Machine learning-based prediction of restless legs syndrome using digital phenotypes from wearables and smartphone data

May 10, 2025Scientific reports

Using wearable and smartphone data to predict restless legs syndrome with machine learning

AI simplified

Circadian Biology on OpenScience ↗PubMed ↗DOI ↗OA ↗

Abstract

The model combining wearable device and application data achieved an AUC of 0.86 for predicting (RLS) symptom groups.

Machine learning models were developed to distinguish between non-RLS and RLS symptom groups based on integrated lifestyle and biometric data.
The random forest model demonstrated the highest performance in predicting RLS symptoms.
When using only wearable device data, the model for RLS symptoms achieved an accuracy of 0.70.
Combining wearable and application data improved accuracy to 0.76 for RLS symptoms.
For severe RLS symptom prediction, the XGB model achieved an accuracy of 0.84 using only wearable device data.

AI simplified

(RLS) is a relatively common neurosensory disorder that causes an irresistible urge for leg movement. RLS causes sleep disturbances and reduced quality of life, but accurate diagnosis remains challenging owing to the reliance on subjective reporting. This study aimed to propose a predictive machine learning model based on digital phenotypes for RLS diagnosis. Self-reported lifestyle data were integrated via a smartphone application with objective biometric data from wearable devices to obtain 85 features processed based on circadian rhythms. Prediction models used these features to distinguish between the non-RLS (International Restless Legs Study Group Severity Rating Scale [IRLS] score ≤ 10) and RLS symptom groups (10 < IRLS ≤ 20) and between the non-RLS and severe RLS symptom groups (IRLS > 20). The RF model showed the highest performance in predicting the RLS symptom group and XGB model in the severe RLS symptom group. For the RLS symptom group, when using only wearable device data, the AUC, accuracy, precision, recall, and F1 scores were 0.78, 0.70, 0.66, 0.84, and 0.74, respectively, while these scores combining wearable device and application data were 0.86, 0.76, 0.68, 1.00, and 0.81, respectively. For the severe RLS symptom group, when using only wearable device data, XGB achieved AUC, accuracy, precision, recall, and F1 scores of 0.66, 0.84, 0.89, 0.93, and 0.91, respectively, while these scores combining wearable device and application data were 0.70, 0.80, 0.88, 0.90, and 0.89, respectively. Diverse digital phenotypes clinically associated with RLS were processed based on circadian rhythms to demonstrate the potential of for RLS prediction. Thus, our study establishes early detection and personalized management of RLS.Trial Registration: Clinical Research Information Service (CRIS) KCT0009175 (Registration data: Feb-15-2024) ( https://cris.nih.go.kr/cris/search/detailSearch.do?search_lang=E&focus=reset_12&search_page=M&pageSize=10&page=undefined&seq=26133&status=5&seq_group=26133 ).

Key numbers

0.86

AUC for symptom prediction

Achieved by the RF model with wearable and application data.

0.70

AUC for severe symptom prediction

Utilizing both wearable device and application data.

119 of 338

Participants with insomnia

Insomnia group included in the overall participant count.

Full Text

We can’t show the full text here under this license. Use the link below to read it at the source.

View full text (PDF) ↗View full text (HTML) ↗

Machine learning-based prediction of restless legs syndrome using digital phenotypes from wearables and smartphone data

Abstract

Key numbers

Full Text

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief

Abstract

Key numbers

Full Text

Related papers

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief