A transformer model for cause-specific hazard prediction.

BACKGROUD: Modelling discrete-time cause-specific hazards in the presence of competing events and non-proportional hazards is a challenging task in many domains. Survival analysis in longitudinal cohorts often requires such models; notably when the data is gathered at discrete points in time and the predicted events display complex dynamics. Current models often rely on strong assumptions of proportional hazards, that is rarely verified in practice; or do not handle sequential data in a meaningful way. This study proposes a Transformer architecture for the prediction of cause-specific hazards in discrete-time competing risks. Contrary to Multilayer perceptrons that were already used for this task (DeepHit), the Transformer architecture is especially suited for handling complex relationships in sequential data, having displayed state-of-the-art performance in numerous tasks with few underlying assumptions on the task at hand. RESULTS: Using synthetic datasets of 2000-50,000 patients, we showed that our Transformer model surpassed the CoxPH, PyDTS, and DeepHit models for the prediction of cause-specific hazard, especially when the proportional assumption did not hold. The error along simulated time outlined the ability of our model to anticipate the evolution of cause-specific hazards at later time steps where few events are observed. It was also superior to current models for prediction of dementia and other psychiatric conditions in the English longitudinal study of ageing cohort using the integrated brier score and the time-dependent concordance index. We also displayed the explainability of our model's prediction using the integrated gradients method. CONCLUSIONS: Our model provided state-of-the-art prediction of cause-specific hazards, without adopting prior parametric assumptions on the hazard rates. It outperformed other models in non-proportional hazards settings for both the synthetic dataset and the longitudinal cohort study. We also observed that basic models such as CoxPH were more suited to extremely simple settings than deep learning models. Our model is therefore especially suited for survival analysis on longitudinal cohorts with complex dynamics of the covariate-to-outcome relationship, which are common in clinical practice. The integrated gradients provided the importance scores of input variables, which indicated variables guiding the model in its prediction. This model is ready to be utilized for time-to-event prediction in longitudinal cohorts.

A descriptive study of routine laboratory testing in intensive care unit in nearly 140,000 patient stays.

To describe the relationship between the use of laboratory tests and changes in laboratory parameters in ICU patients is necessary to help optimize routine laboratory testing. A retrospective, descriptive study was conducted on the large eICU-Collaborative Research Database. The relationship between the use of routine laboratory tests (chemistry and blood counts) and changes in ten common laboratory parameters was studied. Factors associated with laboratory tests were identified in a multivariate regression analysis using generalized estimating equation Poisson models. The study included 138,734 patient stays, with an ICU mortality of 8.97%. For all parameters, the proportion of patients with at least one test decreased from day 0 to day 1 and then gradually increased until the end of the ICU stay. Paradoxically, the results of almost all tests moved toward normal values, and the daily variation in the results of almost all tests decreased over time. The presence of an arterial catheter or teaching hospitals were independently associated with an increase in the number of laboratory tests performed. The paradox of routine laboratory testing should be further explored by assessing the factors that drive the decision to perform routine laboratory testing in ICU and the impact of such testing on patient.

Effect of Body Mass Index on the Clinical Outcomes of Adult Patients Treated With Venoarterial ECMO for Cardiogenic Shock.

OBJECTIVE: Current guidelines consider obesity to be a relative contraindication to venoarterial extracorporeal membrane oxygenation (VA-ECMO) for refractory cardiogenic shock. The authors investigated the effect of body mass index (BMI) on clinical outcomes in patients treated with VA-ECMO for cardiogenic shock. DESIGN: This was a retrospective and observational study. SETTING: University hospital. PARTICIPANTS: The study comprised 150 adult patients who underwent VA-ECMO for cardiogenic shock. MEASUREMENTS AND MAIN RESULTS: The primary outcome was intensive care unit (ICU) mortality. Of the 150 included patients, 10 were underweight (BMI < 18.5 kg/m²), 62 were normal weight (BMI = 18.5-24.9 kg/m²), 34 were overweight (BMI = 25.0-29.9 kg/m²), 34 were obese class I (BMI = 30.0-34.9 kg/m²), and 10 were obese class II (BMI = 35.0-39.9 kg/m²). All-cause ICU mortality was 62% (underweight, 70%; normal weight, 53%; overweight, 65%; class I obese, 71%; class II obese, 70%). After multivariate logistic regression, BMI was not associated with ICU mortality (adjusted odds ratio [aOR] 0.99 [0.92-1.07], p = 0.8). Analysis by BMI category showed unfavorable mortality trends in underweight patients (aOR 3.58 [0.82-19.6], p = 0.11) and class I obese patients (aOR 2.39 [0.95-6.38], p = 0.07). No statistically significant differences were found among BMI categories in the incidences of complications. CONCLUSION: The results suggested that BMI alone should not be considered an exclusion criterion for VA-ECMO. The unfavorable trend observed in underweight patients could be the result of malnutrition.