Systems and methods for subject assessment
The present disclosure provides systems and methods for performing a clinical assessment of a neurological disease, disorder, or condition. In an aspect, a system may comprise sensors, which sensors are configured to acquire sensor data of the subject over a period of time; and which mobile electronic device, comprises: an electronic display; a wireless transceiver; and one or more computer processors configured to (i) receive the sensor data from the sensors, (ii) process the sensor data or features extracted therefrom using a trained algorithm to generate an output indicative of a state of a neurological disease, disorder, or condition of the subject, and (iii) based at least in part on the generated output, perform a clinical assessment on the subject.
1 . A method of performing a clinical assessment of Parkinson's disease on a subject, comprising:
(i) displaying to a subject, via a user interface of a mobile electronic device, a prompt to perform a motor task, wherein the motor task is a member selected from the group consisting of tasks measuring vocalization, balance, gait, tapping, reaction time, resting tremor, and postural tremor;
(ii) acquiring, by one or more sensors of the mobile electronic device, sensor data of the subject during performance of the motor task by the subject, wherein the one or more sensors comprise each of an accelerometer, a touch screen sensor, a video sensor, an audio sensor, and a gyroscope sensor;
(iii) using one or more programmed computer processors to process the sensor data or features extracted therefrom, using a trained machine-learning algorithm, wherein the processing comprises:
(1) determining a simulated dopamine transporter scan (DaTScan) tracer uptake measurement value based at least in part on the sensor data or features extracted therefrom, and
(2) generating an output indicative of a state of Parkinson's disease of the subject, wherein the generated output comprises a prediction of dopamine neuron loss based on the simulated DaTScan tracer uptake measurement value; and
(iv) based at least in part on the generated output, performing the clinical assessment of Parkinson's disease on the subject, wherein the clinical assessment comprises a radiological brain imaging test or a polysomnography test.
2 . The method of claim 1 , wherein (iii) further comprises (a) processing the sensor data to determine motor function scores, and (b) processing the motor function scores to generate the output.
3 . The method of claim 1 , further comprising providing a treatment to the subject based at least in part on the clinical assessment.
4 . The method of claim 1 , wherein the sensor data comprise a each of inertial measurement units (IMUs), event times, coordinates of an electronic display, audio recordings, digital images, and video recordings.
5 . The method of claim 1 , wherein (iii) further comprises processing patient reported outcome measure (PROM) data, medication-specific data, or data from a behavioral test of cognitive function, using the trained machine learning algorithm.
6 . The method of claim 5 , wherein (iii) further comprises processing at least one of the sensor data, the PROM data, or the data from the behavioral test of cognitive function to determine motor function scores; and processing the motor function scores to generate the output.
7 . The method of claim 6 , wherein the PROM data comprise quality of life, pain, fatigue, patient function, clinical events, or symptom severity data.
8 . The method of claim 5 , wherein the medication-specific data comprises medication specific to the treatment of Parkinson's disease.
9 . The method of claim 1 , wherein the trained machine learning algorithm comprises a machine learning classifier.
10 . The method of claim 9 , wherein the machine learning classifier is selected from the group consisting of a support vector machine (SVM), a naïve Bayes classification, a random forest, a neural network, a deep neural network (DNN), a recurrent neural network (RNN), a deep RNN, a long short-term memory (LSTM) recurrent neural network (RNN), and a gated recurrent unit (GRU) recurrent neural network (RNN).
11 . The method of claim 1 , wherein the Parkinson's disease comprises dementia with Lewy bodies, multiple system atrophy, prodromal stage Parkinson's disease, progressive supranuclear palsy (PSP), corticobasal degeneration (CBD), REM Sleep Behavior Disorder (RBD), or Parkinson's dementia.
12 . The method of claim 1 , wherein the radiological brain imaging test comprises determining dopamine neuron loss in a brain area.
13 . The method of claim 12 , wherein the brain area comprises basal ganglia, striatum, putamen, or caudate nucleus.
14 . The method of claim 1 , wherein the radiological brain imaging test comprises a Dopamine Active Transporter tomography scan (DaTscan).
15 . The method of claim 1 , wherein the clinical assessment comprises the polysomnography test.
16 . The method of claim 1 , further comprising using the polysomnography test to detect a presence or an absence of rapid eye movement (REM) sleep behavior disorder (RBD) in the subject.
17 . The method of claim 1 , further comprising using the generated output to classify the subject as having a pre-determined outcome of the clinical assessment or likely to have a pre-determined outcome of the clinical assessment.
18 . The method of claim 1 , wherein the generated output comprises a predicted risk or likelihood of the subject having a pre-determined outcome of the clinical assessment.
19 . The method of claim 1 , wherein the generated output comprises a predicted severity of Parkinson's disease in the subject.
20 . The method of claim 1 , wherein the generated output comprises an indication of whether the subject is likely to benefit from enrollment into a clinical trial.
21 . The method of claim 1 , wherein the generated output comprises an indication of whether the subject is likely to benefit from initiation or alteration of medications or therapies.
22 . The method of claim 1 , wherein the generated output provides sufficient evidence to detect Parkinson's disease in the subject.
23 . The method of claim 1 , wherein the generated output comprises an estimated composite clinical motor score (CMS), an estimated clinical cognitive score (CCS), an estimated Unified Parkinson's Disease Rating Scale (UPDRS) total, or a UPDRS-III score.
24 . The method of claim 1 , wherein the clinical assessment comprises the radiological brain imaging test.