Multichannel mixture models for time-series analysis and classification of engagement with multiple health services: An application to psychology and physiotherapy utilization patterns after traffic accidents
作者：
Highlights：
• We combined supervised and unsupervised algorithms to yield clinical insights.
• The utilization of physiotherapy and psychology was analyzed using compensation data.
• Multidimensional sequences were generated and time series clustering (MHMM) was applied.
• Combinations of hidden states and clusters were evaluated and optimized.
• Cluster membership was classified using gradient boosting machines.
• Models may be used to forecast and improve claimant care and recovery.
摘要
•We combined supervised and unsupervised algorithms to yield clinical insights.•The utilization of physiotherapy and psychology was analyzed using compensation data.•Multidimensional sequences were generated and time series clustering (MHMM) was applied.•Combinations of hidden states and clusters were evaluated and optimized.•Cluster membership was classified using gradient boosting machines.•Models may be used to forecast and improve claimant care and recovery.
论文关键词：Hidden Markov models,Artificial intelligence,Time-series analysis,Traffic accidents,Health service utilization,Claim Insurance Data
论文评审过程：Received 13 April 2020, Revised 2 October 2020, Accepted 23 November 2020, Available online 27 November 2020, Version of Record 14 December 2020.
论文官网地址：https://doi.org/10.1016/j.artmed.2020.101997
