Presentation at the Artid workshop, U. Bristol, March 2024, on digital biomarkers for improved clinical trials and monitoring of complex diseases, including neurological & movement disorders.
2. The obligatory background &
disclaimer
Who am I?
â Once an immunologist
â Then a molecular evolutionist, modeller, bioinformatician,
epi-informatician, analyst, data scientist, âcomputer guyâ ...
â Now solve clinical & trial problems for big pharma using data,
stats & AIML
Nothing in this presentation represents projects or policy at GSK
There are no conïŹicts of interest
3. What is a digital biomarker?
The broad (and oft ignored) deïŹnition
Anything measured and recorded
digitally, even:
â Blood pressure
â Height
â Heart rate
â Online survey
â Phone apps ...
The narrow (and stereotypical) deïŹnition
Digital recording of complex patient
behaviour and physiology, followed by
processing to produce quantiïŹable
metrics or endpoints, perhaps via a
device or sensor carried by the patient:
â Using a wearable to track a
patientâs heart rate over time
â Videoing a patient walking and
modelling it to produce a quality
of locomotion
â Sound analysis of voice or a
cough, to detect obstruction
4. Example: Parkinson's Disease 1
Deng, K., Li, Y., Zhang, H. et al.
Heterogeneous digital biomarker
integration out-performs patient
self-reports in predicting Parkinsonâs
disease. Commun Biol 5, 58 (2022).
https://doi.org/10.1038/s42003-022-03
002-x
5. Example: Parkinson's Disease 2
Interpretable Video-Based Tracking and
Quantification of Parkinsonism Clinical Motor
States
Daniel Deng, Jill L. Ostrem, Vy Nguyen, Daniel
D. Cummins, Julia Sun, Anupam Pathak, Simon
Little, Reza Abbasi-Asl
medRxiv 2023.11.04.23298083; doi:
https://doi.org/10.1101/2023.11.04.23298083
6. Why use digital biomarkers?
â Fidelity: avoids transcription errors
â Memory: not reliant upon patient recall
â Consistency: across sites, investigators, geographies
â Authenticity: measure in a real-world context, away from
clinical visits
â Patient-centricity
â Temporality: measures across time, perhaps to assess
âaverageâ behaviour or look for rare events
â Safety: monitoring patients for AEs
â Simplicity: distil complex behaviour and physiology to
something simpler and measurable
7. Why not use digital biomarkers
â Does it actually work for the patients
â Some patients like going to the clinic
â Also additional medical support
â Hardware & infrastructure & support
â Privacy
â Standardization
â Abstract, intangible measures
â Machine learning magic
8. Validity
Analytical
â Does it take good
measurements?
â Does it measure something
robustly and reproducibly?
â Can it cope with patchy or
imperfect data?
â Do small changes in signal or
source only result in
Clinical
â Does this measure mean
something?
â Does a change in the digital
measure relate to a change in
disease state?
â A form of experimenters
regress?
9. Summary
â Digital biomarkers are any persistent digital
measurement of patients
â Such biomarkers can be used reduce complex behaviours
(e.g. movement) to simpler and more quantiïŹable
endpoints
â But to do this we need hardware solutions and good data
analytics