), applications, and devices. However, the disclosure is not limited to thesedevices or systems, and thus disclosure and embodiments disclosed herein can encompass any device or system capable of generating and reporting a pediatric patient hemodynamic instability risk score.

[0029] Referring to FIG. 1 , in one embodiment, is a flowchart of a method 100 for generating and presenting a pediatric patient hemodynamic instability risk score using a patient risk score system 200. The methods described in connection with the figures are provided as examples only, and shall be understood not limit the scope of the disclosure. The patient risk score system can be any of the systems described or otherwise envisioned herein. The patient risk score system can be a single system or multiple different systems.

[0030] At step 110 of the method, a patient risk score system 200 is provided. Referring to an embodiment of a patient risk score system 200 as depicted in FIG. 2, for example, the system comprises one or more of a processor 220, memory 230, user interface 240, communications interface 250, and storage 260, interconnected via one or more system buses 212. It will be understood that FIG. 2 constitutes, in some respects, an abstraction and that the actual organization of the components of the system 200 may be different and more complex than illustrated. Additionally, patient risk score system 200 can be any of the systems described or otherwise envisioned herein. Other elements and components of patient risk score system 200 are disclosed and / or envisioned elsewhere herein.

[0031] At step 120 of the method, the patient risk score system receives or obtains patient information from an electronic medical record (EMR) database or system 270. The patient is a pediatric patient, and thus can be any age from a newborn to age 18. In some embodiments where the trained machine learning algorithm of the system is trained to generate hemodynamic instability risk scores for pediatric patients of a specific age or age range (as described in greater detail below), the patient is a pediatric patient of that specific age or age range.

[0032] The patient information can be any information about the patient that the patient risk score system can or may utilize for analysis as described or otherwise envisioned herein. According to an embodiment, the patient information comprises one or more of demographic information about the patient, a diagnosis for the patient, medical history of the patient, and / or any other information. For example, demographic information may comprise information about the patient such as name, age, body mass index (BMI), and any other demographic information. Thediagnosis for the patient may be any information about a medical diagnosis for the patient, historical and / or current. The medical history of the patient may be any historical admittance or discharge information, historical treatment information, historical diagnosis information, historical exam or imaging information, and / or any other information.

[0033] According to an embodiment, the patient information comprises urine output for the pediatric patient. The urine output can be measured using a variety of different mechanisms. For example, the urine output can be measured using an indwelling catheter connected to a urometer. The urometer can include, for example, a collection bag or chamber with milliliter (ml) measurement labeling. A clinician or other caretaker can take and record urometer measurements. For example, urometer measurements may be entered into a system that saves the information to the electronic medical record database 270, among many other options. According to another embodiment, an automated urine output system automatically obtains and records urine output measurements. According to an embodiment, the urine output may be measured for any previous time period that can be utilized by the system. For example, the system can utilize urine output measured for the pediatric patient over the past 24 hours, or any other shorter or longer time period.

[0034] Further non-limiting examples of patient information received by the patient risk score system include lab test results. The lab tests performed may be any lab tests that may be utilized by the patient risk score system for analysis as described or otherwise envisioned herein. For example, the lab tests may be an analysis of electrolytes, biomarkers, and / or any other types of lab tests.

[0035] Another non-limiting example of patient information received by the patient risk score system includes information such as a parameter or setting or history of a care device associated with the patient. For example, the parameter or setting or history of a care device may be information about supplemental oxygen or other respiratory support provided to the pediatric patient. Many other care devices, and the parameter(s) or setting(s) or history associated with those care devices, are possible.

[0036] Yet another non-limiting example of patient information received by the patient risk score system includes vital sign information for the patient. The vital sign information can be any vital sign of the patient such as heart rate, respiration rate, blood pressure, blood gases, and / or any other information. The vital sign information can be received from, retrieved from, or otherwiseobtained from a patient monitor 280. The patient monitor may be a component of the patient risk score system, or may be in local and / or remote communication with the patient risk score system. According to an embodiment, the patient monitor is any device that can obtain information about or from a patient. For example, the patient monitor may be a physiological monitor such as a device configured to measure a patient’s vital signs in a care setting. As another example, the patient monitor may be a mobile element that can measure patient information, such as a wearable device among many other types of devices.

[0037] The patient information may be received or obtained from one or a plurality of different sources. According to an embodiment, the patient information is received from, retrieved from, or otherwise obtained from the electronic medical record database or system 270. The EMR database or system may be local or remote. The EMR database or system may be a component of the patient risk score system, or may be in local and / or remote communication with the patient risk score system. The received patient information may be utilized immediately, or may be stored in local or remote storage for use in further steps of the method.

