Forecasting the onset of depression with limited baseline data only: A comparison of a person-specific and a multilevel modeling based exponentially weighted moving average approach.

The onset of depressive episodes is preceded by changes in mean levels of affective experiences, which can be detected using the exponentially weighted moving average procedure on experience sampling method (ESM) data. Applying the exponentially weighted moving average procedure requires sufficient baseline data from the person under study in healthy times, which is needed to calculate a control limit for monitoring incoming ESM data. It is, however, not trivial to obtain sufficient baseline data from a single person. We therefore investigate whether historical ESM data from healthy individuals can help establish an adequate control limit for the person under study via multilevel modeling. Specifically, we focus on the case in which there is very little baseline data available of the person under study (i.e., up to 7 days). This multilevel approach is compared with the traditional, person-specific approach, where estimates are obtained using the person's available baseline data. Predictive performance in terms of Matthews correlation coefficient did not differ much between the approaches; however, the multilevel approach was more sensitive at detecting mean changes. This implies that for low-cost and nonharmful interventions, the multilevel approach may prove particularly beneficial. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Monitoring emotional intensity and variability to forecast depression recurrence in real time in remitted adults.

OBJECTIVE: Recurrent depressive episodes are preceded by changing mean levels of repeatedly assessed emotions (e.g., feeling restless), which can be detected in real time using statistical process control (SPC). This study investigated whether monitoring changes in the standard deviation (SD) of emotions and negative thinking improves the early detection of recurrent depression. METHOD: Formerly depressed adults (N = 41) monitored their emotions five times a day for 4 consecutive months. During the study, 22 individuals experienced recurrent depression. We used SPC to detect warning signs (i.e., changing means and SDs) of four emotions (positive and negative affect with high or low arousal) and negative thinking. RESULTS: SD-based warning signs only preceded 23%-36% of recurrences, but almost never reflected a false alarm (0%-16%). Correspondingly, SD-based warnings had a high specificity (at the cost of sensitivity), while mean-based warnings had a higher sensitivity (but lower specificity). There was little overlap in mean- and SD-based warning signs. For the majority of emotions, monitoring for high SDs alongside monitoring changes in mean levels improved the detection of depression (p < .015) compared to when only monitoring for changing mean levels. CONCLUSIONS: Warning signs for depression manifest not only in changing mean levels of emotions and cognitions but also in increasing SDs. These warnings could eventually be used to detect not just who is at increased risk for depression but also when risk is rising. Further research is needed to evaluate the clinical utility of depression SPC. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Individual-specific change points in circadian rest-activity rhythm and sleep in individuals tapering their antidepressant medication: an actigraphy study.

Group-level studies showed associations between depressive symptoms and circadian rhythm elements, though whether these associations replicate at the within-person level remains unclear. We investigated whether changes in circadian rhythm elements (namely, rest-activity rhythm, physical activity, and sleep) occur close to depressive symptom transitions and whether there are differences in the amount and direction of circadian rhythm changes in individuals with and without transitions. We used 4 months of actigraphy data from 34 remitted individuals tapering antidepressants (20 with and 14 without depressive symptom transitions) to assess circadian rhythm variables. Within-person kernel change point analyses were used to detect change points (CPs) and their timing in circadian rhythm variables. In 69% of individuals experiencing transitions, CPs were detected near the time of the transition. No-transition participants had an average of 0.64 CPs per individual, which could not be attributed to other known events, compared to those with transitions, who averaged 1 CP per individual. The direction of change varied between individuals, although some variables showed clear patterns in one direction. Results supported the hypothesis that CPs in circadian rhythm occurred more frequently close to transitions in depression. However, a larger sample is needed to understand which circadian rhythm variables change for whom, and more single-subject research to untangle the meaning of the large individual differences.

Real-time detection of mean and variance changes in experience sampling data: A comparison of existing and novel statistical process control approaches.

