Search NASA⌕ Search

SEARCH · Search NASA

Results for “clinical development”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5

Clinical Decision Support - Concepts of Operation

We are entering a new era in space exploration to return to the moon and explore Mars. Crew members operating independently during long duration space exploration missions will require a clinical decision support system (CDSS) to increase autonomy by augmenting their knowledge, skills and abilities in different scenarios. Significant changes to in-flight and habitat medical care due to constraints on mass, volume, power, crew time and medical evacuation capabilities are needed to increase crew autonomy and self-reliance in decision making and task performance. The Exploration Medical Capability (ExMC) Element of the Human Research Program (HRP) pushes the boundary of space medical systems to advance the care of astronauts on future exploration missions beyond low Earth orbit by identifying and testing next-generation medical care and crew health maintenance technologies. Clinical decision support (CDS) presents knowledge and data in a context aware manner to augment a crew members’ knowledge, skills and abilities during the process of observation, orientation, decisions and action. A comprehensive crew health and performance CDSS is required to augment crew capability and will be used in different scenarios for several reasons. In general, the CDSS’s role is to assist the crew in prevention, detection, diagnosis and treatment of crew health and performance related conditions that may arise in exploration spaceflight. For example, CDSS would assist a high acuity scenario such as a heart attack by supplying clear instructions, vital signs and treatment reminders. A lower severity scenario such as kidney stone risk could interface to vehicle systems and display more complex predictive data during a diagnosis. A CDSS needs to contribute to successful missions by maintaining a high performing crew who can potentially exhibit countless medical conditions related to derangements from the space environment (sleep, cognition, nutrition and exercise) as well as conditions intrinsic to humans anywhere. While supporting the crew’s ability to make sound clinical decisions is desirable in any mission, it is essential for exploration missions with significant communication delays, no evacuation capability, and extended exposure to the flight environment. Such missions correspond with medical Level of Care V (LOC V), the highest level specified in NASA-STD-3001. The project focuses on CDS implementation research to derive requirements for LOC V, where the need for increased autonomy results in new practices and the inclusion of non-clinical data, such as vehicle environmental measures and physical exercise results, from other human and vehicle domains and advanced analytics. The CDS project describes how the CDSS is intended to be used by defining concepts of operations (ConOps). The process to derive ConOps focuses on increased autonomy that reduces the likelihood and consequences of accepted medical conditions. These crew health and performance inputs are grouped by common datasets and analysis models. Use cases are derived to research new clinical scenarios, architectural development and workflows. Implementation research is conducted with protypes to inform assumptions and derive requirements. The project also establishes how externally developed analysis and approaches can be added to expand a clinical decision support system and thus highlight how a comprehensive system can be globally developed with collaborators. This presentation will cover example scenarios from the CDS ConOps and the method to derive them. One example scenario will be CDSS alerting an increased kidney stone risk during a mission, with diagnosis and treatment options provided during the intervention.

clinical decision support↗

Clinical Decision Support - Concepts of Operation

We are entering a new era in space exploration to return to the moon and explore Mars. Crew members operating independently during long duration space exploration missions will require a clinical decision support system (CDSS) to increase autonomy by augmenting their knowledge, skills and abilities in different scenarios. Significant changes to in-flight and habitat medical care due to constraints on mass, volume, power, crew time and medical evacuation capabilities are needed to increase crew autonomy and self-reliance in decision making and task performance. The Exploration Medical Capability (ExMC) Element of the Human Research Program (HRP) pushes the boundary of space medical systems to advance the care of astronauts on future exploration missions beyond low Earth orbit by identifying and testing next-generation medical care and crew health maintenance technologies. Clinical decision support (CDS) presents knowledge and data in a context aware manner to augment a crew members’ knowledge, skills and abilities during the process of observation, orientation, decisions and action. A comprehensive crew health and performance CDSS is required to augment crew capability and will be used in different scenarios for several reasons. In general, the CDSS’s role is to assist the crew in prevention, detection, diagnosis and treatment of crew health and performance related conditions that may arise in exploration spaceflight. For example, CDSS would assist a high acuity scenario such as a heart attack by supplying clear instructions, vital signs and treatment reminders. A lower severity scenario such as kidney stone risk could interface to vehicle systems and display more complex predictive data during a diagnosis. A CDSS needs to contribute to successful missions by maintaining a high performing crew who can potentially exhibit countless medical conditions related to derangements from the space environment (sleep, cognition, nutrition and exercise) as well as conditions intrinsic to humans anywhere. While supporting the crew’s ability to make sound clinical decisions is desirable in any mission, it is essential for exploration missions with significant communication delays, no evacuation capability, and extended exposure to the flight environment. Such missions correspond with medical Level of Care V (LOC V), the highest level specified in NASA-STD-3001. The project focuses on CDS implementation research to derive requirements for LOC V, where the need for increased autonomy results in new practices and the inclusion of non-clinical data, such as vehicle environmental measures and physical exercise results, from other human and vehicle domains and advanced analytics. The CDS project describes how the CDSS is intended to be used by defining concepts of operations (ConOps). The process to derive ConOps focuses on increased autonomy that reduces the likelihood and consequences of accepted medical conditions. These crew health and performance inputs are grouped by common datasets and analysis models. Use cases are derived to research new clinical scenarios, architectural development and workflows. Implementation research is conducted with protypes to inform assumptions and derive requirements. The project also establishes how externally developed analysis and approaches can be added to expand a clinical decision support system and thus highlight how a comprehensive system can be globally developed with collaborators. This presentation will cover example scenarios from the CDS ConOps and the method to derive them. One example scenario will be CDSS alerting an increased kidney stone risk during a mission, with diagnosis and treatment options provided during the intervention.

