Intelligent planning, execution, and reporting of clinical trials

Abstract

Machine learning based methods for planning, execution, and reporting of clinical trials, incorporating a patient burden index are disclosed. In one aspect, there is a method for determining a patient burden index. The method includes parsing a protocol for a clinical trial. The method further includes providing factor data for each of a plurality of patients. The method further includes calculating a patient burden index for each of the plurality of patients based on the parsed protocol and the provided factor data for each of the plurality of patients.

What is claimed is: 
     
         1 . A system, comprising:
 at least one data processor; and   memory storing instructions which, when executed by the at least one data processor, result in operations comprising:
 parsing a protocol for a clinical trial; 
 providing factor data for each of a plurality of patients; and 
 calculating a patient burden index for each of the plurality of patients based on the parsed protocol and the provided factor data for each of the plurality of patients. 
   
     
     
         2 . The system of  claim 1 , wherein parsing the protocol for the clinical trial comprises analyzing a protocol document using keyword analysis and pattern matching. 
     
     
         3 . The system of  claim 1 , wherein parsing the protocol for the clinical trial comprises generating a schedule of actions to be taken in the clinical trial. 
     
     
         4 . The system of  claim 1 , wherein the factor data comprises at least one of patient data, trial cost data, trial time data, trial content data, trial schedule data, and trial conduct data. 
     
     
         5 . The system of  claim 4 , wherein the patient data comprises at least one of age, gender, insurance status, marital status, number of children, and insurance coverage. 
     
     
         6 . The system of  claim 4 , wherein the trial cost data comprises at least one of transportation cost, lost work cost, and unreimbursed medical costs. 
     
     
         7 . The system of  claim 4 , wherein the trial time data comprises at least one of travel time, waiting time, and direct trial participation time. 
     
     
         8 . The system of  claim 4 , wherein the trial content data comprises at least one of observation by trial clinician, monitoring of vital signs, and blood draws. 
     
     
         9 . The system of  claim 4 , wherein the trial schedule data comprises a plurality of trial events at scheduled dates and times. 
     
     
         10 . The system of  claim 4 , wherein trial conduct data comprises empathy of trial personnel, understandability of trial materials, rigidity of scheduling, physical discomfort associated with trial events, and fatigue associated with trial events. 
     
     
         11 . The system of  claim 1 , wherein the patient burden index corresponds to at least one of an absolute level of burden on the patient participating in the trial, a probability of retention of the patient in the trial to completion, a probability that the patient will offer positive comments about the trial, and a probability that the patient will offer positive comments about a principal investigator or a staff member of the trial. 
     
     
         12 . The system of  claim 1 , wherein the operations further comprise training a machine learning system with a plurality of training observations of historic patient factor data and historic patient burden data. 
     
     
         13 . The system of  claim 12 , wherein the machine learning system comprises at least one of a neural network, a rule based system, a linear regression system, a non-linear regression system, a fuzzy logic system, a decision tree, a nearest neighbor classifier, and a statistical pattern recognition classifier. 
     
     
         14 . The system of  claim 13 , wherein the neural network comprises a plurality of input nodes, a plurality of hidden nodes, and at least one output nodes, the plurality of input nodes connected to the plurality of hidden nodes, and the plurality of hidden nodes connected to the at least one output node. 
     
     
         15 . The system of  claim 14 , wherein the operations further comprise inputting the factor data for the plurality of patients into the trained neural network and outputting, from the at least one output node, the patient burden index for each of the plurality of patients. 
     
     
         16 . The system of  claim 14 , wherein the operations further comprise generating a rule base that associates the patient factors with the patient burden index. 
     
     
         17 . The system of  claim 16 , wherein the rule base comprises fuzzy rules and the protocol is reduced to the patient burden index for the plurality of patients. 
     
     
         18 . A computer-implemented method comprising:
 parsing a protocol for a clinical trial;   providing factor data for each of a plurality of patients; and   calculating a patient burden index for each of the plurality of patients based on the parsed protocol and the provided factor data for each of the plurality of patients, wherein parsing the protocol for the clinical trial comprises analyzing a protocol document using keyword analysis and pattern matching.   
     
     
         19 . The computer-implemented method of  claim 19 , further comprising modifying the protocol to reduce the patient burden index for the plurality of patients. 
     
     
         20 . A non-transitory computer-readable medium storing instructions, which when executed by at least one data processor, result in operations comprising:
 parsing a protocol for a clinical trial;   providing factor data for each of a plurality of patients; and   calculating a patient burden index for each of the plurality of patients based on the parsed protocol and the provided factor data for each of the plurality of patients.