Exploring the associations between auditory hallucinations and psychopathological experiences in 10,933 patient narratives: moving beyond diagnostic categories and surveys.

BACKGROUND: Previous research suggests that auditory hallucinations are prevalent within both the clinical and general populations. Yet, we know little about how these phenomena are associated with other psychopathology symptoms and experiences. The current study aids investigations towards preventing, predicting and more effectively responding to such distressing occurrences. There have been substantial efforts in the literature to propose models of auditory hallucination and attempts to verify them. However, many of these studies used survey methods that restrict the person's responses to a set of pre-defined criteria or experiences and do not allow exploration of potential important other symptoms beyond them. This is the first study to explore the correlates of auditory hallucination using a qualitative dataset consisting of unrestricted responses of patients about their lived experiences with mental illness. METHOD: The study used a dataset consisting of 10,933 narratives from patients diagnosed with mental illnesses. For analysis, the study used correlation on the text-based data. This approach is an alternative to the knowledge-based approach where experts manually read the narratives and infer the rules and relationships from the dataset. RESULT: This study found at least 8 correlates of auditory hallucination (small correlation coefficients), with the unusual ones being "pain." The study also found that auditory hallucinations were independent of obsessive thoughts and compulsive behaviours, and dissociation, in contrast with the literature. CONCLUSION: This study presents an innovative approach to explore the possible associations between symptoms without the restrictions of (or outside the confines of) traditional diagnostic categories. The study exemplified this by finding the correlates of auditory hallucination. However, any other symptom or experience of interest can be studied similarly. Potential future directions of these findings are discussed in the context of mental healthcare screening and treatment.

What can we learn about the psychiatric diagnostic categories by analysing patients' lived experiences with Machine-Learning?

BACKGROUND: To deliver appropriate mental healthcare interventions and support, it is imperative to be able to distinguish one person from the other. The current classification of mental illness (e.g., DSM) is unable to do that well, indicating the problem of diagnostic heterogeneity between disorders (i.e., the disorder categories have many common symptoms). As a result, the same person might be diagnosed with two different disorders by two independent clinicians. We argue that this problem might have resulted because these disorders were created by a group of humans (APA taskforce members) who relied on more intuition and consensus than data. Literature suggests that human-led decisions are prone to biases, group-thinking, and other factors (such as financial conflict of interest) that can enormously influence creating diagnostic and treatment guidelines. Therefore, in this study, we inquire that if we prevent such human intervention (and thereby their associated biases) and use Artificial Intelligence (A.I.) to form those disorder structures from the data (patient-reported symptoms) directly, then can we come up with homogenous clusters or categories (representing disorders/syndromes: a group of co-occurring symptoms) that are adequately distinguishable from each other for them to be clinically useful. Additionally, we inquired how these A.I.-created categories differ (or are similar) from human-created categories. Finally, to the best of our knowledge, this is the first study, that demonstrated how to use narrative qualitative data from patients with psychopathology and group their experiences using an A.I. Therefore, the current study also attempts to serve as a proof-of-concept. METHOD: We used secondary data scraped from online communities and consisting of 10,933 patients' narratives about their lived experiences. These patients were diagnosed with one or more DSM diagnoses for mental illness. Using Natural Language Processing techniques, we converted the text data into a numeric form. We then used an Unsupervised Machine Learning algorithm called K-Means Clustering to group/cluster the symptoms.  RESULTS: Using the data mining approach, the A.I. found four categories/clusters formed from the data. We presented ten symptoms or experiences under each cluster to demonstrate the practicality of application and understanding. We also identified the transdiagnostic factors and symptoms that were unique to each of these four clusters. We explored the extent of similarities between these clusters and studied the difference in data density in them. Finally, we reported the silhouette score of + 0.046, indicating that the clusters are poorly distinguishable from each other (i.e., they have high overlapping symptoms). DISCUSSION: We infer that whether humans attempt to categorise mental illnesses or an A.I., the result is that the categories of mental disorders will not be unique enough to be able to distinguish one service seeker from another. Therefore, the categorical approach of diagnosing mental disorders can be argued to fall short of its purpose. We need to search for a classification system beyond the categorical approaches even if there are secondary merits (such as ease of communication and black-and-white (binary) decision making). However, using our A.I. based data mining approach had several meritorious findings. For example, we found that some symptoms are more exclusive or unique to one cluster. In contrast, others are shared by most other clusters (i.e., identification of transdiagnostic experiences). Such differences are interesting objects of inquiry for future studies. For example, in clear contrast to the traditional diagnostic systems, while some experiences, such as auditory hallucinations, are present in all four clusters, others, such as trouble with eating, are exclusive to one cluster (representing a syndrome: a group of co-occurring symptoms). We argue that trans-diagnostic conditions (e.g., auditory hallucinations) might be prime targets for symptom-level interventions. For syndrome-level grouping and intervention, however, we argue that exclusive symptoms are the main targets. CONCLUSION: Categorical approach to mental disorders is not a way forward because the categories are not unique enough and have several shared symptoms. We argue that the same symptoms can be present in more than one syndrome, although dimensionally different. However, we need additional studies to test this hypothesis. Future directions and implications were discussed.

Measuring diagnostic heterogeneity using text-mining of the lived experiences of patients.

BACKGROUND: The diagnostic system is fundamental to any health discipline, including mental health, as it defines mental illness and helps inform possible treatment and prognosis. Thus, the procedure to estimate the reliability of such a system is of utmost importance. The current ways of measuring the reliability of the diagnostic system have limitations. In this study, we propose an alternative approach for verifying and measuring the reliability of the existing system. METHODS: We perform Jaccard's similarity index analysis between first person accounts of patients with the same disorder (in this case Major Depressive Disorder) and between those who received a diagnosis of a different disorder (in this case Bulimia Nervosa) to demonstrate that narratives, when suitably processed, are a rich source of data for this purpose. We then analyse 228 narratives of lived experiences from patients with mental disorders, using Python code script, to demonstrate that patients with the same diagnosis have very different illness experiences. RESULTS: The results demonstrate that narratives are a statistically viable data resource which can distinguish between patients who receive different diagnostic labels. However, the similarity coefficients between 99.98% of narrative pairs, including for those with similar diagnoses, are low (< 0.3), indicating diagnostic Heterogeneity. CONCLUSIONS: The current study proposes an alternative approach to measuring diagnostic Heterogeneity of the categorical taxonomic systems (e.g. the Diagnostic and Statistical Manual, DSM). In doing so, we demonstrate the high Heterogeneity and limited reliability of the existing system using patients' written narratives of their illness experiences as the only data source. Potential applications of these outputs are discussed in the context of healthcare management and mental health research.