clinical decision support↗

Clinical Outcome Metrics for Optimization of Robust Training

The objective of this research is to develop and use clinical outcome metrics and training tools to quantify the differences in performance of a physician vs non‐physician crew medical officer (CMO) analogues during simulations.

Ebert, Doug↗

Clinical pharmacology information in regulatory submissions and labeling: A comparative analysis of orphan and non-orphan drugs approved by the FDA

Clinical pharmacology is an integral discipline supporting the development, regulatory evaluation, and clinical use of drugs for the treatment of both common and rare diseases. Here, we evaluated the recommendations and information available from select clinical pharmacology studies in the therapeutic product labeling of new molecular entities (NMEs) approved from 2017 to 2019 for both common and rare diseases. A total of 151 NMEs, including 72 orphan and 79 non-orphan drugs, were analyzed for recommendations and information available related to food–drug interaction, drug–drug interaction, renal impairment, hepatic impairment, QT assessment, and human radiolabeled mass balance studies using data collected from the original labeling and other regulatory documents. The analysis showed no statistically significant difference in the recommendations between orphan and non-orphan drugs except for renal impairment related recommendations in section 8 of the labeling. Although not significant, fewer hepatic impairment labeling recommendations were available for orphan drugs when compared with non-orphan drugs. At the time of initial approval, 79 postmarketing requirements (PMRs) and postmarketing commitments (PMCs) for 33 orphan drugs and 39 PMRs and PMCs for 19 non-orphan drugs were established; with most difference observed for drug–drug interaction, hepatic impairment, and QT assessment. Overall, although there was a trend for more labeling recommendations and fewer postmarketing studies and clinical trials for non-orphan drugs, there appeared to be no substantial differences in how these select clinical pharmacology studies are leveraged during the development and approval of orphan and non-orphan drugs.

60 APPLIED LIFE SCIENCES↗

Evaluation of Human Research Facility Ultrasound With the ISS Video System

Most medical equipment on the International Space Station (ISS) is manifested as part of the U.S. or the Russian medical hardware systems. However, certain medical hardware is also available as part of the Human Research Facility. The HRF and the JSC Medical Operations Branch established a Memorandum of Agreement for joint use of certain medical hardware, including the HRF ultrasound system, the only diagnostic imaging device currently manifested to fly on ISS. The outcome of a medical contingency may be changed drastically, or an unnecessary evacuation may be prevented, if clinical decisions are supported by timely and objective diagnostic information. In many higher-probability medical scenarios, diagnostic ultrasound is a first-choice modality or provides significant diagnostic information. Accordingly, the Clinical Care Capability Development Project is evaluating the HRF ultrasound system for its utility in relevant clinical situations on board ISS. For effective management of these ultrasound-supported ISS medical scenarios, the resulting data should be available for viewing and interpretation on the ground, and bidirectional voice communication should be readily available to allow ground experts (sonographers, physicians) to provide guidance to the Crew Medical Officer. It may also be vitally important to have the capability of real-time guidance via video uplink to the CMO-operator during an exam to facilitate the diagnosis in a timely fashion. In this document, we strove to verify that the HRF ultrasound video output is compatible with the ISS video system, identify ISS video system field rates and resolutions that are acceptable for varying clinical scenaiios, and evaluate the HRF ultrasound video with a commercial, off-the-shelf video converter, and compare it with the ISS video system.

