Predicting Early Warning Signs of Psychotic Relapse From Passive Sensing Data: An Approach Using Encoder-Decoder Neural Networks

Abstract

Background: Schizophrenia spectrum disorders (SSDs) are chronic conditions, but the severity of symptomatic experiences and functional impairments vacillate over the course of illness. Developing unobtrusive remote monitoring systems to detect early warning signs of impending symptomatic relapses would allow clinicians to intervene before the patient's condition worsens.

Objective: In this study, we aim to create the first models, exclusively using passive sensing data from a smartphone, to predict behavioral anomalies that could indicate early warning signs of a psychotic relapse.

Methods: Data used to train and test the models were collected during the CrossCheck study. Hourly features derived from smartphone passive sensing data were extracted from 60 patients with SSDs (42 nonrelapse and 18 relapse >1 time throughout the study) and used to train models and test performance. We trained 2 types of encoder-decoder neural network models and a clustering-based local outlier factor model to predict behavioral anomalies that occurred within the 30-day period before a participant's date of relapse (the near relapse period). Models were trained to recreate participant behavior on days of relative health (DRH, outside of the near relapse period), following which a threshold to the recreation error was applied to predict anomalies. The neural network model architecture and the percentage of relapse participant data used to train all models were varied.

Results: A total of 20,137 days of collected data were analyzed, with 726 days of data (0.037%) within any 30-day near relapse period. The best performing model used a fully connected neural network autoencoder architecture and achieved a median sensitivity of 0.25 (IQR 0.15-1.00) and specificity of 0.88 (IQR 0.14-0.96; a median 108% increase in behavioral anomalies near relapse). We conducted a post hoc analysis using the best performing model to identify behavioral features that had a medium-to-large effect (Cohen d>0.5) in distinguishing anomalies near relapse from DRH among 4 participants who relapsed multiple times throughout the study. Qualitative validation using clinical notes collected during the original CrossCheck study showed that the identified features from our analysis were presented to clinicians during relapse events.

Conclusions: Our proposed method predicted a higher rate of anomalies in patients with SSDs within the 30-day near relapse period and can be used to uncover individual-level behaviors that change before relapse. This approach will enable technologists and clinicians to build unobtrusive digital mental health tools that can predict incipient relapse in SSDs.

Keywords: artificial intelligence; deep learning; digital biomarkers; digital phenotyping; mHealth; machine learning; mental health; mobile health; mobile phone; passive sensing; psychotic disorders; schizophrenia; smartphone applications.

Figure 1

Encoder-decoder neural network architectures. (a) the architecture for the fully connected neural network autoencoder (FNN AD) model. (b) the architecture for the GRU sequence-to-sequence (GRU Seq2Seq) model.

Figure 2

Overall model results, the anomaly rate of the best performing model across the near relapse (NR30) period and in (a-c) split by the DRH used in model training. In (a-c), the bar heights describe the median value of the metric listed on the y-axis across study participants and the error bars show lower and upper quartile values (25% and 75% percentiles of the data). In (a) and (b), local outlier factor (LOF) models are not shown as they did not hold predictive power. (a) Sensitivity, or true positive rate, of the models and (b) specificity, or true negative rate. (c) Median number of DRH used to train each model from each study participant. (d) Average (blue line) and 95% CI (gray shading) anomaly rate across relapse participants beginning 35 days before relapse using the best performing model (fully connected neural network autoencoder, 80% of DRH in train, 40 hidden units). DRH: days of relative health.

Figure 3

The hourly features that had the greatest effect on differentiating identified anomalous days near relapse (NR30) from all DRH within the 4 multirelapse participants. We used the Cohen d to identify the 5 features that were the most differentiated. Each subfigure, (a-d), displays boxplots comparing the distribution of these features on anomalous days within each NR30 period compared with all DRH. The center line in the boxplot is the median value, the box limits are the IQR, and the whiskers are 1.5 x the IQR. Points outside of the whiskers are greater than or less than 1.5 x the IQR. A lower IQR signifies that the median result is more generalizable. For example, in (a), we identified anomalies within 2 NR30 periods, described in the figure as Near relapse 1 and Near relapse 2. The 2 left boxes on each plot show the distribution of the feature for anomalies detected within each of these 2 NR30 periods and the right box shows the distribution of this feature on all DRH outside of the 2 NR30 periods. NR30: 30-day near relapse period. DRH: days of relative health.

Figure 4

Example of an anomaly visualization and clinical intervention system. The dashed black lines in (a) each represent an hourly feature trajectory from the anomaly detection system, as identified on the y-axis, during a 30-day near relapse period (NR30). The gray line on each plot is the Mahalanobis distance, which can be interpreted as an anomaly score that increases as we are more likely to detect an anomaly. The 2 vertical thick black lines on each plot are detected anomalies. (b) Example of how this information could be utilized by a clinician or other individuals designated by the patient to intervene during symptom exacerbation. The system would be tuned to send alerts only when a patient is in crisis and not overburden the clinician and the healthcare system.