Sleep Quality Prediction From Wearable Data Using Deep Learning

Risperidone Provides Better Improvement of Sleep Disturbances Than Haloperidol Therapy in Schizophrenia Patients With Cannabis-Positive Urinalysis

A high percentage of persons with Schizophrenia also uses Cannabis and this may potentially alter the therapeutic benefits of the antipsychotic medications prescribed. The aim of this study was to assess the impact of Cannabis usage on antipsychotic therapy of sleep disturbances in schizophrenia subjects. Male subjects, ≥18 years, admitted to the University Hospital of the West Indies psychiatric ward between October 2015 and October 2016, and diagnosed with schizophrenia were recruited for the study. Following written informed consent to the study, subjects were prescribed either risperidone monotherapy or haloperidol monotherapy orally for 14 days and classified as Cannabis users (CU) or non-users (non-CU), with presence/absence of Cannabis metabolite in urine samples. After 1 week of admission, subjects wore the Actiwatch-2 device, to record sleep data for 7 consecutive nights. Inferential statistical analysis involved non-parametric tests, expressed as median and inter-quartile ranges (IQR), with p<0.05 considered statistically significant. Fifty subjects were assessed, with a median (IQR) age of 28 (14) years. Majority (30; 60%) were CU, displaying longer sleep latency (SL) than non-CU when receiving haloperidol; but equivalent SL when receiving risperidone. In comparison to non-CU, the CU also displayed longer time in bed, but shorter durations asleep, awoke more frequently during the nights and for longer durations, whether receiving haloperidol or risperidone. This resulted in lower sleep efficiency for the CU (<85%) compared to the non-CU (≥85%). Over the study period, sleep efficiency was significantly improved for non-CU receiving either risperidone (p = 0.032) or haloperidol (p = 0.010); but was only significantly improved with risperidone for the CU (p = 0.045). It is apparent that the presence of Cannabis may be impacting the therapeutic benefits of antipsychotic drugs on sleep. In schizophrenia subjects with concomitant Cannabis use, risperidone is more beneficial than haloperidol in improving sleep efficiency.

Predicting the hearing outcome in sudden sensorineural hearing loss via machine learning models

OBJECTIVE

Sudden sensorineural hearing loss (SSHL) is a multifactorial disorder with high heterogeneity, thus the outcomes vary widely. This study aimed to develop predictive models based on four machine learning methods for SSHL, identifying the best performer for clinical application.

DESIGN

Single-centre retrospective study.

SETTING

Chinese People's liberation army (PLA) hospital, Beijing, China.

PARTICIPANTS

A total of 1220 in-patient SSHL patients were enrolled between June 2008 and December 2015.

MAIN OUTCOME MEASURES

An advanced deep learning technique, deep belief network (DBN), together with the conventional logistic regression (LR), support vector machine (SVM) and multilayer perceptron (MLP) were developed to predict the dichotomised hearing outcome of SSHL by inputting six feature collections derived from 149 potential predictors. Accuracy, precision, recall, F-score and the area under the receiver operator characteristic curves (ROC-AUC) were exploited to compare the prediction performance of different models.

RESULTS

Overall the best predictive ability was provided by the DBN model when tested in the raw data set with 149 variables, achieving an accuracy of 77.58% and AUC of 0.84. Nevertheless, DBN yielded inferior performance after feature pruning. In contrast, the LR, SVM and MLP models demonstrated opposite trend as the greatest individual prediction powers were obtained when included merely three variables, with the ROC-AUC ranging from 0.79 to 0.81, and then decreased with the increasing size of input features combinations.

CONCLUSIONS

With the input of enough features, DBN can be a robust prediction tool for SSHL. But LR is more practical for early prediction in routine clinical application using three readily available variables, that is time elapse between symptom onset and study entry, initial hearing level and audiogram.

A universal deep learning approach for modeling the flow of patients under different severities

BACKGROUND AND OBJECTIVE

The Accident and Emergency Department (A&ED) is the frontline for providing emergency care in hospitals. Unfortunately, relative A&ED resources have failed to keep up with continuously increasing demand in recent years, which leads to overcrowding in A&ED. Knowing the fluctuation of patient arrival volume in advance is a significant premise to relieve this pressure. Based on this motivation, the objective of this study is to explore an integrated framework with high accuracy for predicting A&ED patient flow under different triage levels, by combining a novel feature selection process with deep neural networks.

METHODS

Administrative data is collected from an actual A&ED and categorized into five groups based on different triage levels. A genetic algorithm (GA)-based feature selection algorithm is improved and implemented as a pre-processing step for this time-series prediction problem, in order to explore key features affecting patient flow. In our improved GA, a fitness-based crossover is proposed to maintain the joint information of multiple features during iterative process, instead of traditional point-based crossover. Deep neural networks (DNN) is employed as the prediction model to utilize their universal adaptability and high flexibility. In the model-training process, the learning algorithm is well-configured based on a parallel stochastic gradient descent algorithm. Two effective regularization strategies are integrated in one DNN framework to avoid overfitting. All introduced hyper-parameters are optimized efficiently by grid-search in one pass.

RESULTS

As for feature selection, our improved GA-based feature selection algorithm has outperformed a typical GA and four state-of-the-art feature selection algorithms (mRMR, SAFS, VIFR, and CFR). As for the prediction accuracy of proposed integrated framework, compared with other frequently used statistical models (GLM, seasonal-ARIMA, ARIMAX, and ANN) and modern machine models (SVM-RBF, SVM-linear, RF, and R-LASSO), the proposed integrated "DNN-I-GA" framework achieves higher prediction accuracy on both MAPE and RMSE metrics in pairwise comparisons.

CONCLUSIONS

The contribution of our study is two-fold. Theoretically, the traditional GA-based feature selection process is improved to have less hyper-parameters and higher efficiency, and the joint information of multiple features is maintained by fitness-based crossover operator. The universal property of DNN is further enhanced by merging different regularization strategies. Practically, features selected by our improved GA can be used to acquire an underlying relationship between patient flows and input features. Predictive values are significant indicators of patients' demand and can be used by A&ED managers to make resource planning and allocation. High accuracy achieved by the present framework in different cases enhances the reliability of downstream decision makings.