System and method to maintain health using personal digital phenotypes

Abstract

A system and method for identifying and treating a disease in a patient collects one or more data streams from sensors configured to detect biological signals generated within a patient's tissue over time. Patient data elements including one or more of demographic, clinical, laboratory, pathology, chemical, image, historical, genetic, and activity data for the patient is collected and processed with the data streams to generate a personalized digital phenotype (PDP). The PDP is compared to a digital taxonomy comprising prior data to classify the patient into one or more quantitative disease classifications to guide personalized intervention for treating the patient.

1 . A method for personalizing a therapy for a heart rhythm disorder in a patient, the method comprising:
 receiving electrical signal data of a patient's heart, the electrical signal data generated from using electrical sensors measuring the patient's heart;   acquiring clinical data comprising one or more of lifestyle, activity, laboratory, demographic, pathology, chemical, imaging, history, and genetic information;   linking the electrical signal data and the clinical data by nodes in a network;   computing weightings between the nodes; and   personalizing treatment for the patient based on the weightings between the nodes.   
     
     
         2 . The method of  claim 1 , wherein the network is trained using known therapy success as training samples. 
     
     
         3 . The method of  claim 1 , wherein a portion of the nodes having higher-than-average weightings represent clinical inputs with higher likelihoods of predicting treatment success. 
     
     
         4 . The method of  claim 1 , wherein a portion of the nodes having differential weightings represent clinical phenotypes that predict if the heart rhythm disorder will progress over time. 
     
     
         5 . The method of  claim 1 , wherein the heart rhythm disorder is atrial fibrillation, and wherein the clinical data linked to a portion of the nodes having higher-than-average weightings are used to predict whether the patient will respond to medications or ablation. 
     
     
         6 . The method of  claim 1 , wherein the heart rhythm disorder is ventricular tachycardia, and wherein clinical data linked to a portion of the nodes having higher-than-average weightings are used to predict whether the patient will respond to medications or ablation. 
     
     
         7 . The method of  claim 1 , wherein the clinical data linked to a portion of the nodes with higher-than-average weightings are combined with the electrical signal data to generate a personalized map to target ablation therapy. 
     
     
         8 . The method of  claim 7 , wherein a portion of the nodes linked to the clinical data are used to identify whether map patterns of focal, rotational, repetitive, or other electrical activations are targets for therapy. 
     
     
         9 . The method of  claim 1 , further comprising collecting data streams of biological signals from a biological signal sensor, wherein the biological signal sensor is one or more of an electrode, an optical sensor, a piezoelectric sensor, an acoustic sensor, an electrical resistance sensor, a thermal sensor, an accelerometer, a pressure sensor, a flow sensor, and an electrochemical sensor. 
     
     
         10 . The method of  claim 9 , wherein the biological signals comprise one or more of electrical heart signals, mechanical heart signals, heart rate, heart sounds, breathing sounds, breathing rate, breathing volume, nerve activity, and immunological signals. 
     
     
         11 . The method of  claim 1 , wherein the clinical data further comprise one or more of hemodynamic data, clinical factors associated with lung conductions, nerve signals, and biomarkers of metabolic status. 
     
     
         12 . The method of  claim 1 , wherein the nodes are weighted based on correlation analyses, logistic regression analyses, decision trees, time domain analyses, frequency domain analyses, trigonometric transformations, logarithmic transformations, cluster analysis, or unsupervised machine learning. 
     
     
         13 . The method of  claim 1 , wherein the heart rhythm disorder comprises one or more of atrial fibrillation, ventricular fibrillation, atrial tachycardia, atrial flutter, polymorphic or monomorphic ventricular tachycardia, ventricular flutter, and electrical disturbance within the heart. 
     
     
         14 . The method of  claim 7 , wherein the personalized map comprises an image representative of activations at locations within the heart, and the method further comprises identifying locations of relatively higher activation in the personalized map. 
     
     
         15 . The method of  claim 1 , further comprising reconstructing action potentials using a machine learning algorithm trained on one or more reference signals associated with different heart rhythms. 
     
     
         16 . The method of  claim 1 , wherein a personalized treatment comprises modifying at least a portion of the patient's heart by one or more of ablation by energy delivery via contact devices, energy delivery by noncontact devices, electrical therapy, thermal therapy, mechanical therapy, delivery of drug therapy, delivery of immunosuppression, delivery of stem cell therapy, and delivery of gene therapy. 
     
     
         17 . The method of  claim 1 , further comprising generating updated personal historical data for the patient, the personal historical data comprising one or more of quantitative disease classifications, the personalized treatment, and a personal treatment outcome. 
     
