2026-10-14T06:49:56Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34000724 2026-09-25T18:00:12Z category_7 category_734 category_931 category_106 portal_5 item_type_3 month_year_09_2026

<p>Model performances.</p> Chao Zhu (385240) Xin Zhang (35492) Anneke van der Walt (293592) Bruce Taylor (4417426) Mastura Monif (7342067) Tomas Kalincik (105432) Jeanette Lechner-Scott (236173) Katherine Buzzard (13168900) Trevor Kilpatrick (127001) Michael Barnett (317282) Zhen Zhou (184390) Vilija Jokubaitis (126974) Melissa Gresle (220765) David Darby (219715) Deval Mehta (24656300) Zongyuan Ge (12272975) Helmut Butzkueven (126230) Daniel Merlo (3175392) Medicine Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy receiver operating characteristic integrating artificial intelligence integrated brier score including dynamic deephit help identify patients convolutional neural network 63 &# 8211 54 &# 8211 16 &# 8211 using summary measures using individual test r ], attention machine learning models clinical trial enrichment convert longitudinal reaction confirmed disability progression 746 rrms patients predict disability progression longitudinal cognitive reaction remitting multiple sclerosis based survival model disability progression multiple sclerosis g ], benchmark models based prediction assessed using predict time cognitive data cognitive assessment clinical variables clinical data serial reaction working memory three tasks september 2022 rrms ). psychomotor function potential applicability msbase registry median follow key features images using higher risk february 2016 dependent area cohort study b ]) <div><p>Serial cognitive assessment in multiple sclerosis can help identify patients at higher risk of disability progression, but high dimensionality of reaction-time data makes analysis challenging. We developed a method to convert longitudinal reaction-time data into images and applied deep survival modelling to predict disability progression in relapsing-remitting MS (RRMS). In this cohort study, clinical data were obtained from the MSBase registry and cognitive data from the MSReactor computerised cognitive battery between February 2016 and September 2022, with a median follow-up of 3.2 years. The serial reaction-time data from three tasks (psychomotor function [R], attention [G], and working memory [B]) were converted into multicolour images using RGB encoding. We extracted the key features from the images using a convolutional neural network and combined them with clinical variables in a Transformer-based survival model (MS-TranSurv) to predict time to confirmed disability progression. Discrimination, calibration, and accuracy were assessed using the C-index, integrated Brier score (iBS), and time-dependent area under the receiver operating characteristic (tAUROC). Performance was compared with other machine learning models, including Dynamic DeepHit, Recurrent Deep Survival Machines, a Cox proportional hazards model in traditional statistics using clinical variables only, and a version of MS-TransSurv using mean test values. A total of 746 RRMS patients were included. MS-TranSurv showed slightly higher discrimination compared with benchmark models, with a C-index of 0.61 (95% CI 0.54–0.68) and tAUROC of 0.74 (95% CI 0.63–0.85), as well as comparable calibration, with an iBS of 0.24 (95% CI 0.16–0.32). Using individual test-level data provided slightly better performance than using summary measures. Longitudinal cognitive reaction-time data can be used for survival-based prediction of disability progression in RRMS. This framework supports remote cognitive monitoring and may improve risk stratification and clinical trial enrichment, with potential applicability to other high-dimensional digital biomarkers.</p></div> 2026-09-25T18:00:01Z Dataset Dataset 10.1371/journal.pdig.0001722.t002 https://figshare.com/articles/dataset/_p_Model_performances_p_/34000724 CC BY 4.0