Efficient Prediction of Vitamin B Deficiencies via Machine-Learning Using Routine Blood Test Results in Patients With Intense Psychiatric Episode.

BACKGROUND: Vitamin B deficiency is common worldwide and may lead to psychiatric symptoms; however, vitamin B deficiency epidemiology in patients with intense psychiatric episode has rarely been examined. Moreover, vitamin deficiency testing is costly and time-consuming, which has hampered effectively ruling out vitamin deficiency-induced intense psychiatric symptoms. In this study, we aimed to clarify the epidemiology of these deficiencies and efficiently predict them using machine-learning models from patient characteristics and routine blood test results that can be obtained within one hour. METHODS: We reviewed 497 consecutive patients, who are deemed to be at imminent risk of seriously harming themselves or others, over a period of 2 years in a single psychiatric tertiary-care center. Machine-learning models (k-nearest neighbors, logistic regression, support vector machine, and random forest) were trained to predict each deficiency from age, sex, and 29 routine blood test results gathered in the period from September 2015 to December 2016. The models were validated using a dataset collected from January 2017 through August 2017. RESULTS: We found that 112 (22.5%), 80 (16.1%), and 72 (14.5%) patients had vitamin B1, vitamin B12, and folate (vitamin B9) deficiency, respectively. Further, the machine-learning models were well generalized to predict deficiency in the future unseen data, especially using random forest; areas under the receiver operating characteristic curves for the validation dataset (i.e., the dataset not used for training the models) were 0.716, 0.599, and 0.796, respectively. The Gini importance of these vitamins provided further evidence of a relationship between these vitamins and the complete blood count, while also indicating a hitherto rarely considered, potential association between these vitamins and alkaline phosphatase (ALP) or thyroid stimulating hormone (TSH). DISCUSSION: This study demonstrates that machine-learning can efficiently predict some vitamin deficiencies in patients with active psychiatric symptoms, based on the largest cohort to date with intense psychiatric episode. The prediction method may expedite risk stratification and clinical decision-making regarding whether replacement therapy should be prescribed. Further research includes validating its external generalizability in other clinical situations and clarify whether interventions based on this method could improve patient care and cost-effectiveness.

Association of schizophrenia onset age and white matter integrity with treatment effect of D-cycloserine: a randomized placebo-controlled double-blind crossover study.

BACKGROUND: It has been reported that drugs which promote the N-Methyl-D-aspartate-type glutamate receptor function by stimulating the glycine modulatory site in the receptor improve negative symptoms and cognitive dysfunction in schizophrenia patients being treated with antipsychotic drugs. METHODS: We performed a placebo-controlled double-blind crossover study involving 41 schizophrenia patients in which D-cycloserine 50 mg/day was added-on, and the influence of the onset age and association with white matter integrity on MR diffusion tensor imaging were investigated for the first time. The patients were evaluated using the Positive and Negative Syndrome Scale (PANSS), Scale for the Assessment of Negative Symptoms (SANS), Brief Assessment of Cognition in Schizophrenia (BACS), and other scales. RESULTS: D-cycloserine did not improve positive or negative symptoms or cognitive dysfunction in schizophrenia. The investigation in consideration of the onset age suggests that D-cycloserine may aggravate negative symptoms of early-onset schizophrenia. The better treatment effect of D-cycloserine on BACS was observed when the white matter integrity of the sagittal stratum/ cingulum/fornix stria terminalis/genu of corpus callosum/external capsule was higher, and the better treatment effect on PANSS general psychopathology (PANSS-G) was observed when the white matter integrity of the splenium of corpus callosum was higher. In contrast, the better treatment effect of D-cycloserine on PANSS-G and SANS-IV were observed when the white matter integrity of the posterior thalamic radiation (left) was lower. CONCLUSION: It was suggested that response to D-cycloserine is influenced by the onset age and white matter integrity. TRIAL REGISTRATION: UMIN Clinical Trials Registry (number UMIN000000468 ). Registered 18 August 2006.

[An Adolescent Case of ASD Presenting with Persistent Catatonia and Epileptic EEG Discharge].

A 26-year-old man developed a catatonic state after his grandmother's death and the Great East Japan Earthquake. He was admitted to hospital because of the prolonged severe stupor. Electroencephalography (EEG) revealed focal (F3 electrode) and generalized epileptic abnormalities. He was administered antiepileptic agents and benzodiazepines, but his stupor did not improve in spite of a reduced frequency of epileptic EEG abnormalities. His clinical his- tory did not suggest any psychotic disorders. Thereafter, extensive physical examinations were performed, but an organic cause of the stupor was not determined. For about two years, he was unable to intake food without tubal feeding, have a conversation, or move spontaneously. One day, a generalized tonic-clonic seizure (GTC) occurred spontaneously for the first time in his life, and then his stupor markedly improved. Thereafter, he could eat food spontaneously, have a fluent conversation, and move actively. After his condition had improved, we asked his parents about his developmental history, clinical history, and present state. According to clini- cal interviews including the use of PARS (Pervasive Developmental Disorders Autism Society Japan Rating Scale), DISCO (Diagnostic Interview for Social and Communication Disorders), and WAIS-III (Wechsler Adult Intelligence Scale-third edition), he was diagnosed with autistic spectrum disorder (ASD) and mild intellectual disability. It was considered that his stupor had occurred secondary to ASD. Wing et al. reported that catatonia occurred in about 17% of ASD adolescents and young adults as a later complication. It is possible that this case, without any psychotic disorders and with ASD that has been undiagnosed until young adult, progress to such a severe and prolonged catatonic state. We report this case to show that severe catatonia is possible in adolescents and young adults during the carry-over period in ASD patients.