Retrospective analyses of experience sampling (ESM) data have shown that changes in mean and variance levels may serve as early warning signs of an imminent depression. Detecting such early warning signs prospectively would pave the way for timely intervention and prevention. The exponentially weighted moving average (EWMA) procedure seems a promising method to scan ESM data for the presence of mean changes in real-time. Based on simulation and empirical studies, computing and monitoring day averages using EWMA works particularly well. We therefore expand this idea to the detection of variance changes and propose to use EWMA to prospectively scan for mean changes in day variability statistics (i.e., s 2 , s , ln( s )). When both mean and variance changes are of interest, the multivariate extension of EWMA (MEWMA) can be applied to both the day averages and a day statistic of variability. We evaluate these novel approaches to detecting variance changes by comparing them to EWMA-type procedures that have been specifically developed to detect a combination of mean and variance changes in the raw data: EWMA- S 2 , EWMA-ln( S 2 ), and EWMA- X ¯ - S 2 . We ran a simulation study to examine the performance of the two approaches in detecting mean, variance, or both types of changes. The results indicate that monitoring day statistics using (M)EWMA works well and outperforms EWMA- S 2 and EWMA-ln( S 2 ); the performance difference with EWMA- X ¯ - S 2 is smaller but notable. Based on the results, we provide recommendations on which statistic of variability to monitor based on the type of change (i.e., variance increase or decrease) one expects.

The Exponentially Weighted Moving Average Procedure for Detecting Changes in Intensive Longitudinal Data in Psychological Research in Real-Time: A Tutorial Showcasing Potential Applications.

Affect, behavior, and severity of psychopathological symptoms do not remain static throughout the life of an individual, but rather they change over time. Since the rise of the smartphone, longitudinal data can be obtained at higher frequencies than ever before, providing new opportunities for investigating these person-specific changes in real-time. Since 2019, researchers have started using the exponentially weighted moving average (EWMA) procedure, as a statistically sound method to reach this goal. Real-time, person-specific change detection could allow (a) researchers to adapt assessment intensity and strategy when a change occurs to obtain the most useful data at the most useful time and (b) clinicians to provide care to patients during periods in which this is most needed. The current paper provides a tutorial on how to use the EWMA procedure in psychology, as well as demonstrates its added value in a range of potential applications.

: An R Package for performing kernel change point detection on the running statistics of multivariate time series.

In many scientific disciplines, researchers are interested in discovering when complex systems such as stock markets, the weather or the human body display abrupt changes. Essentially, this often comes down to detecting whether a multivariate time series contains abrupt changes in one or more statistics, such as means, variances or pairwise correlations. To assist researchers in this endeavor, this paper presents the package for performing kernel change point (KCP) detection on user-selected running statistics of multivariate time series. The running statistics are extracted by sliding a window across the time series and computing the value of the statistic(s) of interest in each window. Next, the similarities of the running values are assessed using a Gaussian kernel, and change points that segment the time series into maximally homogeneous phases are located by minimizing a within-phase variance criterion. To decide on the number of change points, a combination of a permutation-based significance test and a grid search is provided. stands out among the variety of change point detection packages available in because it can be easily adapted to uncover changes in any user-selected statistic without imposing any distribution on the data. To exhibit the usefulness of the package, two empirical examples are provided pertaining to two types of physiological data.

Detecting mean changes in experience sampling data in real time: A comparison of univariate and multivariate statistical process control methods.

Detecting early warning signals of developing mood disorders in continuously collected affective experience sampling (ESM) data would pave the way for timely intervention and prevention of a mood disorder from occurring or to mitigate its severity. However, there is an urgent need for online statistical methods tailored to the specifics of ESM data. Statistical process control (SPC) procedures, originally developed for monitoring industrial processes, seem promising tools. However, affective ESM data violate major assumptions of the SPC procedures: The observations are not independent across time, often skewed distributed, and characterized by missingness. Therefore, evaluating SPC performance on simulated data with typical ESM features is a crucial step. In this article, we didactically introduce six univariate and multivariate SPC procedures: Shewhart, Hotelling's T², EWMA, MEWMA, CUSUM and MCUSUM. Their behavior is illustrated on publicly available affective ESM data of a patient that relapsed into depression. To deal with the missingness, autocorrelation, and skewness in these data, we compute and monitor the day averages rather than the individual measurement occasions. Moreover, we apply all procedures on simulated data with typical affective ESM features, and evaluate their performance at detecting small to moderate mean changes. The simulation results indicate that the (M)EWMA and (M)CUSUM procedures clearly outperform the Shewhart and Hotelling's T² procedures and support using day averages rather than the original data. Based on these results, we provide some recommendations for optimizing SPC performance when monitoring ESM data as well as a wide range of directions for future research. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

The Short-Term Psychological Impact of the COVID-19 Pandemic in Psychiatric Patients: Evidence for Differential Emotion and Symptom Trajectories in Belgium.

