Toward a Machine Learning Predictive-Oriented Approach to Complement Explanatory Modeling. An Application for Evaluating Psychopathological Traits Based on Affective Neurosciences and Phenomenology

Artificial Neural Networks for Short-Form Development of Psychometric Tests: A Study on Synthetic Populations Using Autoencoders

Short-form development is an important topic in psychometric research, which requires researchers to face methodological choices at different steps. The statistical techniques traditionally used for shortening tests, which belong to the so-called exploratory model, make assumptions not always verified in psychological data. This article proposes a machine learning-based autonomous procedure for short-form development that combines explanatory and predictive techniques in an integrative approach. The study investigates the item-selection performance of two autoencoders: a particular type of artificial neural network that is comparable to principal component analysis. The procedure is tested on artificial data simulated from a factor-based population and is compared with existent computational approaches to develop short forms. Autoencoders require mild assumptions on data characteristics and provide a method to predict long-form items' responses from the short form. Indeed, results show that they can help the researcher to develop a short form by automatically selecting a subset of items that better reconstruct the original item's responses and that preserve the internal structure of the long-form.

Machine learning algorithms distinguish discrete digital emotional fingerprints for web pages related to back pain

Back pain is the leading cause of disability worldwide. Its emergence relates not only to the musculoskeletal degeneration biological substrate but also to psychosocial factors; emotional components play a pivotal role. In modern society, people are significantly informed by the Internet; in turn, they contribute social validation to a "successful" digital information subset in a dynamic interplay. The Affective component of medical pages has not been previously investigated, a significant gap in knowledge since they represent a critical biopsychosocial feature. We tested the hypothesis that successful pages related to spine pathology embed a consistent emotional pattern, allowing discrimination from a control group. The pool of web pages related to spine or hip/knee pathology was automatically selected by relevance and popularity and submitted to automated sentiment analysis to generate emotional patterns. Machine Learning (ML) algorithms were trained to predict page original topics from patterns with binary classification. ML showed high discrimination accuracy; disgust emerged as a discriminating emotion. The findings suggest that the digital affective "successful content" (collective consciousness) integrates patients' biopsychosocial ecosystem, with potential implications for the emergence of chronic pain, and the endorsement of health-relevant specific behaviors. Awareness of such effects raises practical and ethical issues for health information providers.

Neurocognitive Artificial Neural Network Models Are Superior to Linear Models at Accounting for Dimensional Psychopathology

In recent years, there has been debate about the optimal conceptualisation of psychopathology. Structural models of psychopathology have been developed to counter issues, including comorbidity and poor diagnostic stability prevalent within the traditional nosological approach. Regardless of the conceptualisation of psychological dysfunction, deficits in neurocognitive abilities have been claimed to be an aetiological feature of psychopathology. Explorations of the association between neurocognition and psychopathology have typically taken a linear approach, overlooking the potential interactive dynamics of neurocognitive abilities. Previously, we proposed a multidimensional hypothesis, where within-person interactions between neurocognitive domains are fundamental to understanding the role of neurocognition within psychopathology. In this study, we used previously collected psychopathology data for 400 participants on psychopathological symptoms, substance use, and performance on eight neurocognitive tasks and compared the predictive accuracy of linear models to artificial neural network models. The artificial neural network models were significantly more accurate than the traditional linear models at predicting actual (a) lower-level and (b) high-level dimensional psychopathology. These results provide support for the multidimensional hypothesis: that the study of non-linear interactions and compensatory neurocognitive profiles are integral to understanding the functional associations between neurocognition and of psychopathology.

The Affective Neuroscience of Sexuality: Development of a LUST Scale

Background

In recent years, there have been many studies using the Affective Neuroscience Personality Scales (ANPS) to investigate individual differences in primary emotion traits. However, in contrast to other primary emotion traits proposed by Jaak Panksepp and colleagues, there is a considerable lack of research on the LUST (L) dimension – defined as an individual’s capacity to attain sexual desire and satisfaction – a circumstance mainly caused by its exclusion from the ANPS. Therefore, this study aims to take a first step toward the development of a standardized self-rate measurement for the L-disposition. For this purpose, two versions of the L-scales (L-12 and L-5) were developed and evaluated regarding reliability and aspects of validity.