Melton, Shannon↗

Lunar Surface Reference Missions: A Description of Human and Robotic Surface Activities

Most medical equipment to the International Space Station (ISS) is manisfested as part of the U.S. or the Russian medical hardware systems. However, certain medical hardware is also available as part of the Human Research Facility. The HRF and the JSC Medical Operations Branch established a Memorandum of Agreement for joint use of certain medical hardware, including the HRF ultrasound system, the only diagnostic imaging device currently manifested to fly on ISS. The outcome of a medical contingency may be changed drastically, or an unnecessary evacuation may be prevented, if clinical decisions are supported by timely and objective diagnostic information. In many higher-probability medical scenarios, diagnostic ultrasound is a first-choice modality or provides significant diagnostic information. Accordingly, the Clinical Care Capability Development Project is evaluating the HRF ultrasound system for its utility in relevant clinical siruations on board ISS. For effective management of these ultrasound-supported ISS medical scenarios, the resulting data should be available for viewing and interpretation on the ground, and bidirectional voice communication should be readily available to allow ground experts (sonographers, physicians) to provide guidance to the Crew Medical Officer. It may also be vitally important to have the capability of real-time guidance via video uplink to the CMO-opertor during an exam to facilitate the diagnosis in a timely fashion.

Duke, Michael B.↗

What Clinical Trials Can Teach Us About the Development of More Resilient AI for Cybersecurity

Policy-mandated, rigorously administered scientific testing is needed to provide transparency into the efficacy of artificial intelligence-–based (AI-based) cyber defense tools for consumers and to prioritize future research and development. In this work, we propose a model that is informed by our experience, urged forward by massive-scale cyberattacks, and inspired by parallel developments in the biomedical field and the unprecedentedly fast development of new vaccines to combat global pathogens.

97 MATHEMATICS AND COMPUTING↗

Flow Analysis of the Cleveland Clinic Centrifugal Pump

An implantable ventricular assist rotordynamic blood pump is being developed by the Cleveland Clinic Foundation in cooperation with the NASA Lewis Research Center. At the nominal design condition, the pump provides blood flow at the rate of 5 liters per minute at a pressure rise of 100 mm of mercury and a rotative speed of 3000 RPM. Bench testing of the centrifugal pump in a water/glycerin mixture has provided flow and pressure data at several rotative speeds. A one-dimensional empirical based pump flow analysis computer code developed at NASA Lewis Research Center has been used in the design process to simulate the flow in the primary centrifugal pump stage. The computer model was used to size key impeller and volute geometric parameters that influence pressure rise and flow. Input requirements to the computer model include a simple representation of the pump geometry. The model estimates the flow conditions at the design and at off-design operating conditions at the impeller leading and trailing edges and the volute inlet and exit. The output from the computer model is compared to flow and pressure data obtained from bench testing.

Veres, Joseph P.↗

Psychiatric diagnoses in a group of astronaut applicants

Between 1959 and 1987, the psychiatric evaluation of astronaut candidates evolved from a 30-h intensive examination evaluating applicants for psychopathology, and studying their performance under stress, to a 2-h clinical interview whose structure and contents were determined by the individual examiner. Evaluations done during these years applied both psychiatric (or, 'select-out') criteria and psychological (or, 'select-in') criteria. In an attempt to more rigorously define the psychiatric, 'select-out' component, a standardized, semistructured clinical interview was developed to identify the presence or history of psychiatric disorders listed in the Diagnostic and Statistical Manual of Mental Disorders, 3rd Ed. ('DSM-III'). A total of 117 astronaut applicants underwent this clinical interview as part of a comprehensive medical evaluation during a recent astronaut selection. Of the 117 applicants, 9 (7.7 percent) met DSM-III criteria for a variety of Axis I and Axis II diagnoses, including V-code diagnoses.

