Identifying and characterising sources of variability in digital outcome measures in Parkinson's disease.

Smartphones and wearables are widely recognised as the foundation for novel Digital Health Technologies (DHTs) for the clinical assessment of Parkinson's disease. Yet, only limited progress has been made towards their regulatory acceptability as effective drug development tools. A key barrier in achieving this goal relates to the influence of a wide range of sources of variability (SoVs) introduced by measurement processes incorporating DHTs, on their ability to detect relevant changes to PD. This paper introduces a conceptual framework to assist clinical research teams investigating a specific Concept of Interest within a particular Context of Use, to identify, characterise, and when possible, mitigate the influence of SoVs. We illustrate how this conceptual framework can be applied in practice through specific examples, including two data-driven case studies.

How can natural language processing help model informed drug development?: a review.

Objective: To summarize applications of natural language processing (NLP) in model informed drug development (MIDD) and identify potential areas of improvement. Materials and Methods: Publications found on PubMed and Google Scholar, websites and GitHub repositories for NLP libraries and models. Publications describing applications of NLP in MIDD were reviewed. The applications were stratified into 3 stages: drug discovery, clinical trials, and pharmacovigilance. Key NLP functionalities used for these applications were assessed. Programming libraries and open-source resources for the implementation of NLP functionalities in MIDD were identified. Results: NLP has been utilized to aid various processes in drug development lifecycle such as gene-disease mapping, biomarker discovery, patient-trial matching, adverse drug events detection, etc. These applications commonly use NLP functionalities of named entity recognition, word embeddings, entity resolution, assertion status detection, relation extraction, and topic modeling. The current state-of-the-art for implementing these functionalities in MIDD applications are transformer models that utilize transfer learning for enhanced performance. Various libraries in python, R, and Java like huggingface, sparkNLP, and KoRpus as well as open-source platforms such as DisGeNet, DeepEnroll, and Transmol have enabled convenient implementation of NLP models to MIDD applications. Discussion: Challenges such as reproducibility, explainability, fairness, limited data, limited language-support, and security need to be overcome to ensure wider adoption of NLP in MIDD landscape. There are opportunities to improve the performance of existing models and expand the use of NLP in newer areas of MIDD. Conclusions: This review provides an overview of the potential and pitfalls of current NLP approaches in MIDD.

Metadata Framework to Support Deployment of Digital Health Technologies in Clinical Trials in Parkinson's Disease.

Sensor data from digital health technologies (DHTs) used in clinical trials provides a valuable source of information, because of the possibility to combine datasets from different studies, to combine it with other data types, and to reuse it multiple times for various purposes. To date, there exist no standards for capturing or storing DHT biosensor data applicable across modalities and disease areas, and which can also capture the clinical trial and environment-specific aspects, so-called metadata. In this perspectives paper, we propose a metadata framework that divides the DHT metadata into metadata that is independent of the therapeutic area or clinical trial design (concept of interest and context of use), and metadata that is dependent on these factors. We demonstrate how this framework can be applied to data collected with different types of DHTs deployed in the WATCH-PD clinical study of Parkinson's disease. This framework provides a means to pre-specify and therefore standardize aspects of the use of DHTs, promoting comparability of DHTs across future studies.

Precompetitive Consensus Building to Facilitate the Use of Digital Health Technologies to Support Parkinson Disease Drug Development through Regulatory Science.

Innovative tools are urgently needed to accelerate the evaluation and subsequent approval of novel treatments that may slow, halt, or reverse the relentless progression of Parkinson disease (PD). Therapies that intervene early in the disease continuum are a priority for the many candidates in the drug development pipeline. There is a paucity of sensitive and objective, yet clinically interpretable, measures that can capture meaningful aspects of the disease. This poses a major challenge for the development of new therapies and is compounded by the considerable heterogeneity in clinical manifestations across patients and the fluctuating nature of many signs and symptoms of PD. Digital health technologies (DHT), such as smartphone applications, wearable sensors, and digital diaries, have the potential to address many of these gaps by enabling the objective, remote, and frequent measurement of PD signs and symptoms in natural living environments. The current climate of the COVID-19 pandemic creates a heightened sense of urgency for effective implementation of such strategies. In order for these technologies to be adopted in drug development studies, a regulatory-aligned consensus on best practices in implementing appropriate technologies, including the collection, processing, and interpretation of digital sensor data, is required. A growing number of collaborative initiatives are being launched to identify effective ways to advance the use of DHT in PD clinical trials. The Critical Path for Parkinson's Consortium of the Critical Path Institute is highlighted as a case example where stakeholders collectively engaged regulatory agencies on the effective use of DHT in PD clinical trials. Global regulatory agencies, including the US Food and Drug Administration and the European Medicines Agency, are encouraging the efficiencies of data-driven engagements through multistakeholder consortia. To this end, we review how the advancement of DHT can be most effectively achieved by aligning knowledge, expertise, and data sharing in ways that maximize efficiencies.

Approaching neural net feature interpretation using stacked autoencoders: gene expression profiling of systemic lupus erythematosus patients.

Systemic lupus erythematosus (SLE) is a rare, autoimmune disorder known to affect most organ sites. Complicating clinical management is a poorly differentiated, heterogenous SLE disease state. While some small molecule drugs and biologics are available for treatment, additional therapeutic options are needed. Parsing complex biological signatures using powerful, yet human interpretable approaches is critical to advancing our understanding of SLE etiology and identifying therapeutic repositioning opportunities. To approach this goal, we developed a semi-supervised deep neural network pipeline for gene expression profiling of SLE patients and subsequent characterization of individual gene features. Our pipeline performed exemplar multinomial classification of SLE patients in independent balanced validation (F1=0.956) and unbalanced, under-powered testing (F1=0.944) cohorts. A stacked autoencoder disambiguated individual feature representativeness by regenerating an input-like(A ') feature matrix. A to A' comparisons suggest the top associated features to be key features in gene expression profiling using neural nets.