Dataset Information

Physiological sleep measures predict time to 15-year mortality in community adults: Application of a novel machine learning framework.

ABSTRACT: Clarifying whether physiological sleep measures predict mortality could inform risk screening; however, such investigations should account for complex and potentially non-linear relationships among health risk factors. We aimed to establish the predictive utility of polysomnography (PSG)-assessed sleep measures for mortality using a novel permutation random forest (PRF) machine learning framework. Data collected from the years 1995 to present are from the Sleep Heart Health Study (SHHS; n = 5,734) and the Wisconsin Sleep Cohort Study (WSCS; n = 1,015), and include initial assessments of sleep and health, and up to 15 years of follow-up for all-cause mortality. We applied PRF models to quantify the predictive abilities of 24 measures grouped into five domains: PSG-assessed sleep (four measures), self-reported sleep (three), health (eight), health behaviours (four), and sociodemographic factors (five). A 10-fold repeated internal validation (WSCS and SHHS combined) and external validation (training in SHHS; testing in WSCS) were used to compute unbiased variable importance metrics and associated p values. We observed that health, sociodemographic factors, and PSG-assessed sleep domains predicted mortality using both external validation and repeated internal validation. The PSG-assessed sleep efficiency and the percentage of sleep time with oxygen saturation <90% were among the most predictive individual measures. Multivariable Cox regression also revealed the PSG-assessed sleep domain to be predictive, with very low sleep efficiency and high hypoxaemia conferring the highest risk. These findings, coupled with the emergence of new low-burden technologies for objectively assessing sleep and overnight oxygen saturation, suggest that consideration of physiological sleep measures may improve risk screening.

SUBMITTER: Wallace ML

PROVIDER: S-EPMC8591145 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Physiological sleep measures predict time to 15-year mortality in community adults: Application of a novel machine learning framework.

Wallace Meredith L ML Coleman Timothy S TS Mentch Lucas K LK Buysse Daniel J DJ Graves Jessica L JL Hagen Erika W EW Hall Martica H MH Stone Katie L KL Redline Susan S Peppard Paul E PE

Journal of sleep research 20210515 6

Clarifying whether physiological sleep measures predict mortality could inform risk screening; however, such investigations should account for complex and potentially non-linear relationships among health risk factors. We aimed to establish the predictive utility of polysomnography (PSG)-assessed sleep measures for mortality using a novel permutation random forest (PRF) machine learning framework. Data collected from the years 1995 to present are from the Sleep Heart Health Study (SHHS; n = 5,73 ...[more]

PMID: 33991144

Similar Datasets

Project description:BackgroundAccurate prognostic estimation for esophageal cancer (EC) patients plays an important role in the process of clinical decision-making. The objective of this study was to develop an effective model to predict the 5-year survival status of EC patients using machine learning (ML) algorithms.MethodsWe retrieved the information of patients diagnosed with EC between 2010 and 2015 from the Surveillance, Epidemiology, and End Results (SEER) Program, including 24 features. A total of 8 ML models were applied to the selected dataset to classify the EC patients in terms of 5-year survival status, including 3 newly developed gradient boosting models (GBM), XGBoost, CatBoost, and LightGBM, 2 commonly used tree-based models, gradient boosting decision trees (GBDT) and random forest (RF), and 3 other ML models, artificial neural networks (ANN), naive Bayes (NB), and support vector machines (SVM). A 5-fold cross-validation was used in model performance measurement.ResultsAfter excluding records with missing data, the final study population comprised 10,588 patients. Feature selection was conducted based on the χ2 test, however, the experiment results showed that the complete dataset provided better prediction of outcomes than the dataset with removal of non-significant features. Among the 8 models, XGBoost had the best performance [area under the receiver operating characteristic (ROC) curve (AUC): 0.852 for XGBoost, 0.849 for CatBoost, 0.850 for LightGBM, 0.846 for GBDT, 0.838 for RF, 0.844 for ANN, 0.833 for NB, and 0.789 for SVM]. The accuracy and logistic loss of XGBoost were 0.875 and 0.301, respectively, which were also the best performances. In the XGBoost model, the SHapley Additive exPlanations (SHAP) value was calculated and the result indicated that the four features: reason no cancer-directed surgery, Surg Prim Site, age, and stage group had the greatest impact on predicting the outcomes.ConclusionsThe XGBoost model and the complete dataset can be used to construct an accurate prognostic model for patients diagnosed with EC which may be applicable in clinical practice in the future.