Santy, Patricia A.↗

Quantification of mitral regurgitation by automated cardiac output measurement: experimental and clinical validation

OBJECTIVES: To develop and validate an automated noninvasive method to quantify mitral regurgitation. BACKGROUND: Automated cardiac output measurement (ACM), which integrates digital color Doppler velocities in space and in time, has been validated for the left ventricular (LV) outflow tract but has not been tested for the LV inflow tract or to assess mitral regurgitation (MR). METHODS: First, to validate ACM against a gold standard (ultrasonic flow meter), 8 dogs were studied at 40 different stages of cardiac output (CO). Second, to compare ACM to the LV outflow (ACMa) and inflow (ACMm) tracts, 50 normal volunteers without MR or aortic regurgitation (44+/-5 years, 31 male) were studied. Third, to compare ACM with the standard pulsed Doppler-two-dimensional echocardiographic (PD-2D) method for quantification of MR, 51 patients (61+/-14 years, 30 male) with MR were studied. RESULTS: In the canine studies, CO by ACM (1.32+/-0.3 liter/min, y) and flow meter (1.35+/-0.3 liter/min, x) showed good correlation (r=0.95, y=0.89x+0.11) and agreement (deltaCO(y-x)=0.03+/-0.08 [mean+/-SD] liter/min). In the normal subjects, CO measured by ACMm agreed with CO by ACMa (r=0.90, p < 0.0001, deltaCO=-0.09+/-0.42 liter/min), PD (r=0.87, p < 0.0001, deltaCO=0.12+/-0.49 liter/min) and 2D (r=0.84, p < 0.0001, deltaCO=-0.16+/-0.48 liter/min). In the patients, mitral regurgitant volume (MRV) by ACMm-ACMa agreed with PD-2D (r= 0.88, y=0.88x+6.6, p < 0.0001, deltaMRV=2.68+/-9.7 ml). CONCLUSIONS: We determined that ACM is a feasible new method for quantifying LV outflow and inflow volume to measure MRV and that ACM automatically performs calculations that are equivalent to more time-consuming Doppler and 2D measurements. Additionally, ACM should improve MR quantification in routine clinical practice.

Non-NASA Center↗

The evolution of analytical techniques for multiplex analysis of protein biomarkers

Introduction: The landscape of biomarker development has evolved with advanced analytical technologies, particularly affinity- and mass spectrometry-based techniques. These advancements have deepened our understanding of disease mechanisms, enabling the development of precise diagnostic tools and personalized medicine. Protein biomarkers, which play pivotal roles in biological processes, have become invaluable in diagnosing and monitoring diseases, aided by their presence in various biological samples and the availability of established detection methods. Areas covered: This review covers the role of protein biomarkers in clinical practice, the development and dimensionality of protein biomarkers, advancements in detection technologies, a comparison of these technologies, and future directions in biomarker discovery and disease mechanism elucidation. Expert opinion: Advances in biomarker technologies have the potential to transform diagnostics and personalized treatment but face challenges such as high costs and technical complexity. Enhancing reproducibility and integrating multi-omics approaches may offer better insights. In conclusion, the field should evolve toward high-throughput, automated methods, continuously adapting research, and clinical practices.

59 BASIC BIOLOGICAL SCIENCES↗

Antimicrobial Peptide Mimics for Clinical Use: Does Size Matter?

The search for efficient antimicrobial therapies that can alleviate suffering caused by infections from resistant bacteria is more urgent than ever before. Infections caused by multi-resistant pathogens represent a significant and increasing burden to healthcare and society and researcher are investigating new classes of bioactive compounds to slow down this development. Antimicrobial peptides from the innate immune system represent one promising class that offers a potential solution to the antibiotic resistance problem due to their mode of action on the microbial membranes. However, challenges associated with pharmacokinetics, bioavailability and off-target toxicity are slowing down the advancement and use of innate defensive peptides. Improving the therapeutic properties of these peptides is a strategy for reducing the clinical limitations and synthetic mimics of antimicrobial peptides are emerging as a promising class of molecules for a variety of antimicrobial applications. These compounds can be made significantly shorter while maintaining, or even improving antimicrobial properties, and several downsized synthetic mimics are now in clinical development for a range of infectious diseases. A variety of strategies can be employed to prepare these small compounds and this review describes the different compounds developed to date by adhering to a minimum pharmacophore based on an amphiphilic balance between cationic charge and hydrophobicity. These compounds can be made as small as dipeptides, circumventing the need for large compounds with elaborate three-dimensional structures to generate simplified and potent antimicrobial mimics for a range of medical applications. This review highlights key and recent development in the field of small antimicrobial peptide mimics as a promising class of antimicrobials, illustrating just how small you can go.