Materials and Methods

After a pilot study (N = 204; female: 81%) with an initial 20-item pool item reductions were conducted. This led to the construction of a 12-item (L-12) version and a 5-item version (L-5), which were assessed in a second sample consisting of 371 German-speaking healthy adults (58.50% female) aged 18–69 years (M = 28; SD = 9.75). Aspects of external validity were assessed by investigation of correlations with the ANPS, psychiatric symptoms (Brief Symptom Inventory-18), attachment security (Adult Attachment Scales) and personality functioning (Operationalized Psychodynamic Diagnostics Structure Questionnaire). To evaluate structural validity, both L-scales were investigated via confirmatory factor analysis (CFA).

Results

Cronbach’s α indicated excellent internal consistency regarding L-12 (α = 0.90), while L-5 showed acceptable reliability (α = 0.82). CFA of a bifactor model of the L-12 indicated excellent model fit. Moreover, an excellent model fit was observed regarding a single factor model of L-5. For both scales small to moderate positive correlations were observed with SEEKING, PLAY, and secure attachment, while they exhibited small to moderate negative correlations with SADNESS, insecure attachment, lower personality functioning, and increased psychiatric symptom load.

Conclusion

Both newly developed scales exhibit satisfying psychometric properties, indicating high reliability, good structural validity and plausible correlations with external criteria. Hence, this study poses an important step toward the operationalization of the LUST concept. However, more research is needed in particular with respect to the scale’s external validity and its applicability in clinical populations.

Exploring the Question: "Does Empathy Work in the Same Way in Online and In-Person Therapeutic Settings?"

Providing remote psychotherapy using technology is a growing practice, especially since the outbreak of the COVID-19 pandemic. Even if in numerous studies video conferencing psychotherapy (VCP) was found to be clinically effective, some doubts continue to exist about how the psychotherapeutic alliance works in the online setting, and the characteristics of the empathic process are still poorly understood. This is an exploratory study aimed at analyzing the degree of empathy between the psychotherapist and client pair, and the degree of support perceived by the client who shall be referred to as the patient interchangeably in this study, comparing the sessions in person with those online, during the current pandemic, in order to discriminate the impact of empathy in the digital setting. The sample analyzed was composed of 23 patients with different severity of pathology engaged in online and in-person therapeutic sessions with five psychotherapists of different theoretical leanings. The scores of the support and empathy scale, obtained by both members of the psychotherapeutic couple in the two settings, were analyzed and compared. The test used belongs to an Italian adaptation of the Empathic Understanding (EU) of the Relationship Inventory. What emerged from comparing the scores was interesting: Unlike the psychotherapists, the patients perceived their therapists as significantly more empathic and supportive in the remote setting. These are rather important data, because the literature documents that client empathic perception measures represent a more accurate measure of the empathic relationship and, in general, can predict a good treatment outcome. Although these results need further investigation, they represent an important contribution in filling the scientific gap in the understanding of digital empathy. Also, this study provides new insights for future research on the characteristics and impact empathy has on the practice of remote psychotherapy.

The experience of living with a chronic disease in pediatrics from the mothers' narratives: The Clinical Interview on Parental Sense of Grip on the Disease

The Clinical Interview on the Sense of Grip on Chronic Disease has been administered to 68 mothers of children affected by Hereditary Angioedema (C1-Inh HAE), Type 1 Diabetes (T1D), Juvenile Rheumatoid Arthritis (JRA). The objectives are to detect general features of the experience of parenting children with chronic illness as well as the specificities of this experience related to the different conditions. Four Profiles of Sense of Grip were identified: Adempitive, Controlling, Reactive, Dynamic. The Sense of Grip Interview is an effective clinical tool for understanding the characteristics of the disease in daily life, which can help clinicians to encourage family adjustment to disease.