Project description:ObjectiveEarly prediction of long-term outcomes in patients with sepsis-induced cardiorenal syndrome (CRS) remains a great challenge in clinical practice. Herein, we aimed to construct a nomogram and machine learning model for predicting the 1-year mortality risk in patients with sepsis-induced CRS.MethodsThis retrospective study enrolled 340 patients diagnosed with sepsis-induced CRS in Shanghai Tongji Hospital between January 2015 and May 2019, as a discovery cohort. Two predictive models, the nomogram and machine learning model, were used to predict 1-year mortality. The prognostic variables used to develop the nomogram were identified based on a forward stepwise binary logistic regression, and the predictive ability of the nomogram was evaluated by the areas under the receiver operating characteristic curve (AUC) and the calibration curve. Meanwhile, machine learning (ML) techniques, such as support vector machine, random forest (RF), and gradient boosted decision tree, were assessed mainly by accuracy and AUC. Feature ranking analysis was performed using the ML algorithm. Both nomogram and ML models were externally validated by an independent cohort of 103 patients diagnosed with sepsis-induced CRS between June 2019 and December 2020.ResultsAge, sequential sepsis-related organ failure score (SOFA), serum myoglobin (MYO), vasopressor use, and mechanical ventilation were identified as independent risk factors for 1-year mortality in the nomogram predictive model. In the discovery cohort, the nomogram yielded higher AUC for predicting mortality than did the SOFA score (0.855 [95% CI: 0.815-0.895] vs. 0.756 [95% CI: 0.705-0.808]). For ML, the model developed by RF showed the highest accuracy (0.765) and AUC (0.854). In feature ranking analysis, factors such as age, MYO, SOFA score, vasopressor use, and baseline serum creatinine were identified as important features affecting 1-year prognosis. Moreover, the nomogram and RF model both performed well in external validation, with an AUC of 0.877 and 0.863, respectively.ConclusionOur nomogram and ML models showed that age, SOFA score, serum MYO levels, and the use of vasopressors during hospitalization were the main factors influencing the risk of long-term mortality. Our models may serve as useful tools for assessing long-term prognosis in patients with sepsis-induced CRS.

Project description:BackgroundThe mortality of metabolic-obesity phenotypes has been thoroughly studied, but it is not known if or how the association between mortality and body mass index (BMI), waist circumference or a body shape index (ABSI) differ in strata of cardiometabolic health status.MethodsWe linked data on 12,815 men and women aged 36-79 years from the SAMINOR 1 Survey with mortality data from the Norwegian Cause of Death Registry. We defined metabolically healthy and unhealthy as having zero and ≥ 1, respectively, of the following: MetS, pre-existing diabetes or cardiovascular disease (CVD), or prescribed drugs for high blood pressure, hyperglycaemia or dyslipidaemia. We defined general and abdominal obesity as BMI ≥ 30 kg/m2 and waist circumference ≥ 88 cm (women) or 102 cm (men), respectively, and cross-classified these categories with metabolic status to create metabolically healthy non-obese and obese (MHNO and MHO) and metabolically unhealthy non-obese and obese (MUNO and MUO) phenotypes. We used Cox regression to estimate the hazard ratio (HR) for all-cause and CVD mortality for 1) the four phenotypes and 2) BMI, waist circumference and ABSI fitted with restricted cubic splines. We adjusted for age and lifestyle, and tested for interactions with sex and metabolic status (only continuous measures).ResultsThe MHO phenotype was present in 7.8% of women and 5.8% of men. During a median follow-up of 15.3/15.2 years, 596/938 women/men had died, respectively. The MUNO and MUO groups had higher mortality than the MHNO group. Sex and phenotypes interacted with respect to CVD mortality: relative to the MHNO group, the MHO group had an adjusted HR (95% confidence interval) for CVD mortality of 1.05 (0.38-2.88) in women and 2.92 (1.71-5.01) in men. We found curvilinear associations between BMI/waist circumference and all-cause mortality irrespective of metabolic status. Corresponding relationships with CVD mortality were linear and the slope differed by sex and metabolic status. ABSI was linearly and positively associated with all-cause and CVD mortality in men.ConclusionThe relationships between BMI, waist circumference or ABSI and mortality differed by sex, metabolic status and cause of death. Poor metabolic health substantially increases mortality regardless of obesity status.

Dataset Information

Physiological sleep measures predict time to 15-year mortality in community adults: Application of a novel machine learning framework.

Publications

Physiological sleep measures predict time to 15-year mortality in community adults: Application of a novel machine learning framework.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets