Advanced Modeling & Analysis Services

Koneksa Health's Advanced Modeling and Analysis Services is a full-service solution designed to help clinical trial sponsors unlock actionable insights from complex, multi-modal digital data. In modern clinical trials, digital biomarkers promise richer and more sensitive endpoints — but realizing that value requires expert processing, rigorous statistical methodology, and advanced modeling capabilities. Koneksa's team partners with pharmaceutical sponsors, biotech companies, and research foundations to accelerate development timelines, improve trial design, and strengthen regulatory submissions.

The service is purpose-built for organizations working with wearable and sensor-derived data at scale, including those pursuing digital biomarker validation, disease progression monitoring, and novel endpoint development across a range of therapeutic areas including neurology, cardiovascular disease, respiratory conditions, and rare diseases.

Scalable Data Processing

• Cloud-native pipelines capable of handling terabytes of time-series data from wearables and sensors
• Flexible architecture that supports both standard and custom algorithms across diverse study designs
• Outputs are structured, analysis-ready datasets suitable for downstream modeling and regulatory use
• Scaled compute infrastructure enabling 10–20x faster delivery of extracted insights compared to conventional approaches

Statistical and Machine Learning Modeling

• Development of comprehensive Statistical Analysis Plans (SAPs) tailored to study objectives
• Longitudinal modeling of disease progression across slow-variable and complex populations
• Assessment of test-retest reliability and other dimensions of clinical validity
• Machine learning model development for feature selection, risk scoring, and endpoint optimization
• Power analyses to inform study design and optimize sample size

Scientific Consulting and Reporting

• Support for regulatory-facing documentation and submission-ready outputs
• Data visualization and interactive result exploration for client teams
• Guidance on endpoint selection, adaptive design strategies, and predictive modeling approaches
• Ongoing collaboration to maximize the commercial impact of digital biomarkers

Disease Models Built on Digital Measures

• PD On/Off: Symptomatic levodopa dose response curve, also applicable to drugs for other neurological conditions, pain, hypertension, ADHD, and addictions
• PD Risk Score: Prognostic biomarker using known precursors to diagnosis, with potential application across other indications using similar composite approaches
• PD Progression: Amplifying progression signal in slow, variable disease progression; applicable to palsies, cardiovascular disease, Huntington's disease, and multiple sclerosis
• Ambulatory Function: Functional capacity assessment at home in indications that reduce physical capacity, including cardiovascular disease, HPP, asthma, and knee osteoarthritis
• Neuro EEG: Prognostic biomarker leveraging EEG power spectrum analysis for neurologic changes prior to clinical presentation, cardiac events before ischemia, and early symptom detection
• ALS Progression: Isolating progression rate in variable populations; applicable to dementias, PSP, and diseases without established progression models such as lysosomal disorders
• SCD Pain Crisis: Objective detection of clinical events; applicable to asthma, COPD, migraine, epilepsy, ataxias, and most autoimmune disorders

Client Project Impact

• Parkinson's Risk Prediction: In partnership with the Michael J. Fox Foundation and Verily, Koneksa processed 32 TB of smartwatch data (150,000 files from 350 participants) to develop a composite machine learning predictor that stratified individuals into high- and low-risk groups. The resulting digital risk index predicted clinical test outcomes and supported identification of individuals at elevated risk for targeted intervention.
• ALS Progression: For a leading biopharmaceutical company, Koneksa processed approximately 1.5 TB of tri-axial accelerometry data from 450+ participants. Custom algorithms were integrated into the cloud-native pipeline to extract gait, upper limb mobility, postural transitions, and daily activity measures. The resulting measures demonstrated excellent reliability and sensitivity, enabling the sponsor to identify superior biomarkers and inform future digital strategy. Digital measures showed a significant increase in monthly change over time relative to the standard patient-reported outcome (PRO).
• PD Progression: In partnership with a top-10 pharmaceutical company, Koneksa deployed its neuroscience toolkit to support digital biomarker validation in Parkinson's disease, processing 54 GB of accelerometry data (50,000 files from 100+ participants). The team successfully accommodated mid-study protocol amendments, reprocessing data with updated algorithms to ensure scientific rigor and consistency.

Demonstrated Value Across Projects

• Accelerated development timelines through earlier and more sensitive disease signal detection, with 10–20x faster delivery of extracted insights
• Digital progression measures proven more sensitive than traditional PROs in ALS tracking studies
• Data-driven protocol optimization enabling adaptive trial designs; simulated analyses comparing at-home versus in-clinic study designs showed that denser and more precise digital measures resulted in 68% fewer patients required per trial arm (Lavine et al., 2024)
• Regulatory-grade outputs that support confident submissions and strategic trial decisions

Koneksa's Advanced Modeling and Analysis Services are delivered through a cloud-native infrastructure designed for high-throughput processing, and the team works closely with sponsors whether the goal is validating an existing measure, developing novel digital biomarkers, or extracting new insights from complex datasets. The service supports regulatory submissions and is backed by published research and patents in the digital biomarker space.