The importance of considering the h

The importance of considering the heterogeneity in the study population and the treatment effects has been emphasised in recent years [6]. As shown in the analysis of multiple sepsis registries and RCTs [5], clinical pheno-types were correlated with host-response patterns and clinical outcomes, and simulations suggested the pres-ence of heterogeneity in treatment effects across phe-notypes. Thus, such heterogeneity may at least partially explain the underlying mechanisms of RCTs that failed to reveal significant benefit of therapies in critical care [18, 19]. Indeed, patients who met the inclusion criteria for the SCARLET trial accounted for 20–30% of the patients with rhTM target phenotype, suggesting that further studies are needed to investigate the effects of rhTM for sepsis. Additionally, the process of identifying the tar-get population to be treated is important and should be discussed in future cost–benefit analyses of treatment strategies, even if a small proportion of patients can be treated effectively (as was the case in our study sample).Subgroup analyses have been widely used to address treatment effect heterogeneity despite its limitations [20]. In particular, conventional subgroup analyses assess one characteristic at a time, which may not reflect the previous study to address the heterogeneity in our study population. While it is still challenging to find the truephenotypes that are responsible for the heterogene-ity, we believe that our research process: (1) discover-ing the target phenotype, (2) implementing a model for predicting the phenotype, and (3) conducting studies for identifying the optimal target population or exploring underlying mechanisms—is an efficient way of conduct-ing future studies and advancing personalised medicine. For example, our findings support the findings from a post hoc analysis of the SCARLET trial that reported an association between higher baseline thrombin generation biomarker levels and the effect of rhTM [9], by demon-strating that a subtype consisting of a high-dimensional coagulation profile could be a potential target of rhTM.This study has several limitations. First, although we developed a model to predict the rhTM target pheno-type, it remains unclear whether the rhTM target phe-notype is the true target of rhTM therapy. Second, there may be diagnostic suspicion bias and unmeasured con-founding. Additionally, the number of missing variables for prediction may have limited our findings. Thus, our findings should be validated in randomised controlled trials. Third, because machine learning models are gener-ally difficult to interpret, our model itself does not pro-vide information on the underlying mechanisms. Finally, our data were obtained from Japanese patients, and the generalisability of the results to other populations may be limited.