Can adverse childhood experiences predict chronic health conditions? Development of trauma-informed, explainable machine learning models.

Introduction: Decades of research have established the association between adverse childhood experiences (ACEs) and adult onset of chronic diseases, influenced by health behaviors and social determinants of health (SDoH). Machine Learning (ML) is a powerful tool for computing these complex associations and accurately predicting chronic health conditions. Methods: Using the 2021 Behavioral Risk Factor Surveillance Survey, we developed several ML models-random forest, logistic regression, support vector machine, Naïve Bayes, and K-Nearest Neighbor-over data from a sample of 52,268 respondents. We predicted 13 chronic health conditions based on ACE history, health behaviors, SDoH, and demographics. We further assessed each variable's importance in outcome prediction for model interpretability. We evaluated model performance via the Area Under the Curve (AUC) score. Results: With the inclusion of data on ACEs, our models outperformed or demonstrated similar accuracies to existing models in the literature that used SDoH to predict health outcomes. The most accurate models predicted diabetes, pulmonary diseases, and heart attacks. The random forest model was the most effective for diabetes (AUC = 0.784) and heart attacks (AUC = 0.732), and the logistic regression model most accurately predicted pulmonary diseases (AUC = 0.753). The strongest predictors across models were age, ever monitored blood sugar or blood pressure, count of the monitoring behaviors for blood sugar or blood pressure, BMI, time of last cholesterol check, employment status, income, count of vaccines received, health insurance status, and total ACEs. A cumulative measure of ACEs was a stronger predictor than individual ACEs. Discussion: Our models can provide an interpretable, trauma-informed framework to identify and intervene with at-risk individuals early to prevent chronic health conditions and address their inequalities in the U.S.

Reverse intermetamorphosis--a rare misidentification phenomenon.

The authors present a case including two variants of delusional misidentification: Fregoli variant and intermetamorphosis. The present case has two interesting aspects: a) intermetamorphosis occurred in the patient himself, rather than in another person; b) the intermetamorphosis was only psychological and not physical.

[Overlap between schizophrenia and affective disorders--a family study].

The distinction between schizophrenia and affective disorders is fundamental. However, overlapping has been described in most studies of schizophrenia and of affective disorders. We studied 20 families, each with at least 1 parent and 1 child with a diagnosis of schizophrenia or of affective disorder. In half the families there were 2 diagnoses. In most of these families the children had a more severe disorder than the sick parent, onset was earlier, more were diagnosed as schizophrenic, hospitalizations were longer, and social functioning was worse. The results emphasize current problems in psychiatric diagnosis, which still lacks a pathophysiological etiologic basis.

An unusual effect of ECT on drug-induced parkinsonism and tardive dystonia.

A patient with schizoaffective disorder and anticholinergic refractory neuroleptic-induced parkinsonism manifested a marked increase of parkinsonian symptoms and dystonia after ECT. This is the first report in the literature of such an unusual reaction of parkinsonian and dystonic symptoms to ECT.

Possible precipitants of psychiatric hospitalization in patients with major depression: results from the Jerusalem Collaborative Depression Project.

In spite of substantial advances in the treatment of major depression by pharmacotherapy and other means, a significant number of depressed patients require hospitalization. In the context of the Jerusalem Collaborative Depression Project, possible precipitants of psychiatric hospitalization were sought in a cohort of patients (n = 107) who were admitted to hospitals in the Jerusalem area during a 14-month period because of a depressive episode. The patients fulfilled DSM III-R criteria for major depression, single or recurrent; bipolar 1 disorder, depressed or mixed; bipolar 2, depressed. The cohort encompassed more than two thirds of potential subjects admitted during this period with the ICD-9 equivalents of the specified diagnoses (as reported to the Israel Ministry of Health National Psychiatric Case Register) and were similar to the entire potential population in terms of their diagnostic breakdown. The patients underwent extensive socio-demographic and clinical evaluation that included detailed documentation of treatment received prior to hospitalization. Notwithstanding the absence of a comparison group of depressed patients who were not hospitalized, a number of potential precipitants were identified. These included older age (55.2% > 60 years, 20.6% > 70 years), immigration to Israel during the preceding 5 years (34.7%), concomitant physical illness (60%) which was associated with moderate to severe disability in 41% and poor quality of antidepressant pharmacotherapy prior to hospitalisation (only 24.3% received an adequate trial of antidepressant medication). Further evaluation of these and other potential factors could facilitate targeting of patient groups at particular risk for hospitalization and reduce the need for it.

