Predictive biosignature of major depressive disorder derived from physiological measurements of outpatients using machine learning.

Major Depressive Disorder (MDD) has heterogeneous manifestations, leading to difficulties in predicting the evolution of the disease and in patient's follow-up. We aimed to develop a machine learning algorithm that identifies a biosignature to provide a clinical score of depressive symptoms using individual physiological data. We performed a prospective, multicenter clinical trial where outpatients diagnosed with MDD were enrolled and wore a passive monitoring device constantly for 6 months. A total of 101 physiological measures related to physical activity, heart rate, heart rate variability, breathing rate, and sleep were acquired. For each patient, the algorithm was trained on daily physiological features over the first 3 months as well as corresponding standardized clinical evaluations performed at baseline and months 1, 2 and 3. The ability of the algorithm to predict the patient's clinical state was tested using the data from the remaining 3 months. The algorithm was composed of 3 interconnected steps: label detrending, feature selection, and a regression predicting the detrended labels from the selected features. Across our cohort, the algorithm predicted the daily mood status with 86% accuracy, outperforming the baseline prediction using MADRS alone. These findings suggest the existence of a predictive biosignature of depressive symptoms with at least 62 physiological features involved for each patient. Predicting clinical states through an objective biosignature could lead to a new categorization of MDD phenotypes.

An ecological approach to clinically assess nightmares in military service members with severe PTSD.

BACKGROUND: Trauma-related nightmares (TRNs) are distressing events which contribute to insomnia severity, chronicity and treatment resistance of PTSD. Therefore, recording TRNs is a crucial technical challenge in order to understand their physiopathological patterns and their impact on sleep. However, TRNs are difficult to record during a single night in a sleep laboratory, which, moreover, is likely to be considered by patients as a protective sleep environment that is therefore not representative of home sleep conditions. METHOD: In the present study, we investigate if objective sleep measures acquired at-home using two ambulatory devices is of clinical value by correlating with PTSD patients' complaints about sleep and nightmares. A secondary objective is to relate awakenings associated with TRNs to sleep stages and to provide new insights into the use of electrodermal activity (EDA) as a potential physiological marker of TRNs. Sixty veterans and active-duty service members were assessed by questionnaires and recorded for 5 consecutive nights in their homes. RESULTS: Our approach firstly identified positive correlations between subjective and objective sleep parameters (total sleep time, sleep-onset latency and TRNs frequency). We also developed a method of synchronization between the two ambulatory devices that allowed us to match 200 TRNs (reported by event marker push button) with sleep stages corresponding to 91 nights and 37 patients. Most awakenings associated with TRNs occurred during NREM sleep (65.5% versus 34.5% during REM sleep). Our results also reveal significant differences in the frequency of EDA peaks 10 min before the reported events, with a lower frequency in REM (13.7 peaks) than in NREM (24.8 peaks) awakenings associated with TRNs. This EDA peaks frequency in REM sleep is not statistically different from that in REM sleep preceding awakenings that are not associated with TRNs. CONCLUSION: The development of wearable devices to collect physiological parameters is of interest in clinical practice to improve our knowledge of sleep and trauma-related nightmares in patients with PTSD.

[Treating mentally wounded patients within the French armed forces]. / Soigner les blessés psychiques au sein des armées françaises.

The French army has put in place a doctrine aimed at treating mentally wounded soldiers. A real treatment pathway comprising different specialised medical staff, places and time frames supports the soldier from the theatre of operations to France.

Multidisciplinary approach of organic catatonia in children and adolescents may improve treatment decision making.

Catatonia is an infrequent but severe condition in young people. Organic diseases may be associated and need to be investigated though no specific recommendations and guidelines are available. We extensively reviewed the literature of all the cases of organic catatonia in children and adolescents from January 1969 to June 2007. We screened socio-demographic characteristics, organic diagnosis, clinical characteristics and treatment. We found 38 cases of children and adolescents with catatonia due to an organic condition. The catatonic syndrome occurred in 21 (57%) females and 16 (43%) males. The mean age of patients was 14.5 years (+/-3.39) [range=7-18 years], and three died from their condition. The organic conditions included infectious diseases (N=10), neurological conditions (N=10), toxic induced states (N=12) and genetic conditions including inborn errors of metabolism (N=6). The onset was dominantly acute, and the clinical presentation most frequently stuporous. Although benzodiazepines were recommended as primary symptomatic treatment, they were rarely prescribed. In several cases, therapeutic approach was related to organic cause (e.g., plasma exchange in lupus erythematosus; copper chelators in Wilson's disease). Based on this review and on our own experience of catatonia in youth, we proposed a consensual and multidisciplinary diagnostic strategy to help practitioners to identify underlying organic diseases.

Severe Sympathomimetic Toxidrome in a French Soldier: How Caffeine Overdose Can Lead to Severe Consequences.

We report the case of a French soldier, 29-yr-old, hospitalized in intensive care unit at Begin Military Hospital for the management of a sympathomimetic syndrome associated with severe metabolic disorders. Diagnosis of voluntary caffeine overdose was made. The evolution was favorable after metabolic disorders correction, without the need for dialysis. Caffeine is a molecule free of serious adverse effects when consumed at low doses. However, when consumed at high doses, it can become toxic and lead to death. Caffeine consumption has increased in recent years and especially in French Army. This toxicity remains unknown by a large part of population. We must be vigilant because this substance misuse can lead to serious consequences.

[Antipsychotic induced rhabdomyolysis]. / Rhabdomyolyse induite par un traitement antipsychotique.

We report the case of a 40-year-old patient followed for post-traumatic stress disorder. A re-evaluation of its pharmacological treatment with the introduction of mirtazapine (30 mg/day) was associated with a rhabdomyolysis (CK> 20,000 IU/L at day 3). The diagnosis of mirtazapine induced rhabdomyolysis was made. After withdrawal of this drug combined with a symptomatic treatment (hydratation), the patient recovered well and was discharged without any nephrological sequelae. This article is intended to underline the diagnostic approach to elevated CK activity and the potential role of the "medical biologist" as a consultant for the relevant use of biological examinations. A physiopathological mechanism of this rhabdomyolysis is also proposed.