60 APPLIED LIFE SCIENCES↗

The flavonoid procyanidin C1 has senotherapeutic activity and increases lifespan in mice

Ageing-associated functional decline of organs and increased risk for age-related chronic pathologies is driven in part by the accumulation of senescent cells, which develop the senescence-associated secretory phenotype (SASP). Here we show that procyanidin C1 (PCC1), a polyphenolic component of grape seed extract (GSE), increases the healthspan and lifespan of mice through its action on senescent cells. By screening a library of natural products, we find that GSE, and PCC1 as one of its active components, have specific effects on senescent cells. At low concentrations, PCC1 appears to inhibit SASP formation, whereas it selectively kills senescent cells at higher concentrations, possibly by promoting production of reactive oxygen species and mitochondrial dysfunction. In rodent models, PCC1 depletes senescent cells in a treatment-damaged tumour microenvironment and enhances therapeutic efficacy when co-administered with chemotherapy. Intermittent administration of PCC1 to either irradiated, senescent cell-implanted or naturally aged old mice alleviates physical dysfunction and prolongs survival. We identify PCC1 as a natural senotherapeutic agent with in vivo activity and high potential for further development as a clinical intervention to delay, alleviate or prevent age-related pathologies.

60 APPLIED LIFE SCIENCES↗

Evaluation of Cross-Protection of African Swine Fever Vaccine ASFV-G-ΔI177L Between ASFV Biotypes

Background/Objectives: Vaccine development for the prevention of ASF has been very challenging due to the extensive genetic and largely unknown antigenic diversity. Inactivated vaccines, using different inactivation methods and a variety of adjuvants, have been consistently inefficacious. Historically, animals recovering from an infection with an attenuated virus became protected from the development of a clinical disease caused by an antigenically related strain. Therefore, immunization of susceptible animals with attenuathe ted virus strains has become a common method of vaccination with the first two commercially available vaccines based on recombinant live-attenuated viruses (LAVs). An important limitation is that the efficacy of the LAV is restricted to those strains that are antigenically related and, in most cases, only provide protection against homologous strains. Due to the unknown antigenic heterogeneity among all ASFV field isolates, the development of broad-spectrum vaccines is a challenge. Besides the anecdotal data, there is not a large amount of information describing patterns of cross-protection between different ASFV strains. Methods: We evaluated the cross-protection induced by the ASFV live-attenuated vaccine ASFV-G-ΔI177L against different biotypes of ASFV and compared their genomic sequences to determine potential genetic mutations that could cause the lack of cross-protection. Results: Results presented here demonstrate different patterns of protection when ASFV-G-ΔI177L vaccinated pigs were challenged with six different ASFV field isolates belonging to different biotypes. Conclusions: The presence of cross-protection cannot be predicted solely by the classical methodology for genotyping-based B646L ORF only. Biotyping, considering the entire virus proteome, appears to be a more promising prediction tool, although additional gathering of experimental data will be necessary to fully validate it; until then, the presence of cross-protection needs to be confirmed in efficacy trials challenging vaccinated animals.

Immunology↗

Clinical knowledge extraction via sparse embedding regression (KESER) with multi-center large scale electronic health record data

The increasing availability of electronic health record (EHR) systems has created enormous potential for translational research. However, it is difficult to know all the relevant codes related to a phenotype due to the large number of codes available. Traditional data mining approaches often require the use of patient-level data, which hinders the ability to share data across institutions. In this project, we demonstrate that multi-center large-scale code embeddings can be used to efficiently identify relevant features related to a disease of interest. We constructed large-scale code embeddings for a wide range of codified concepts from EHRs from two large medical centers. We developed knowledge extraction via sparse embedding regression (KESER) for feature selection and integrative network analysis. We evaluated the quality of the code embeddings and assessed the performance of KESER in feature selection for eight diseases. Besides, we developed an integrated clinical knowledge map combining embedding data from both institutions. The features selected by KESER were comprehensive compared to lists of codified data generated by domain experts. Features identified via KESER resulted in comparable performance to those built upon features selected manually or with patient-level data. The knowledge map created using an integrative analysis identified disease-disease and disease-drug pairs more accurately compared to those identified using single institution data. Analysis of code embeddings via KESER can effectively reveal clinical knowledge and infer relatedness among codified concepts. KESER bypasses the need for patient-level data in individual analyses providing a significant advance in enabling multi-center studies using EHR data.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

