Clustering of critically ill patients using an individualized learning approach enables dose optimization of mobilization in the ICU

Abstract

Background While early mobilization is commonly implemented in intensive care unit treatment guidelines to improve functional outcome, the characterization of the optimal individual dosage (frequency, level or duration) remains unclear. The aim of this study was to demonstrate that artificial intelligence-based clustering of a large ICU cohort can provide individualized mobilization recommendations that have a positive impact on the likelihood of being discharged home. Methods This study is an analysis of a prospective observational database of two interdisciplinary intensive care units in Munich, Germany. Dosage of mobilization is determined by sessions per day, mean duration, early mobilization as well as average and maximum level achieved. A k-means cluster analysis was conducted including collected parameters at ICU admission to generate clinically definable clusters. Results Between April 2017 and May 2019, 948 patients were included. Four different clusters were identified, comprising “Young Trauma,” “Severely ill & Frail,” “Old non-frail” and “Middle-aged” patients. Early mobilization (< 72 h) was the most important factor to be discharged home in “Young Trauma” patients (ORadj 10.0 [2.8 to 44.0], p < 0.001). In the cluster of “Middle-aged” patients, the likelihood to be discharged home increased with each mobilization level, to a maximum 24-fold increased likelihood for ambulating (ORadj 24.0 [7.4 to 86.1], p < 0.001). The likelihood increased significantly when standing or ambulating was achieved in the older, non-frail cluster (ORadj 4.7 [1.2 to 23.2], p = 0.035 and ORadj 8.1 [1.8 to 45.8], p = 0.010). Conclusions An artificial intelligence-based learning approach was able to divide a heterogeneous critical care cohort into four clusters, which differed significantly in their clinical characteristics and in their mobilization parameters. Depending on the cluster, different mobilization strategies supported the likelihood of being discharged home enabling an individualized and resource-optimized mobilization approach. Trial Registration: Clinical Trials NCT03666286, retrospectively registered 04 September 2018.

Responsiveness of Critically Ill Adults With Multimorbidity to Rehabilitation Interventions: A Patient-Level Meta-Analysis Using Individual Pooled Data From Four Randomized Trials*

“…The novelty of this study is that it provides new insights into a more homogeneous subgroup of patients with two or more comorbidities who, as identified from a comprehensive transparent attempt to integrate trial data from an international team of researchers, derived significant benefits from the rehabilitation intervention delivered within the trials. Our results are consistent with those of Fuest et al (33) who identified clusters of patient characteristics using artificial intelligence that responded differently to mobilization intervention. Similarly, Schaller et al (34) reported significant outcomes of mobilization in a more homogenous surgical patient population.…”

Reliability and Effectiveness of the Japanese Version of the Mobilization Quantification Score

“…However, in many cases, it is difficult to perform PA assessment with a PA meter or a metabolic meter at an early stage in critically ill patients due to the effects of sedation and mechanical ventilation. In the cluster analysis of Fuest et al, the mobilization dose was determined by sessions per day, mean duration, early mobilization, and average and maximum level achieved, but it is difficult to use all these evaluations on the bedside [ 22 ]. The MQS has several benefits over other scales, including the combination of duration and intensity in a single score.…”

From bedside to recovery: exercise therapy for prevention of post-intensive care syndrome

“…PICS-related outcomes, healthcare resource usage, economic and social impacts) are being examined. Investigating the heterogenous effect of ET among different cohorts of ICU patients is also considered a high priority to optimise the delivered intervention to match patients’ individual backgrounds, presentations, and comorbidities [ 24 , 25 ]. Recently, an artificial intelligence-based learning approach demonstrated the heterogenous effect of ET in different cohorts of ICU patients, suggesting the importance of an individualised and resource-optimised approach [ 24 ].…”

“…Investigating the heterogenous effect of ET among different cohorts of ICU patients is also considered a high priority to optimise the delivered intervention to match patients' individual backgrounds, presentations, and comorbidities [24,25]. Recently, an artificial intelligence-based learning approach demonstrated the heterogenous effect of ET in different cohorts of ICU patients, suggesting the importance of an individualised and resource-optimised approach [24]. This approach will be also helpful to address the paradox that increased ET dose in ICU have no effects in the general ICU cohort or may even have deleterious effect [26,27].…”