[0038] According to an embodiment, the received patient information may be associated with a timestamp indicating time of measurement. The patient information can include patient data and medical records that cover a period of time. For example, the patient information can include patient data and medical records for an entirety of a patient’s hospitalization to date, for a predetermined previous time, or any other period of time. The patient information can be continuously received or obtained, or the patient information can be periodically received or obtained such as once an hour, once a day, and so on. Additionally or alternatively, the patient information can be received or obtained in response to a triggering event, such as a patient care event like availability of a new record, transitioning to a new diagnosis or care routine, moving to a new location, and so on. Many other triggering events are possible.

[0039] At step 130 of the method, the patient risk score system analyzes some or all of the received patient information to extract a set of hemodynamic instability risk score features. The extracted set or plurality of hemodynamic instability risk score features can include any patient information that the patient risk score system can or may utilize for analysis as described or otherwise envisioned herein. The feature set can include, for example, demographic information about the patient (including but not limited to age of the pediatric patient), urine output of thepatient, lab results for the patient, vital signs of the patient, and parameter or setting or history of a care device associated with the patient, among many other possible hemodynamic instability risk score features.

[0040] The features in the hemodynamic instability risk score feature set can be identified or extracted using known methods for identifying and extracting features in patient information. According to an embodiment, the plurality of features utilized by the patient risk score system may depend on the patient’s diagnosis, treatment, demographics, and / or any other information specific to the patient. The parameters of the hemodynamic instability risk score feature set can be determined based in part or in whole on user input, or can be identified or determined in part or in whole from the received or obtained patient data. Once extracted, the hemodynamic instability risk score feature set can be utilized immediately, or may be stored in local or remote storage for use in further steps of the method.

[0041] At step 140 of the method, a trained model of the patient risk score system analyzes the hemodynamic instability risk score feature set in order to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period. The trained model of the patient risk score system can be any algorithm or model configured to utilize the hemodynamic instability risk score feature set to generate a pediatric patient hemodynamic instability risk score for a predetermined future time period. The predetermined future time period may be any time period, such as 1 hour, 90 minutes, 2 hours, 3 hours, 4 hours, 5 hours, 6 hours, 10 hours, 12 hours, 24 hours, or any other shorter or longer time period. The predetermined future time period may be determined, assigned, selected, and / or preprogrammed, such as by a clinician, other care giver, or other entity. The calculated pediatric patient hemodynamic instability risk score can be a prediction of whether the pediatric patient will receive a hemodynamic intervention during the predetermined future time period.

[0042] According to an embodiment, the methods and systems described or otherwise envisioned herein incorporate methods for handling extensive missing clinical data. Indeed, clinical data often has missing input features. For example, many lab tests may not be performed, or performed frequently, for all patients. A complex machine learning tool that relies on many input features may perform poorly, or fail to produce results at all, in the presence of many missinginputs. Thus, the methods and systems described or otherwise envisioned herein incorporate methods for providing a patient risk score even when there is missing clinical data.

[0043] According to an embodiment, in one implemented system, the component implementing the trained model will be capable of running it automatically at specified intervals (e.g., hourly) on patient data drawn from data sources. Thus, the trained model of the patient risk score system can automatically calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period at each of the specified intervals.

[0044] Referring to FIG. 3, in one embodiment, is a flowchart of a method 300 for training the risk score model of the patient risk score system 200. At step 310 of the method, the system receives or obtains a training data set comprising training data for a plurality of patients, such as historical patient data and information. The training data can comprise input such as demographic information about the patients, diagnoses for the patients, medical history of the patients, and / or any other information. For example, demographic information may comprise information about the patients such as name, age, body mass index (BMI), and any other demographic information. The diagnosis for the patients may be any information about a medical diagnosis for the patients, historical and / or current. The medical history of the patients may be any historical admittance or discharge information, historical treatment information, historical diagnosis information, historical exam or imaging information, and / or any other information. The training data can further comprise patient information such as urine output for the pediatric patient, which can be measured using a variety of different mechanisms. The training data can further comprise patient information such as lab test results, vital signs, and / or parameter(s) or setting(s) or history of a care device associated with the patient. The training data may be stored in and / or received from one or more databases. The database may be a local and / or remote database. For example, the patient risk score system may comprise a database of training data, such as the electronic medical record database or system 270.

[0045] According to an embodiment, the patient risk score system may comprise a data preprocessor or similar component or algorithm configured to process the received training data. For example, the data pre-processor analyzes the training data to remove noise, bias, errors, and other potential issues. The data pre-processor may also analyze the input data to remove low-qualitydata. Many other forms of data pre-processing or data point identification and / or extraction are possible.

[0046] At step 320 of the method, the system trains the machine learning algorithm, which will be the algorithm utilized in analyzing the input information as described or otherwise envisioned. The machine learning algorithm is trained using the training data set according to known methods for training a machine learning algorithm. According to an embodiment, the algorithm is trained, using the processed training dataset, to utilize the hemodynamic instability risk score feature set to generate a pediatric patient hemodynamic instability risk score for a predetermined future time period as described or otherwise envisioned herein. According to an embodiment, the algorithm is trained, using the processed training dataset, to determine a contribution of one or more of the hemodynamic instability risk score features to a calculated pediatric patient hemodynamic instability risk score.

[0047] Notably, according to an embodiment, the machine learning algorithm can be trained using a subset of the training data set such that training data for a specific age or age range of pediatric patients is utilized to train the machine learning algorithm. Alternatively, the training data set may be constructed in steps 310 and / or 320, to only generate training data comprising pediatric patients for a specific age or age range. In this way, the machine learning algorithm may be trained to provide a hemodynamic instability risk score for pediatric patients of a specific age or age range. Thus, the system may comprise a plurality of different machine learning algorithms, each trained to generate a hemodynamic instability risk score for pediatric patients of a specific age or age range. For example, a first trained machine learning algorithm may generate hemodynamic instability risk scores for pediatric patients of ages 0 to <3, while a second trained machine learning algorithm may generate hemodynamic instability risk scores for pediatric patients of ages 3 to 5, and so on. The ages and age ranges can be any breakdown or subset of the traditional pediatric age range of 0 to 18 years.

[0048] At step 330 of the method, the trained risk score model of the patient risk score system is stored for future use. According to an embodiment, the model may be stored in local or remote storage.

[0049] Returning to method 100 in FIG. 1, at step 150 of the method, the trained risk score model of the patient risk score system determines a contribution of one or more of the extractedplurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score. For example, the determined contribution of a feature can be a feature importance score, which determines the importance (or contribution) of the feature to the output of a machine learning algorithm. The score can be calculated or determined by the machine learning algorithm or by any other mechanism for determining feature contribution or importance. For example, features may be scored or ranked based on their contribution to the final prediction or output.

[0050] According to an embodiment, the determined contribution of a feature can be useful to clinicians receiving the pediatric patient hemodynamic instability risk score generated from the hemodynamic instability risk score feature set. For example, a clinician may have preexisting experience or information about which features might be most informative to a pediatric patient’s hemodynamic instability, and thus may evaluate the generated risk score based on how the determined feature contribution(s) align with their preexisting experience. Further, by understanding which features in a feature set are most important, clinicians can gain insight into the underlying data and how the model is making predictions, thus improving model interpretability.

[0051] Many machine learning methods can be “black box” methods in that they do not provide information on what factors contributed to a risk score. This is a disadvantage as it reduces clinician trust in a tool, especially when the output of the tool does not immediately agree with intuition. The methods and systems described or otherwise envisioned herein estimate the contribution of input features and can provide the top contributing features along with the risk score. In addition to improving clinician trust, this increases the value of the system by providing additional guidance to clinicians in the interpretation of a risk score.

[0052] At optional step 152 of the method, the patient risk score system compares the calculated pediatric patient hemodynamic instability risk score to a predetermined threshold. According to an embodiment, the threshold can be determined by a clinician, or can be determined by the system or another system. For example, according to an embodiment, the value of the threshold can be determined based on preexisting information or knowledge or experience regarding pediatric patient hemodynamic instability. According to an embodiment, the threshold can be based in whole or in part on the age of the pediatric patient. For example, a pediatric patient of age X mayhave one hemodynamic instability risk score threshold, and a pediatric patient of age XI may have a different hemodynamic instability risk score threshold. For example, younger pediatric patients may have a lower hemodynamic instability risk score threshold as they may be at higher risk of hemodynamic instability. However, many other variables may be utilized to determine the hemodynamic instability risk score threshold.

