The Promise and the Challenge of Technology-Facilitated Methods for Assessing Behavioral and Cognitive Markers of Risk for Suicide among U.S. Army National Guard Personnel

Adaptation of an Emotional Stroop Test for Screening of Suicidal Ideation in Portugal

Cognitive instruments, especially those with emotional components, may be useful to address the limitations of self-report scales commonly used to assess suicidal ideation. The aim of this study was to develop an emotional Stroop test for screening suicidal ideation in Portugal. The project was developed in five phases using different samples for each phase. The first two phases were focused on the formulation of the potential words that would compose the slides. For this purpose, five biology teachers (neutral slide) and five mental health professionals (positive and negative slides) were invited to help choose the words that were most representative for each slide. The third phase validated the words defined in the previous phase. In this phase, 300 university students participated (M_age = 21.66; SD = 3.67; 68% female). They rated the words on a Likert scale in terms of their frequency of use, familiarity, level of understanding, and degree of image evocation. In the fourth phase, the researchers developed the complete version of the test, which consists of three slides with neutral, positive, and negative emotional stimuli, consecutively. Finally, in the fifth phase, we validated the final version of the test through a comparative study between a clinical group and a non-clinical group, each one composed by 50 participants (M_age = 32; SD = 9.70; 55% female). Results indicated that the clinical group demonstrated significantly higher scores for depression and suicidal ideation and lower scores for the three Stroop tasks. Words related to negative emotions were strongly correlated with suicidal ideation. Finally, the three Stroop slides explained 74.1% of the variance in suicidal ideation. These findings suggest that this test can be a viable complementary measure in the psychological assessment of suicide ideation, and intervention in the field of suicide prevention in Portugal.

Examining spoken words and acoustic features of therapy sessions to understand family caregivers’ anxiety and quality of life

BACKGROUND

Speech and language cues are considered significant data sources that can reveal insights into one's behavior and well-being. The goal of this study is to evaluate how different machine learning (ML) classifiers trained both on the spoken word and acoustic features during live conversations between family caregivers and a therapist, correlate to anxiety and quality of life (QoL) as assessed by validated instruments.

METHODS

The dataset comprised of 124 audio-recorded and professionally transcribed discussions between family caregivers of hospice patients and a therapist, of challenges they faced in their caregiving role, and standardized assessments of self-reported QoL and anxiety. We custom-built and trained an Automated Speech Recognition (ASR) system on older adult voices and created a logistic regression-based classifier that incorporated audio-based features. The classification process automated the QoL scoring and display of the score in real time, replacing hand-coding for self-reported assessments with a machine learning identified classifier.

FINDINGS

Of the 124 audio files and their transcripts, 87 of these transcripts (70%) were selected to serve as the training set, holding the remaining 30% of the data for evaluation. For anxiety, the results of adding the dimension of sound and an automated speech-to-text transcription outperformed the prior classifier trained only on human-rendered transcriptions. Specifically, precision improved from 86% to 92%, accuracy from 81% to 89%, and recall from 78% to 88%.

INTERPRETATION

Classifiers can be developed through ML techniques which can indicate improvements in QoL measures with a reasonable degree of accuracy. Examining the content, sound of the voice and context of the conversation provides insights into additional factors affecting anxiety and QoL that could be addressed in tailored therapy and the design of conversational agents serving as therapy chatbots.

Implicit Cognition Tests for the Assessment of Suicide Risk: a Systematic Review

PURPOSE OF REVIEW

Suicide risk assessment is a challenge in clinical practice. Implicit measures may present with advantages with respect to explicit methods, and therefore may be useful for the assessment of suicide risk. We conducted a systematic review of 2 databases (PubMed and EMBASE) about implicit tests that measure suicide risk to explore their validity and reliability.

RECENT FINDINGS

Initial research revealed 321 articles. After the selection process, 31 articles were included in the review. The most death-related implicit cognition test used was the Death/Suicide Implicit association test (D/S IAT), followed by the Suicide Stroop Task. The Suicide Affect Misattribution Procedure (S-AMP) and the Death version of the Implicit Relational Assessment Procedure (D-IRAP) were also used. We found that the measures reviewed were generally valid for the assessment of past and future suicidal thoughts and behaviors, with statistically significant results regarding retrospective and prospective associations.

Spoken words as biomarkers: using machine learning to gain insight into communication as a predictor of anxiety

OBJECTIVE

The goal of this study was to explore whether features of recorded and transcribed audio communication data extracted by machine learning algorithms can be used to train a classifier for anxiety.

MATERIALS AND METHODS

We used a secondary data set generated by a clinical trial examining problem-solving therapy for hospice caregivers consisting of 140 transcripts of multiple, sequential conversations between an interviewer and a family caregiver along with standardized assessments of anxiety prior to each session; 98 of these transcripts (70%) served as the training set, holding the remaining 30% of the data for evaluation.

RESULTS

A classifier for anxiety was developed relying on language-based features. An 86% precision, 78% recall, 81% accuracy, and 84% specificity were achieved with the use of the trained classifiers. High anxiety inflections were found among recently bereaved caregivers and were usually connected to issues related to transitioning out of the caregiving role. This analysis highlighted the impact of lowering anxiety by increasing reciprocity between interviewers and caregivers.

CONCLUSION

Verbal communication can provide a platform for machine learning tools to highlight and predict behavioral health indicators and trends.

Everyday couples' communication research: Overcoming methodological barriers with technology

Relationship behaviors contribute to compromised health or resilience. Everyday communication between intimate partners represents the vast majority of their interactions. When intimate partners take on new roles as patients and caregivers, everyday communication takes on a new and important role in managing both the transition and the adaptation to the change in health status. However, everyday communication and its relation to health has been little studied, likely due to barriers in collecting and processing this kind of data. The goal of this paper is to describe deterrents to capturing naturalistic, day-in-the-life communication data and share how technological advances have helped surmount them. We provide examples from a current study and describe how we anticipate technology will further change research capabilities.