Systems and methods for identifying risk of infection in dialysis patients

Abstract

A method and system for determining a patient's risk of developing an infection is disclosed. In one embodiment, the system and method includes extracting patient data from one or more databases corresponding to a pool of patients receiving treatment; using one or more predictive models with the extracted patient data to generate, for each of the patients in the pool of patients, a respective patient risk score for developing an infection within a selected time period; generating a report including at least a portion of the identified subset of the pool of patients and their respective patient risk scores; and transmitting the report to one or more health care facilities, the one or more health care facilities further identifying one or more patients from the portion of the identified subset of the pool of patients for interventional treatment, consultation, training, or combinations thereof.

1 . A system for determining a patient's risk of developing an infection, the system comprising:
 at least one computing device comprising:
 a memory storing instructions; and 
 a processor coupled to the memory operative to, responsive to executing the instructions:
 receive patient data of a patient receiving an identified treatment; 
 analyze the received patient data via one or more predictive models to determine:
 a patient risk score for the patient to develop an infection within a selected time period, and 
 at least one reason associated with the patient risk score identifying leading factors for developing the infection; and 
 
 determine, responsive to patient risk score being over a predetermined threshold value, at least one individualized interventional treatment for the patient based on the patient risk score and the at least one reason to reduce the risk of the patient developing the infection; 
 
 wherein each of the one or more predictive models is generated from a training set representative of a pool of patients receiving the identified treatment; 
 wherein the pool of patients comprises a first pool of patients diagnosed with an infection within the selected time period and a second pool of patients that did not develop an infection within the selected time period, and the training set is representative of both the first pool of patients and the second pool of patients; and 
 wherein generating the one or more predictive models comprises:
 extracting patient historical data from one or more databased corresponding to the pool of patients; and 
 training the one or more predictive models using the training set to determine factors associated with an infection diagnosis and to determine factors associated with no infection diagnosis. 
 
   
     
     
         2 . The system of  claim 1 , wherein the one or more predictive models are arranged and configured to:
 analyze the extracted historical patient data to identify patient characteristics common to patients having previous documented reports of infections; and   identify the patient characteristics in each of the patients in the pool of patients when generating the patient risk score for developing an infection within the selected time period.   
     
     
         3 . The system of  claim 2 , wherein the one or more predictive models are arranged and configured to analyze the extracted historical patient data to identify patient characteristics common to patients who have not had previous documented reports of infections. 
     
     
         4 . The system of  claim 1 , wherein the one or more predictive models are arranged and configured to:
 identify characteristics of patients previously diagnosed with an infection; and   analyze the extracted historical patient data against the characteristics for commonalities.   
     
     
         5 . The system of  claim 1 , wherein the at least one individualized interventional treatment comprises at least one of:
 transmitting a questionnaire to the patient to obtain additional information about the patient's treatment;   contacting the patient to determine appropriate interventions to aid in minimizing a risk of developing the infection;   contacting the patient for an assessment of the patient's treatment;   altering one or more conditions regarding the patient's treatment;   sending a medical professional for a visual assessment of the patient's treatment; or   combinations thereof.   
     
     
         6 . The system of  claim 5 ,
 wherein the patient's treatment is an at-home treatment; and   wherein the at least one individualized interventional treatment comprises sending a medical professional for an in-home visual assessment of the patient's treatment.   
     
     
         7 . The system of  claim 1 , wherein the pool of patients comprises patients in a similar geographic area, patients assigned to a facility associated with the identified treatment, or a group of patients receiving care from an individual medical professional, or combinations thereof. 
     
     
         8 . The system of  claim 1 , wherein the predetermined threshold value is determined by the one or more predictive models based on historical data. 
     
     
         9 . The system of  claim 1 , wherein the extracted historical patient data comprises patient demographics, laboratory values, recorded information, physician notes, or treatment data, or combinations thereof. 
     
     
         10 . The system of  claim 9 , wherein the patient demographics comprises gender, race, age, or marital status, or combinations thereof. 
     
     
         11 . The system of  claim 9 , wherein the laboratory values comprise a patient's albumin level, a patient's calcium level, a patient's chloride level, a patient's creatinine level, or a patient's transferrin saturation (TSAT) level, or combinations thereof. 
     
     
         12 . The system of  claim 11 , wherein the laboratory values comprise a time period over which a patient has been undergoing the identified treatment, a time period over which a patient was last diagnosed with an infection, a total number of previous infections from a patient, or a distance of a patient's home to a facility associated with the identified treatment, or combinations thereof. 
     
     
         13 . The system of  claim 1 , wherein the selected time period is one month. 
     
     
         14 . The system of  claim 1 , wherein the processor, responsive to executing the instructions, is further operative to analyze patient data of a plurality of patients via the one or more predictive models to determine:
 a patient risk score for each of the plurality of patients to develop an infection within the selected time period, and   at least one reason associated with the patient risk score identifying leading factors for developing the infection,   wherein the plurality of patients includes the patient.   
     
     
         15 . The system of  claim 14 , wherein the processor, responsive to executing the instructions, is further operative to determine at least one individualized interventional treatment for each patient of the plurality of patients with a patient risk score greater than the predetermined threshold value. 
     
     
         16 . A method for determining a patient's risk of developing an infection, the method comprising:
 receiving patient data of a patient receiving an identified treatment;   analyzing the received patient data via one or more predictive models to determine:
 a patient risk score for the patient to develop an infection within a selected time period, and 
 at least one reason associated with the patient risk score identifying leading factors for developing the infection; and 
   administering, responsive to patient risk score being over a predetermined threshold value, at least one individualized interventional treatment to the patient based on the patient risk score and the at least one reason to reduce the risk of the patient developing the infection;   wherein each of the one or more predictive models is generated from a training set representative of a pool of patients receiving the identified treatment;   wherein the pool of patients comprises a first pool of patients previously diagnosed with an infection within the selected time period and a second pool of patients that did not develop an infection within the selected time period, and the training set is representative of both the first pool of patients and the second pool of patients; and   wherein generating the one or more predictive models comprises:
 extracting patient historical data from one or more databased corresponding to the pool of patients; and 
 training the one or more predictive models using the training set to determine factors associated with an infection diagnosis and to determine factors associated with no infection diagnosis. 
   
     
     
         17 . The method of  claim 16 , wherein the one or more predictive models are arranged and configured to:
 analyze the extracted historical patient data to identify patient characteristics common to patients having previous documented reports of infections; and   identify the patient characteristics in each of the patients in the pool of patients when generating the patient risk score for developing an infection within a selected time period.   
     
     
         18 . The method of  claim 17 , wherein the one or more predictive models are arranged and configured to: analyze the extracted historical patient data to identify patient characteristics common to patients who have not had previous documented reports of infections. 
     
     
         19 . The method of  claim 16 , comprising analyzing patient data of a plurality of patients via the one or more predictive models to determine:
 a patient risk score for each of the plurality of patients to develop an infection within the selected time period, and   at least one reason associated with the patient risk score identifying leading factors for developing the infection,   wherein the plurality of patients includes the patient.   
     
     
         20 . The method of  claim 19 , comprising determining at least one individualized interventional treatment for each patient of the plurality of patients with a patient risk score greater than the predetermined threshold value.