[0053] At step 160 of the method, the calculated pediatric patient hemodynamic instability risk score and the determined contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score are provided to a user via a user interface 240 of the patient risk score system. The user can be any individual, although it will typically be a clinician involved in or responsible for care of the patient. According to an embodiment, the calculated pediatric patient hemodynamic instability risk score is only presented to the user when it meets or exceeds the predetermined threshold based on the comparison in step 152 of the method.

[0054] The determined pediatric patient hemodynamic instability risk score and the determined contribution(s) can be provided to the user via any mechanism for display, visualization, or otherwise providing information via a user interface. According to an embodiment, the information may be communicated by wired and / or wireless communication to a user interface and / or to another device. For example, the system may communicate the information to a mobile phone, computer, laptop, wearable device, and / or any other device configured to allow display and / or other communication of the report. The user interface can be any device or system that allows information to be conveyed and / or received, and may include a display, a mouse, and / or a keyboard for receiving user commands. According to an embodiment, the display may further comprise one or more of the patient’s name and / or a treatment recommendation, among many other types of information.

[0055] According to an embodiment, the determined pediatric patient hemodynamic instability risk score and the determined contribution(s), optionally including other information, can be provided to a user via a variety of other mechanisms, devices, and systems. For example, in accordance with an embodiment, the information can be provided via a clinical decision support (CDS) device, system, or application.

[0056] At optional step 170 of the method, the patient risk system repeats the receiving (120), extracting (130), analyzing (140), and determining (150) steps to generate one or more updated calculated pediatric patient hemodynamic instability risk scores. Accordingly, at step 160 of the method, the patient risk system can provide a trend of the calculated pediatric patient hemodynamic instability risk scores over time. The system can calculate the trend using two or more of the calculated pediatric patient hemodynamic instability risk scores, such as the initial risk score and an updated risk score. Alternatively, the system can utilize two or more updated risk scores. Many other variations are possible.

[0057] At step 180 of the method, after receiving the calculated pediatric patient hemodynamic instability risk score and determining that hemodynamic intervention is necessary, a clinician administers a hemodynamic intervention to the pediatric patient. The hemodynamic intervention administered to the pediatric patient can be any hemodynamic intervention that treats or prevents a hemodynamic issue experienced by the pediatric patient. For example, the hemodynamic intervention administered to the pediatric patient can be an intravenous vasoactive medication, although other interventions are possible. Examples of vasoactive medications include, but are not limited to, one or more of dopamine, epinephrine, vasopressin, norepinephrine, dobutamine, phenylephrine, and milrinone.

[0058] EXAMPLE

[0059] The following is an example implementation of a patient risk score model of a patient risk score system trained to analyze a hemodynamic instability risk score feature set in order to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period. The example is provided only as one possible example or implementation or embodiment of the patient risk score model and / or patient risk score system, and thus does not limit the scope of the model or system.

[0060] According to an embodiment, a suitable dataset was utilized to train a predictive model. In particular, the dataset should be sufficiently large and varied (in terms of patient population, for example), and should be representative of patients in typical pediatric ICU care. For this example, a dataset was assembled from routine care at a large pediatric tertiary care facility from 2014 to 2019. The dataset included anonymized records from 4494 patients who collectively had 5941 hospital encounters. Patients in the dataset visited one of two separate ICUs in the same facility: acardiothoracic ICU (CUCU), which primarily treats very young patients following cardiac surgery, and a general pediatric ICU (PICU), which treats a range of patients for a variety of conditions. Between the two care units, this dataset represented a strong variety of patients, which resulted in a model that generalized well to patients at other hospitals.

[0061] According to an embodiment, a suitable identification of cohorts in a dataset (i.e., marking which patients received a hemodynamic intervention) is also necessary. Patients given vasoactive intravenous medications, including dopamine, epinephrine, vasopressin, norepinephrine, dobutamine, phenylephrine, and milrinone, were identified as positive cases (i.e., those receiving interventions). This was chosen to match the most common clinical interventions for this population and to give interpretability of the risk score to clinicians.

[0062] A variety of machine learning algorithms can be utilized for the predictive model described or otherwise envisioned herein. A gradient tree boosting method was used, as implemented in the XGBoost library, based on prior experience with this type of model for similar tasks.

[0063] Referring to FIG. 4, in one embodiment, is a graph showing the performance of the trained model on a held-out test set, predicting hemodynamic interventions one hour ahead. This is a ROC (receiver operating characteristic) curve, showing true positive rate against false positive rate when varying the decision threshold of the risk score output by the model. The area under the ROC curve (AUROC) is commonly used as an overall measure of predictive model performance. This model achieves an AUROC of 0.785 (with a 95% confidence interval of [0.741, 0.823]), which is excellent performance.

[0064] According to an embodiment, one aspect of suitability for informing clinical decisions is interpretability of a machine learning model. To address this, the system can use Shapley values to provide an estimate of the contribution of each feature to the risk score. The system is capable of displaying the top contributing features. In addition to or alternatively to Shapley values, other methods can be utilized to provide an estimate of the contribution of each feature to the risk score.

[0065] Referring to FIG. 2 is a schematic representation of a patient risk score system 200. System 200 may be any of the systems described or otherwise envisioned herein, and may comprise any of the components described or otherwise envisioned herein. It will be understoodthat FIG. 2 constitutes, in some respects, an abstraction and that the actual organization of the components of the system 200 may be different and more complex than illustrated.

[0066] According to an embodiment, system 200 comprises a processor 220 capable of executing instructions stored in memory 230 or storage 260 or otherwise processing data to, for example, perform one or more steps of the method. Processor 220 may be formed of one or multiple modules. Processor 220 may take any suitable form, including but not limited to a microprocessor, microcontroller, multiple microcontrollers, circuitry, field programmable gate array (FPGA), application-specific integrated circuit (ASIC), a single processor, or plural processors.

[0067] Memory 230 can take any suitable form, including a non-volatile memory and / or RAM. The memory 230 may include various memories such as, for example LI, L2, or L3 cache or system memory. As such, the memory 230 may include static random access memory (SRAM), dynamic RAM (DRAM), flash memory, read only memory (ROM), or other similar memory devices. The memory can store, among other things, an operating system. The RAM is used by the processor for the temporary storage of data. According to an embodiment, an operating system may contain code which, when executed by the processor, controls operation of one or more components of system 200. It will be apparent that, in embodiments where the processor implements one or more of the functions described herein in hardware, the software described as corresponding to such functionality in other embodiments may be omitted.

[0068] User interface 240 may include one or more devices for enabling communication with a user. The user interface can be any device or system that allows information to be conveyed and / or received, and may include a display, a mouse, and / or a keyboard for receiving user commands. In some embodiments, user interface 240 may include a command line interface or graphical user interface that may be presented to a remote terminal via communication interface 250. The user interface may be located with one or more other components of the system, or may located remote from the system and in communication via a wired and / or wireless communications network.

[0069] Communication interface 250 may include one or more devices for enabling communication with other hardware devices. For example, communication interface 250 may include a network interface card (NIC) configured to communicate according to the Ethernetprotocol. Additionally, communication interface 250 may implement a TCP / IP stack for communication according to the TCP / IP protocols. Various alternative or additional hardware or configurations for communication interface 250 will be apparent.

[0070] Storage 260 may include one or more machine-readable storage media such as readonly memory (ROM), random-access memory (RAM), magnetic disk storage media, optical storage media, flash-memory devices, or similar storage media. In various embodiments, storage 260 may store instructions for execution by processor 220 or data upon which processor 220 may operate. For example, storage 260 may store an operating system 261 for controlling various operations of system 200.

[0071] It will be apparent that various information described as stored in storage 260 may be additionally or alternatively stored in memory 230. In this respect, memory 230 may also be considered to constitute a storage device and storage 260 may be considered a memory. Various other arrangements will be apparent. Further, memory 230 and storage 260 may both be considered to be non-transitory machine-readable media. As used herein, the term non-transitory will be understood to exclude transitory signals but to include all forms of storage, including both volatile and non-volatile memories.

[0072] While system 200 is shown as including one of each described component, the various components may be duplicated in various embodiments. For example, processor 220 may include multiple microprocessors that are configured to independently execute the methods described herein or are configured to perform steps or subroutines of the methods described herein such that the multiple processors cooperate to achieve the functionality described herein. Further, where one or more components of system 200 is implemented in a cloud computing system, the various hardware components may belong to separate physical systems. For example, processor 220 may include a first processor in a first server and a second processor in a second server. Many other variations and configurations are possible.

[0073] According to an embodiment, the patient risk system comprises an electronic medical record (EMR) database or system 270. Alternatively, the EMR database or system 270 may be a local or remote database or system and thus the patient risk system may be in direct and / or indirect communication with the EMR database or system 270.

[0074] According to an embodiment, the patient risk system comprises a patient monitor or patient monitoring device or system 280. Alternatively, the patient monitor may be a remote patient monitor and thus the patient risk system may be in direct and / or indirect communication with the patient monitor 280.

[0075] According to an embodiment, storage 260 of system 200 may store one or more algorithms, modules, and / or instructions to carry out one or more functions or steps of the methods described or otherwise envisioned herein. For example, the system may comprise, among other instructions or data, feature extraction instructions 262, a trained patient risk score model 263, and / or reporting instructions 264.

[0076] According to an embodiment, the feature extraction instructions 262 direct the system to analyze some or all of the received patient information to extract a plurality of hemodynamic instability risk score features. The plurality of hemodynamic instability risk score features can be extracted using any method for extracting features from input information. The extracted set or plurality of hemodynamic instability risk score features can include any patient information that the patient risk score system can or may utilize for analysis as described or otherwise envisioned herein. The feature set can include, for example, demographic information about the patient (including but not limited to age of the pediatric patient), urine output of the patient, lab results for the patient, vital signs of the patient, and parameter or setting or history of a care device associated with the patient, among many other possible hemodynamic instability risk score features. Once extracted, feature set can be utilized immediately, or may be stored in local or remote storage for use in further steps of the method.

[0077] According to an embodiment, the trained patient risk score model 263 is trained to analyze the plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period. The trained model of the patient risk score system can be any algorithm or model configured to utilize the hemodynamic instability risk score feature set to generate a pediatric patient hemodynamic instability risk score for a predetermined future time period. The predetermined future time period may be any time period, such as 1 hour, 90 minutes, 2 hours, 3 hours, 4 hours, 5 hours, 6 hours, 10 hours, 12 hours, 24 hours, or any other shorter or longer time period. The predetermined future time period may be determined, assigned, selected, and / or preprogrammed, such as by a clinician, other care giver, orother entity. The calculated pediatric patient hemodynamic instability risk score can be a prediction of whether the pediatric patient will receive a hemodynamic intervention during the predetermined future time period.

[0078] According to an embodiment, the trained patient risk score model 263 is further trained to determine a contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score. For example, the determined contribution of a feature can be a feature importance score, which determines the importance (or contribution) of the feature to the output of a machine learning algorithm. The score can be calculated or determined by the machine learning algorithm or by any other mechanism for determining feature contribution or importance. For example, features may be scored or ranked based on their contribution to the final prediction or output.

[0079] According to an embodiment, the reporting instructions 264 direct the system to generate and provide to a user via a user interface the calculated pediatric patient hemodynamic instability risk score and the determined contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score. According to an embodiment, the calculated pediatric patient hemodynamic instability risk score is only presented to the user when it meets or exceeds the predetermined threshold based on the comparison in step 152 of the method. The determined risk score and contribution(s) may be provided to the user via any mechanism for display, visualization, or otherwise providing information via a user interface. According to an embodiment, the information may be communicated by wired and / or wireless communication to a user interface and / or to another device. For example, the system may communicate the information to a mobile phone, computer, laptop, wearable device, and / or any other device configured to allow display and / or other communication of the report. The user interface can be any device or system that allows information to be conveyed and / or received, and may include a display, a mouse, and / or a keyboard for receiving user commands. According to an embodiment, the display may further comprise one or more of the patient’s name and / or a treatment recommendation, among many other types of information.

[0080] Accordingly, within the context of the disclosure herein, aspects of the embodiments may take the form of a computer program product embodied in one or more non-transitorycomputer-readable media having computer readable program code embodied thereon. Thus, according to one embodiment is a non-transitory computer-readable storage medium comprising computer program code instructions which, when executed by a processor, enables the processor to carry out a method including: (i) receive patient information comprising at least (1) demographic information, and (2) urine output for a first previous time period; (ii) extract a plurality of hemodynamic instability risk score features from the received patient information; (iii) analyze the extracted plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period; (iv) determine a contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score; and (v) provide the calculated pediatric patient hemodynamic instability risk score to a user. The program code may perform entirely on a user’s computer, partly on a user’s computer, as a stand-alone software package, partly on a user’s computer and partly on a remote computer, or entirely on a remote computer or server.

[0081] According to an embodiment, the patient risk score system is configured to process millions of datapoints in the input data used to train the system, as well as to process and analyze the received patient information. For example, generating a functional and skilled trained system using an automated process such as feature identification and extraction and subsequent training requires processing of millions of datapoints from input data and the generated features. This can require millions or billions of calculations to generate a novel trained system from those millions of datapoints and millions or billions of calculations. As a result, the trained system is novel and distinct based on the input data and parameters of the machine learning algorithm, and thus improves the functioning of a patient care system. Generating a functional and skilled trained system comprises a process with a volume of calculation and analysis that a human brain cannot accomplish in a lifetime, or multiple lifetimes. By providing improved patient monitoring and analysis, this novel patient risk score system has an enormous positive effect on patient monitoring and analysis and care compared to prior art systems.

