Identifying the presence and timing of discrete mood states prior to therapy

• Published in: Behaviour research and therapy 2020-05, Vol.128, p.103596-11, Article 103596
• Main Authors: Fisher, Aaron J., Bosley, Hannah G.
• Format: Article
• Language: English
• Subjects: Anhedonia; Anxiety; Anxiety disorders; Avoidance behavior; Depression; Emotional states; Hedonic response; Hopelessness; Idiographic analysis; Irritability; Latent profile analysis; Machine learning; Mood; Personalized treatment; Rumination; Time of day; Time series
• ISSN: 0005-7967; 1873-622X
• DOI: 10.1016/j.brat.2020.103596

The present study tested a novel, person-specific method for identifying discrete mood profiles from time-series data, and examined the degree to which these profiles could be predicted by lagged mood and anxiety variables and time-based variables, including trends (linear, quadratic, cubic), cycles (12-hr, 24-hr, and 7-day), day of the week, and time of day. We analyzed ambulatory data from 45 individuals with mood and anxiety disorders prior to therapy. Data were collected four-times-daily for at least 30 days. Latent profile analysis was applied person-by-person to discretize each individual's continuous multivariate time series of rumination, worry, fear, anger, irritability, anhedonia, hopelessness, depressed mood, and avoidance. That is, each time point was classified according to its unique blend of emotional states, and latent classes representing discrete mood profiles were identified for each participant. We found that the modal number of latent classes per person was three (mean = 3.04, median = 3), with a range of two to four classes. After splitting each individual's time series into random halves for training and testing, we used elastic net regularization to identify the temporal and lagged predictors of each mood profile's presence or absence in the training set. Prediction accuracy was evaluated in the testing set. Across 127 models, the average area under the curve was 0.77, with sensitivity of 0.81 and specificity of 0.75. Brier scores indicated an average prediction accuracy of 83%. •Discusses the importance of understanding time in psychopathology.•Demonstrates how to use latent profile analysis person by person (i.e. within person).•Discusses the meaning of within-person latent classes of mood & anxiety data.•Uses machine learning to recover the timing of latent class occurrence.•Discusses how latent classes of symptoms can be used to inform case conceptualization and personalize treatment.