An evaluation of time series summary statistics as features for clinical prediction tasks

Abstract

Background: Clinical prediction tasks such as patient mortality, length of hospital stay, and disease diagnosis are highly important in critical care research. The existing studies for clinical prediction mainly used simple summary statistics to summarize information from physiological time series. However, this lack of statistics leads to a lack of information. In addition, using only maximum and minimum statistics to indicate patient features fails to provide an adequate explanation. Few studies have evaluated which summary statistics best represent physiological time series. Methods: In this paper, we summarize 14 statistics describing the characteristics of physiological time series, including the central tendency, dispersion tendency, and distribution shape. Then, we evaluate the use of summary statistics of physiological time series as features for three clinical prediction tasks. To find the combinations of statistics that yield the best performances under different tasks, we use a cross-validation-based genetic algorithm to approximate the optimal statistical combination. Results: By experiments using the EHRs of 6,927 patients, we obtained prediction results based on both single statistics and commonly used combinations of statistics under three clinical prediction tasks. Based on the results of an embedded cross-validation genetic algorithm, we obtained 25 optimal sets of statistical combinations and then tested their prediction results. By comparing the performances of prediction with single statistics and commonly used combinations of statistics with quantitative analyses of the optimal statistical combinations, we found that some statistics play central roles in patient representation and different prediction tasks have certain commonalities. Conclusion: Through an in-depth analysis of the results, we found many practical reference points that can provide guidance for subsequent related research. Statistics that indicate dispersion tendency, such as min, max, and range, are more suitable for length of stay prediction tasks, and they also provide information for short-term mortality prediction. Mean and quantiles that reflect the central tendency of physiological time series are more suitable for mortality and disease prediction. Skewness and kurtosis perform poorly when used separately for prediction but can be used as supplementary statistics to improve the overall prediction effect.

Predicting the Mortality of ICU Patients by Topic Model with Machine-Learning Techniques

“…To determine the variables to be used, we referenced relevant studies [ 7 , 41 , 42 , 44 ] and manually selected 16 quantitative variables based on their clinical importance in the domain from admission, chartevents, labevents, and output events data tables in the MIMIC-III dataset. The variables were Glasgow Coma Scale, heart rate, systolic blood pressure, temperature, FiO 2 , urine output, PO 2 , blood urea nitrogen, white blood cell count, potassium level, sodium level, serum bicarbonate level, bilirubin, admission type, patient’s sex, and age.…”

“…Using EHR data to make clinical predictions (e.g., predicting patients’ mortality, hospital stay, disease diagnoses, and onset time) is crucial in intensive care research. In other words, identifying how to effectively predict ICU patient mortality by using EHR data allows medical personnel to accurately assess the patients’ mortality risks, detect high-risk groups early, and implement interventions promptly, improving patient prognoses and enhancing care planning and resource allocation [ 7 ].…”

High-Resolution Digital Phenotypes from Consumer Wearables Enhance Prediction of Cardiometabolic Risk Markers

“…As many of these conditions are amenable to early intervention via dietary changes or increased physical activity, there is also interest in using wearables to promote selfawareness and regulation [20] and to enhance screening [11]. Second, wearable-derived measures, such as circadian measures, sleep patterns/quality [11,21], step counts [4], wearable-derived resting heart rate [4,8,10,21,22] and heart rate variability (HRV) [23][24][25][26][27] have been found to correlate with outcomes in cardiometabolic disease. As such, there is increasing recognition in the clinical community to incorporate wearable-derived measures into practical cardiometabolic disease management [6,28].…”

A Deep Learning Post-Discharge Mortality Prediction Method Considering Diagnosis Information for ICU Patients

“…Nowadays, massive volumes of data recorded in electronic health records (EHRs) also supported researchers to design models and algorithms for in-hospital mortality prediction which aim at improving the predicting performance and facilitating the clinical decision making. Outperformance of mortality prediction methods based on machine learning models have been shown by many works [6][7][8][9][10][11][12][13]. Some of them show better prediction performance of machine learning models than traditional scoring systems [7,8] and some of them develop various models and machine learning algorithms for mortality prediction [6,[9][10][11][12][13].…”

“…Outperformance of mortality prediction methods based on machine learning models have been shown by many works [6][7][8][9][10][11][12][13]. Some of them show better prediction performance of machine learning models than traditional scoring systems [7,8] and some of them develop various models and machine learning algorithms for mortality prediction [6,[9][10][11][12][13]. Further more, the deep learning models achieve particularly satisfactory performance in ICU mortality prediction tasks due to their strong ability of capturing non-linear patterns hidden in data [14].…”