[0082] There is no tool available to physicians that provides a continuous assessment of risk and enables them to make the right hemodynamic intervention treatment choice at the earliest possible moment. Currently physicians assess the clinical status of the patient in a non-continuousmanner and based on this assessment make a care decision. They also do not have quantitative information of feature contributions to pediatric patient hemodynamic instability. The methods and systems described or otherwise envisioned herein provide such a system and the necessary quantitative information, thereby improving clinician analysis, monitoring, and care. Consequently, the methods and systems described herein improve patient care and improve patient outcomes.

[0083] It should be appreciated that all combinations of the foregoing concepts and additional concepts discussed in greater detail below (provided such concepts are not mutually inconsistent) are contemplated as being part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter appearing at the end of this disclosure are contemplated as being part of the inventive subject matter disclosed herein. It should also be appreciated that terminology explicitly employed herein that also may appear in any disclosure incorporated by reference should be accorded a meaning most consistent with the particular concepts disclosed herein.

[0084] All definitions, as defined and used herein, should be understood to control over dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined terms.

[0085] The indefinite articles “a” and “an,” as used herein in the specification and in the claims, unless clearly indicated to the contrary, should be understood to mean “at least one.”

[0086] The phrase “and / or,” as used herein in the specification and in the claims, should be understood to mean “either or both” of the elements so conjoined, i.e., elements that are conjunctively present in some cases and disjunctively present in other cases. Multiple elements listed with “and / or” should be construed in the same fashion, i.e., “one or more” of the elements so conjoined. Other elements may optionally be present other than the elements specifically identified by the “and / or” clause, whether related or unrelated to those elements specifically identified.

[0087] As used herein in the specification and in the claims, the phrase “at least one,” in reference to a list of one or more elements, should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed within the list of elements and notexcluding any combinations of elements in the list of elements. This definition also allows that elements may optionally be present other than the elements specifically identified within the list of elements to which the phrase “at least one” refers, whether related or unrelated to those elements specifically identified.

[0088] As used herein, 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.

[0089] 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.

[0090] In the claims, as well as in the specification above, all transitional phrases such as “comprising,” “including,” “carrying,” “having,” “containing,” “involving,” “holding,” “composed of,” and the like are to be understood to be open-ended, i.e., to mean including but not limited to. Only the transitional phrases “consisting of’ and “consisting essentially of’ shall be closed or semi-closed transitional phrases, respectively.

[0091] It should also be understood that, unless clearly indicated to the contrary, in any methods claimed herein that include more than one step or act, the order of the steps or acts of the method is not necessarily limited to the order in which the steps or acts of the method are recited.

[0092] The above-described examples of the described subject matter can be implemented in any of numerous ways. For example, some aspects can be implemented using hardware, software or a combination thereof. When any aspect is implemented at least in part in software, the software code can be executed on any suitable processor or collection of processors, whether provided in a single device or computer or distributed among multiple devices / computers.

[0093] The present disclosure can be implemented as a system, a method, and / or a computer program product at any possible technical detail level of integration. The computer program product can include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present disclosure.

[0094] The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium can be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium comprises the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.

[0095] Computer readable program instructions described herein can be downloaded to respective computing / processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and / or a wireless network. The network can comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and / or edge servers. A network adapter card or network interface in each computing / processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing / processing device.

[0096] Computer readable program instructions for carrying out operations of the present disclosure can be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data,configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, comprising an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions can execute entirely on the user’s computer, partly on the user’s computer, as a standalone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, comprising a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some examples, electronic circuitry comprising, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) can execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0097] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to examples of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0100] The computer readable program instructions can be provided to a processor of a, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture comprising instructions which implement aspects of the function / act specified in the flowchart and / or block diagram or blocks.

[0101] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0102] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various examples of the present disclosure. In this regard, each block in the flowchart or block diagrams can represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks can occur out of the order noted in the Figures. For example, two blocks shown in succession can, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

[0103] Other implementations are within the scope of the following claims and other claims to which the applicant can be entitled.