A microCT-based platform to quantify drug targeting

Abstract Background Heterotopic ossification (HO) is a frequent and debilitating complication of traumatic musculoskeletal injuries and orthopedic procedures. Prophylactic dosing of botulinum toxin type A (BTxA) holds potential as a novel treatment option if accurately distributed throughout soft-tissue volumes where protection is clinically desired. We developed a high-resolution, microcomputed tomography (microCT)-based imaging strategy to assess drug distribution and validated this platform by quantifying distribution achieved via a prototype delivery system versus a single-bolus injection. Methods We injected an iodine-containing contrast agent (iodixanol 320 mg I/mL) into dissected rabbit musculature followed by microCT imaging and analysis. To contrast the performance of distributed versus bolus injections, a three-dimensional (3D) 64-cm 3 -printed soft-tissue holder was developed. A centered 2-cm 3 volume of interest (VOI) was targeted with a single-bolus injection or an equal volume distributed injection delivered via a 3D-printed prototype. VOI drug coverage was quantified as a percentage of the VOI volume that was < 1.0 mm from the injected fluid. Results The microCT-based approach enabled high-resolution quantification of injection distribution within soft tissue. The distributed dosing prototype provided significantly greater tissue coverage of the targeted VOI (72 ± 3%, mean ± standard deviation) when compared to an equal volume bolus dose (43 ± 5%, p = 0.031) while also enhancing the precision of injection targeting. Conclusions A microCT-based imaging technique precisely quantifies drug distribution within a soft-tissue VOI, providing a path to overcome a barrier for clinical translation of prophylactic inhibition of HO by BTxA. Relevance statement This platform will facilitate rapid optimization of injection parameters for clinical devices used to effectively and safely inhibit the formation of heterotopic ossification. Key points • MicroCT provides high-resolution quantification of soft-tissue drug distribution. • Distributed dosing is required to maximize soft-tissue drug coverage. • Imaging platform will enable rapid screening of 3D-printed drug distribution prototypes. Graphical Abstract

Ausk, Brandon J. (ORCID:0000000335338303)↗

Exploration Medical Capability Science and Research Overview and Update

The mission of the Exploration Medical Capability (ExMC) Element is to advance medical system design and risk-informed decision making for exploration beyond Low Earth Orbit to promote human health and performance in space. To accomplish this mission, ExMC focuses on several key areas: • Investigating specific risks that are relevant for human exploration spaceflight, including in-flight medical conditions, degraded or toxic medications, and renal stones • Developing medical probabilistic risk analysis tools that are integrated with systems engineering processes to inform the medical system trade space and support the development of robust requirements • Demonstrating and defining requirements for a prototype clinical decision support system • Developing and demonstrating novel medical technologies that will improve future medical capabilities in space This presentation will focus on selected scientific and technical conceptual drivers for the Element and its current and future research risks and gaps while providing an overview of the Element’s progress in 2021 and areas of focus for 2022.

Benjamin Easter↗

Optimizing Patient-Specific Medication Regimen Policies Using Wearable Sensors in Parkinson’s Disease

Effective treatment of Parkinson’s disease (PD) is a continual challenge for healthcare providers, and providers can benefit from leveraging emerging technologies to supplement traditional clinic care. We develop a data-driven reinforcement learning (RL) framework to optimize PD medication regimens through wearable sensors. We leverage a data set of n = 26 PD patients who wore wrist-mounted movement trackers for two separate six-day periods. Using these data, we first build and validate a simulation model of how individual patients’ movement symptoms respond to medication administration. We then pair this simulation model with an on-policy RL algorithm that recommends optimal medication types, timing, and dosages during the day while incorporating human-in-the-loop considerations on medication administration. The results show that the RL-prescribed medication regimens outperform physicians’ medication regimens, despite physicians having access to the same data as the RL agent. To validate our results, we assess our wearable-based RL medication regimens using n = 399 PD patients from the Parkinson’s Progression Markers Initiative data set. We show that the wearable-based RL medication regimens would lead to significant symptom improvement for these patients, even more so than training RL policies directly from this data set. In doing so, we show that RL models from even small data sets of wearable data can offer novel, generalizable clinical insights and medication strategies, which may outperform those derived from larger data sets without wearable data.

60 APPLIED LIFE SCIENCES↗