     
         18 . A system for personalizing a therapy for a heart rhythm disorder in a patient, the system comprising:
 an electrode catheter comprising at least one electrical sensor configured to detect electrical activity of a patient's heart by recording electrical signal data generated within the patient's heart over time;   a computing device comprising memory and one or more processors, the memory configured to store instructions, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:   receive the electrical signal data recorded by the electrode catheter;   acquire clinical data comprising one or more of lifestyle, activity, laboratory, demographic, pathology, chemical, imaging, history, and genetic information;   linking the electrical signal data and the clinical data by nodes in a network;   computing weightings between the nodes; and   personalizing treatment for the patient based on the weightings between the nodes.   
     
     
         19 . The system of  claim 18 , wherein the network is trained using known therapy success as training samples. 
     
     
         20 . The system of  claim 18 , wherein a portion of the nodes with higher-than-average weightings represent clinical inputs with higher likelihoods of predicting treatment success. 
     
     
         21 . The system of  claim 18 , wherein a portion of the nodes with differential weightings represent clinical phenotypes that predict if the heart rhythm disorder will progress over time. 
     
     
         22 . The system of  claim 18 , wherein the heart rhythm disorder is atrial fibrillation, and wherein the clinical data linked to a portion of the nodes having higher-than-average weightings are used to predict whether the patient will respond to medications or ablation. 
     
     
         23 . The system of  claim 18 , wherein the heart rhythm disorder is ventricular tachycardia, and wherein clinical data linked to a portion of the nodes having higher-than-average weightings are used to predict whether the patient will respond to medications or ablation. 
     
     
         24 . The system of  claim 18 , wherein the clinical data linked to a portion of the nodes having higher-than-average weightings are combined with the electrical signal data to generate a personalized map to target ablation therapy. 
     
     
         25 . The system of  claim 24 , wherein a portion of the nodes linked to the clinical data are used to identify whether map patterns of focal, rotational, repetitive, or other electrical activations are targets for therapy. 
     
     
         26 . The system of  claim 18 , wherein the instructions, when executed, further cause the one or more processors to collect data streams of biological signals from a biological signal sensor, wherein the biological signal sensor is one or more of an electrode, an optical sensor, a piezoelectric sensor, an acoustic sensor, an electrical resistance sensor, a thermal sensor, an accelerometer, a pressure sensor, a flow sensor, and an electrochemical sensor. 
     
     
         27 . The system of  claim 26 , wherein the biological signals comprise one or more of electrical heart signals, mechanical heart signals, heart rate, heart sounds, breathing sounds, breathing rate, breathing volume, nerve activity, and immunological signals. 
     
     
         28 . The system of  claim 18 , wherein the clinical data further comprise one or more of hemodynamic data, clinical factors associated with lung conductions, nerve signals, and biomarkers of metabolic status. 
     
     
         29 . The system of  claim 18 , wherein the nodes are weighted based on one or more of correlation analyses, logistic regression analyses, decision trees, time domain analyses, frequency domain analyses, trigonometric transformations, logarithmic transformations, cluster analysis, and unsupervised machine learning. 
     
     
         30 . The system of  claim 18 , wherein the heart rhythm disorder comprises one or more of atrial fibrillation, ventricular fibrillation, atrial tachycardia, atrial flutter, polymorphic or monomorphic ventricular tachycardia, ventricular flutter, and electrical disturbance within the heart. 
     
     
         31 . The system of  claim 24 , wherein the personalized map comprises an image representative of activations at locations within the heart, and the instructions, when executed, further cause the one or more processors to identify locations of relatively higher activation in the personalized map. 
     
     
         32 . The system of  claim 18 , wherein the instructions, when executed, further cause the one or more processors to reconstruct action potentials using a machine learning algorithm trained on one or more reference signals associated with different heart rhythms. 
     
     
         33 . The system of  claim 18 , wherein a personalized treatment comprises modifying at least a portion of the patient's tissue by one or more of ablation by energy delivery via contact devices, energy delivery by noncontact devices, electrical therapy, thermal therapy, mechanical therapy, delivery of drug therapy, delivery of immunosuppression, delivery of stem cell therapy, and delivery of gene therapy. 
     
     
         34 . The system of  claim 18 , wherein the instructions, when executed, further cause the one or more processors to generate updated personal historical data for the patient, the personal historical data comprising one or more of quantitative disease classifications, the personalized treatment, and a personal treatment outcome.