[0104] While several inventive embodiments have been described and illustrated herein, those of ordinary skill in the art will readily envision a variety of other means and / or structures for performing the function and / or obtaining the results and / or one or more of the advantages described herein, and each of such variations and / or modifications is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and / or configurations will depend upon the specific application or applications for which the inventive teachings is / are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific inventive embodiments described herein. It is, therefore, to be understood that the foregoing embodiments are presented by way of example onlyand that, within the scope of the appended claims and equivalents thereto, inventive embodiments may be practiced otherwise than as specifically described and claimed. Inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and / or methods, if such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent, is included within the inventive scope of the present disclosure.

Claims

ClaimsWhat is claimed is:

1. A method (100) for generating and presenting a pediatric patient hemodynamic instability risk score using a patient risk score system (200), comprising: receiving (120), at the patient risk score system, patient information comprising at least (i) demographic information, and (ii) urine output for a first previous time period; extracting (130), by a processor (220) of the patient risk score system, a plurality of hemodynamic instability risk score features from the received patient information; analyzing (140), by a trained model of the patient risk score system, the extracted plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period; determining (150), by the trained model of the patient risk score system, a contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score; and providing (160), via a user interface (240) of the patient risk score system, the calculated pediatric patient hemodynamic instability risk score to a user.

2. The method of claim 1, wherein providing the calculated pediatric patient hemodynamic instability risk score to the user further comprises providing the determined contribution of the one or more extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score.

3. The method of claim 1, further comprising repeating (170) one or more iterations of the receiving, extracting, analyzing, and determining steps to generate one or more updated calculated pediatric patient hemodynamic instability risk scores; wherein providing the calculated pediatric patient hemodynamic instability risk score to the user further comprises providing a trend of the calculated pediatric patient hemodynamic instability risk scores over time.

4. The method of claim 1, further comprising administering (180), in response to receiving the calculated pediatric patient hemodynamic instability risk score, a hemodynamic intervention to the pediatric patient.

5. The method of claim 4, wherein the hemodynamic intervention administered to the pediatric patient is an intravenous vasoactive medication.

6. The method of claim 5, wherein the hemodynamic intervention administered to the pediatric patient is one or more of dopamine, epinephrine, vasopressin, norepinephrine, dobutamine, phenylephrine, and milrinone.

7. The method of claim 1 , further comprising comparing (152) the calculated pediatric patient hemodynamic instability risk score to a predetermined threshold; wherein the calculated pediatric patient hemodynamic instability risk score is presented to the user when it meets or exceeds the predetermine threshold.

8. The method of claim 1, wherein the calculated pediatric patient hemodynamic instability risk score is a prediction of whether the pediatric patient will receive a hemodynamic intervention during the predetermined future time period.

9. The method of claim 1 , wherein the patient information further comprises one or more vital signs for the patient.

10. The method of claim 1 , wherein the patient information further comprises one or more lab test results for the patient, and / or a setting for a care device associated with the patient.

11. The method of claim 1 , wherein the patient information is received from one or more of an electronic medical record system (270) and a patient monitor (280).

12. A system for generating and presenting a pediatric patient hemodynamic instability risk score, comprising: a trained pediatric patient risk score model (263) trained to analyze a plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period; a user interface (240); and a processor (220) configured to: (i) receive patient information comprising at least (1) demographic information, and (2) urine output for a first previous time period; (ii) extract a plurality of hemodynamic instability risk score features from the received patient information; (iii) analyze, by the trained pediatric patient risk score model, the extracted plurality of hemodynamic instability risk score features to calculate a pediatric patient hemodynamic instability risk score for a predetermined future time period; (iv) determine, by the trained pediatric patient risk score model, a contribution of one or more of the extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score; and (vi) provide, via the user interface, the calculated pediatric patient hemodynamic instability risk score to a user.

13. The system of claim 12, wherein providing the calculated pediatric patient hemodynamic instability risk score to the user further comprises providing the determined contribution of the one or more extracted plurality of hemodynamic instability risk score features to the calculated pediatric patient hemodynamic instability risk score.

14. The system of claim 12, further comprising an administration, in response to receiving the calculated pediatric patient hemodynamic instability risk score, a hemodynamic intervention to the pediatric patient, wherein the hemodynamic intervention administered to the pediatric patient is an intravenous vasoactive medication.

15. The system of claim 14, wherein the hemodynamic intervention administered to the pediatric patient is one or more of dopamine, epinephrine, vasopressin, norepinephrine, dobutamine, phenylephrine, and milrinone.

Images