Increased prevalence of negative life events in subtypes of major depressive disorder.

The prevalence of negative life events is known to be increased among patients with depression. Little data exist on the specific subtypes of depression that are related to negative life events. Our study aimed to address this issue. We compare 115 patients with major depressive disorder (MDD) to 60 normal controls. MDD patients reported experiencing one (P = .0001) or two (P = .01) negative life events more frequently than controls. Patients reported marital, other personal problems, and medical events significantly more often than controls (P < .01). Patients did not report more positive life events, and did not attribute greater severity to their adversities than controls. Younger MDD patients experienced four (P = .01) negative life events significantly more often than older patients. Similarly, patients with mild-moderate depression, nonmelancholic depression, or first episode of depression (FDE), respectively, experienced three or four life events significantly more often than patients with severe, melancholic, or recurrent depression (RDE). Other patient and illness characteristics such as gender, early parental loss, family history of depression or other mental disorders, psychotic features, suicide attempts, and chronicity were not related to increased prevalence of negative life events. Our results support the hypothesis that a subset of patients with MDD is especially prone to suffer from a cluster of negative life events. This subgroup is at increased risk for relapse and poor prognosis. The implications of these results for further research and for treatment are discussed.

Environment and vulnerability to major psychiatric illness: a case control study of early parental loss in major depression, bipolar disorder and schizophrenia.

The current focus on identifying genes which predispose to psychiatric illness sharpens the need to identify environmental factors which interact with genetic predisposition and thus contribute to the multifactorial causation of these disorders. One such factor may be early parental loss (EPL). The putative relationship between early environmental stressors such as parental loss and psychopathology in adult life has intrigued psychiatrists for most of this century. We report a case control study in which rates of EPL, due to parental death or permanent separation before the age of 17 years were evaluated in patients with major depression (MD), bipolar disorder (BPD) and schizophrenia (SCZ), compared to individually matched, healthy control subjects (MD-Control, 79 pairs; BPD-Control, 79 pairs; SCZ-Control, 76 pairs). Loss of parent during childhood significantly increased the likelihood of developing MD during adult life (OR=3.8, P=0.001). The effect of loss due to permanent separation (P=0.008) was more striking than loss due to death, as was loss before the age of 9 years (OR=11.0, P=0.003) compared to later childhood and adolescence. The overall rate of EPL was also increased in BPD (OR=2.6, P=0.048) but there were no significant findings in any of the subcategories of loss. A significantly increased rate of EPL was observed in schizophrenia patients (OR=3.8, P=0.01), particularly before the age of 9 years (OR=4.3, P=0.01). Comparison of psychosocial, medical and clinical characteristics of subjects with and without a history of EPL, within the larger patient groups from which the matched samples were drawn (MD, n=136; BPD, n=107; SCZ, n=160), yielded few significant findings. Among the controls (n=170), however, subjects who had experienced EPL, reported lower incomes, had been divorced more frequently, were more likely to be living alone, were more likely to smoke or have smoked cigarettes and reported more physical illness (P=0.03-0.001). Long term neurobiological consequences of early environmental stressors such as maternal deprivation have been extensively studied in many animal species. Recently, enduring changes in hypothalamic-pituitary-adrenal axis function, including corticotrophin releasing factor gene expression, have received particular attention. Analogous processes may be implicated in the effect of EPL on human vulnerability to psychopathology, via alterations in responsiveness to stress. Genetic predisposition may influence the degree of susceptibility of the individual to the effects of early environmental stress and may also determine the psychopathological entity to which the individual is rendered vulnerable as a consequence of the stress.