The spread of COVID-19 and the implementation of various containment strategies across the world have seriously disrupted people's everyday life, and it is especially uncertain what the psychological impact of this pandemic will be for vulnerable individuals, such as psychiatric (ex-)patients. Governments fear that this virus outbreak may prelude a major mental health crisis, and psychiatrists launch critical calls to flatten an upcoming mental ill-health surge. Here, we aim to add nuance to the idea that we are heading towards a mental health pandemic and that psychiatric populations will unavoidably (re)develop psychopathology. Despite being subjected to the same challenges posed by COVID-19, we argue that people with a history of psychiatric illness will psychologically deal with this adversity in different ways. To showcase the short-term differential impact of COVID-19 on patients' mental health, we present the day-to-day emotion and symptom trajectories of different psychiatric patients that took part in an experience sampling study before, during, and after the start of the first wave of the COVID-19 pandemic in March 2020 and associated lockdown measures in Belgium. Piecewise regression models show that not all patients' psychological well-being is affected to a similar degree. As such, we argue that emphasizing human resilience, also among the more vulnerable in society, may be opportune in these unsettling times.

The data representativeness criterion: Predicting the performance of supervised classification based on data set similarity.

In a broad range of fields it may be desirable to reuse a supervised classification algorithm and apply it to a new data set. However, generalization of such an algorithm and thus achieving a similar classification performance is only possible when the training data used to build the algorithm is similar to new unseen data one wishes to apply it to. It is often unknown in advance how an algorithm will perform on new unseen data, being a crucial reason for not deploying an algorithm at all. Therefore, tools are needed to measure the similarity of data sets. In this paper, we propose the Data Representativeness Criterion (DRC) to determine how representative a training data set is of a new unseen data set. We present a proof of principle, to see whether the DRC can quantify the similarity of data sets and whether the DRC relates to the performance of a supervised classification algorithm. We compared a number of magnetic resonance imaging (MRI) data sets, ranging from subtle to severe difference is acquisition parameters. Results indicate that, based on the similarity of data sets, the DRC is able to give an indication as to when the performance of a supervised classifier decreases. The strictness of the DRC can be set by the user, depending on what one considers to be an acceptable underperformance.

Touch-induced pupil size reflects stimulus intensity, not subjective pleasantness.

Interpersonal touch is known to influence human communication and emotion. An important system for interpersonal touch is the C-tactile (CT) system, which is activated by a soft stroke on hairy skin with a velocity of 1-10 cms-1. This system been proposed to play a unique role in hedonic valence and emotion of touch. For other sensory modalities, hedonic processing has been associated with pupil dilation. However, it is unclear whether pupil dilation can be modulated by hedonic touch. The current study investigated in two experiments how pupil size reacts to both affective and non-affective stroking. Pupil-size data were obtained to investigate differences between stroking conditions. In addition, an adjusted version of the Touch Perception Task (TPT) was used to assess subjective touch pleasantness ratings. In Experiment 1, affective (3 cms-1) and non-affective (0.3 and 30 cms-1) stroking was applied to the dorsal side of the right hand. Results revealed that stroking velocity had a significant effect on TPT-item scores, showing higher that affective touch was rated as more pleasant compared to non-affective touch, thereby replicating the previous studies. Results, however, revealed no specific pupil dilation for the 3 cms-1 condition; instead, a logarithmic relation was found between pupil-size dilation and stroking velocity. This relation was confirmed in a second experiment. Furthermore, the palm of the hand was used as a control site for tactile stimulation, for which similar findings were obtained as for the dorsal side of the hand. In addition, skin conductance recordings showed a pattern of response to different stroking velocities similar to pupil dilation. These results suggest that pupil-size dilation does respond to tactile input, but that this response is related to arousal caused by changes in stimulus intensity (e.g., stroking velocity) rather than specific C-tactile stimulation.