The use of machine learning techniques in trauma-related disorders: a systematic review.

Establishing the diagnosis of trauma-related disorders such as Acute Stress Disorder (ASD) and Posttraumatic Stress Disorder (PTSD) have always been a challenge in clinical practice and in academic research, due to clinical and biological heterogeneity. Machine learning (ML) techniques can be applied to improve classification of disorders, to predict outcomes or to determine person-specific treatment selection. We aim to review the existing literature on the use of machine learning techniques in the assessment of subjects with ASD or PTSD. We systematically searched PubMed, Embase and Web of Science for articles published in any language up to May 2019. We found 806 abstracts and included 49 studies in our review. Most of the included studies used multiple levels of biological data to predict risk factors or to identify early symptoms related to PTSD. Other studies used ML classification techniques to distinguish individuals with ASD or PTSD from other psychiatric disorder or from trauma-exposed and healthy controls. We also found studies that attempted to define outcome profiles using clustering techniques and studies that assessed the relationship among symptoms using network analysis. Finally, we proposed a quality assessment in this review, evaluating methodological and technical features on machine learning studies. We concluded that etiologic and clinical heterogeneity of ASD/PTSD patients is suitable to machine learning techniques and a major challenge for the future is to use it in clinical practice for the benefit of patients in an individual level.

Depletion of adult neurogenesis using the chemotherapy drug temozolomide in mice induces behavioural and biological changes relevant to depression.

Numerous studies have examined links between postnatal neurogenesis and depression using a range of experimental methods to deplete neurogenesis. The antimitotic drug temozolomide (TMZ) has previously been used successfully as an experimental tool in animals to deplete adult neurogenesis and is used regularly on human patients as a standard chemotherapy for brain cancer. In this study, we wanted to evaluate whether TMZ as a model for chemotherapy treatment could affect parameters related to depression in an animal model. Prevalence rates of depression in patients is thought to be highly underdiagnosed, with some studies reporting rates as high as 90%. Results from this study in mice, treated with a regimen of TMZ similar to humans, exhibited behavioural and biochemical changes that have relevance to the development of depression. In particular, behavioural results demonstrated robust deficits in processing novelty and a significant increase in the corticosterone response. Quantification of neurogenesis using a novel sectioning method, which clearly evaluates dorsal and ventral neurogenesis separately, showed a significant correlation between the level of ventral neurogenesis and the corticosterone response. Depression is a complex disorder with discoveries regarding its neurobiology and how it relates to behaviour being only in their infancy. The findings presented in this study demonstrate that chemotherapy-induced decreases in neurogenesis results in previously unreported behavioural and biochemical consequences. These results, we argue, are indicative of a biological mechanism, which may contribute to the development of depression in patients being treated with chemotherapy and is separate from the mental distress resulting from a cancer diagnosis.

A randomized, double-blind pilot study of dexmedetomidine versus midazolam for intensive care unit sedation: patient recall of their experiences and short-term psychological outcomes.

INTRODUCTION: Sedation with dexmedetomidine may facilitate ventilator liberation and limit the occurrence of delirium. No trial has assessed patient recall or the development of psychological outcomes after dexmedetomidine sedation. This pilot study evaluated whether transitioning benzodiazepine sedation to dexmedetomidine alters patient recall and the incidence of anxiety, depression, or acute stress disorder (ASD). METHODS: This investigation was a randomized, double-blind, single-center study. Existing continuous benzodiazepine sedation was converted to dexmedetomidine or midazolam when patients qualified for daily awakenings. Sedation was titrated to achieve Riker sedation agitation scores of 3 to 4. The intensive care unit (ICU) Stressful Experiences Questionnaire, hospital anxiety and depression scale, and the impact of event scale-revised were administered before hospital discharge to assess recall, anxiety, depression, and manifestations of ASD. RESULTS: A total of 11 patients received dexmedetomidine, and 12 patients received midazolam. Median dosing was 0.61 µg/kg/h for 3.5 days for dexmedetomidine and 3.7 mg/h for 3 days for midazolam. Attainment of goal sedation and analgesia was similar; however, more dexmedetomidine patients experienced agitation and pain. The median duration of mechanical ventilation from study drug initiation to extubation was 3.4 days in dexmedetomidine patients and 2.9 days in midazolam patients. Dexmedetomidine patients remembered 18.5 experiences compared with 8.5 in midazolam patients (P = .015). Rates of anxiety and depression were similar. In all, 5 (62.5%) dexmedetomidine patients and 1 (12.5%) midazolam patient manifested ASD (P = .063), and 1 dexmedetomidine patient and 5 midazolam patients developed new-onset delirium (P = .07). Hypotension occurred in 10 (90.9%) dexmedotomidine patients and 6 (50%) midazolam patients (P = .069). CONCLUSIONS: Transitioning benzodiazepine sedation to dexmedetomidine when patients qualify for daily awakenings may reduce the development of delirium and facilitate remembrance of ICU experiences but may lead to manifestations of ASD. Monitoring hypotension is required for both the sedatives. Additional comparative studies focusing on the long-term impact of ICU recall and psychological outcomes are needed.