Automatic Patient Functionality Assessment from Multimodal Data using Deep Learning Techniques - Development and Feasibility Evaluation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149092" target="_blank" >RIV/00216305:26230/23:PU149092 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S221478292300057X" target="_blank" >https://www.sciencedirect.com/science/article/pii/S221478292300057X</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.invent.2023.100657" target="_blank" >10.1016/j.invent.2023.100657</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Automatic Patient Functionality Assessment from Multimodal Data using Deep Learning Techniques - Development and Feasibility Evaluation

Popis výsledku v původním jazyce

Wearable devices and mobile sensors enable the real-time collection of an abundant source of physiological and behavioural data unobtrusively. Unlike traditional in-person evaluation or ecological momentary assessment (EMA) questionnaire-based approaches, these data sources open many possibilities in remote patient monitoring. However, defining robust models is challenging due to the data's noisy and frequently missing observations. This work proposes an attention-based Long Short-Term Memory (LSTM) neural network-based pipeline for predicting mobility impairment based on WHODAS 2.0 evaluation from such digital biomarkers. Furthermore, we addressed the missing observation problem by utilising hidden Markov models and the possibility of including information from unlabelled samples via transfer learning. We validated our approach using two wearable/mobile sensor data sets collected in the wild and socio-demographic information about the patients. Our results showed that in the WHODAS 2.0 mobility impairment prediction task, the proposed pipeline outperformed a prior baseline while additionally providing interpretability with attention heatmaps. Moreover, using a much smaller cohort via task transfer learning, the same model could learn to predict generalised anxiety severity accurately based on GAD-7 scores.

Název v anglickém jazyce

Automatic Patient Functionality Assessment from Multimodal Data using Deep Learning Techniques - Development and Feasibility Evaluation

Popis výsledku anglicky

Wearable devices and mobile sensors enable the real-time collection of an abundant source of physiological and behavioural data unobtrusively. Unlike traditional in-person evaluation or ecological momentary assessment (EMA) questionnaire-based approaches, these data sources open many possibilities in remote patient monitoring. However, defining robust models is challenging due to the data's noisy and frequently missing observations. This work proposes an attention-based Long Short-Term Memory (LSTM) neural network-based pipeline for predicting mobility impairment based on WHODAS 2.0 evaluation from such digital biomarkers. Furthermore, we addressed the missing observation problem by utilising hidden Markov models and the possibility of including information from unlabelled samples via transfer learning. We validated our approach using two wearable/mobile sensor data sets collected in the wild and socio-demographic information about the patients. Our results showed that in the WHODAS 2.0 mobility impairment prediction task, the proposed pipeline outperformed a prior baseline while additionally providing interpretability with attention heatmaps. Moreover, using a much smaller cohort via task transfer learning, the same model could learn to predict generalised anxiety severity accurately based on GAD-7 scores.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Internet Interventions

ISSN

2214-7829

e-ISSN

—

Svazek periodika

33

Číslo periodika v rámci svazku

100657

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

9

Strana od-do

1-9

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85166982926