Sensorineural hearing loss associated with a factitious disorder.

Factitious disorders are characterized by intentionally abnormal physical and/or psychological behavior, and affected patients often make up their symptoms and clinical histories. The most serious and chronic type of factitious disorder is Munchausen syndrome. We report the case of a 24-year-old woman with a 2-year history of sensorineural hearing loss (SNHL) who later confessed to feigning her hearing loss. She was eventually diagnosed with a factitious disorder. During those 2 years, she was able to induce her SNHL by exposing herself to excessive noise or high doses of aspirin. To the best of our knowledge, this is the first report describing an association between a factitious disorder and SNHL.

Clinical course of the bipolar II disorder in a Japanese sample.

BACKGROUND: The bipolar II disorder has been recognized a mental disorder distinctive from the bipolar I disorder, showing the stability of diagnosis in prospective studies. However, the characterization of the bipolar II disorder still remains under investigation. METHODS: The present study was conducted on consecutively admitted bipolar II inpatients diagnosed by DSM-IV-TR to delineate the clinical features. RESULTS: The types of initial mood disorders of the bipolar II inpatients were divided into four groups, i.e., major depressive episode (MDE), hypomanic episode (HME), and dysthymic and cyclothymic disorders. Seventy-one percent of all the patients belonged to the MDE group, a half of which underwent the first HME following the first MDE. The number of patients that exhibited the HME within one year after the first MDE was the highest in a widely distributed interval of years between the first MDE and the first HME. The cyclothymic disorder group was relatively young at the onset and was more prone to attempt suicide. Moreover, there might be a complex connection with other psychiatric disorders, such as anxiety disorders, in the longitudinal course of the bipolar disorder. LIMITATION: The present study was carried out on a limited number of patients admitted to one hospital. The data are partly based on the retrospective information from the patients and their relatives. The generalization of the results requires further studies. CONCLUSION: The bipolar II disorder could be divided into heterogeneous groups in the longitudinal course. Hence, paying attention to the heterogeneity in clinical practice and a study of the disorder are required.

Subgenual cingulate theta activity predicts treatment response of repetitive transcranial magnetic stimulation in participants with vascular depression.

Repetitive transcranial magnetic stimulation (rTMS) is an effective treatment for depression. Increased metabolism in the anterior cingulate cortex (ACC) is a known predictor for antidepressant response. The authors assessed whether increased theta power within the ACC predicts rTMS response in participants with vascular depression. Sixty-five participants were randomized to active or sham rTMS. Outcome was assessed using the Hamilton Depression Rating Scale. Electroencephalography was obtained, and comparisons were made among each group with a normative database using low-resolution electromagnetic tomography. Results suggest that vascular depression participants respond well to rTMS and that increased low-theta power in the subgenual ACC predicts response to rTMS.

Correlation between denial of illness and executive function following stroke: a pilot study.

Executive function and denial of illness were examined among 24 patients who received double-blind antidepressant treatment following stroke. Between end-of-treatment at 3 months and follow-up at 2 years, significant correlation was found between improvement in executive function and decrease in denial of illness.

Effect of antidepressant therapy on executive function after stroke.

BACKGROUND: Executive dysfunction is common after stroke and may impair long-term outcome. Remedies for this condition are limited. AIMS: To examine the effect of antidepressants on executive function after stroke. METHOD: Forty-seven patients who had had a stroke during the prior 6 months received 12 weeks of antidepressant treatment in double-blind placebo-controlled fashion, followed by assessment of executive function at the end of treatment and after 2 years. RESULTS: No significant group effect was found at the end of treatment. However, 21 months after the end of treatment the placebo group showed deterioration of executive function, whereas the active treatment group showed clear and significant improvement independent of depressive symptoms (F=12.1, d.f.=1,45, P= 0.001). CONCLUSIONS: Antidepressant treatment fosters long-term improvement of executive function following stroke. This phenomenon is consistent with a reorganisation of neuronal networks associated with prefrontal functions based on modulation of monoaminergic neurotransmission and the activity of neurotrophins.

Repetitive transcranial magnetic stimulation as treatment of poststroke depression: a preliminary study.

BACKGROUND: Depression has a significant impact on poststroke recovery and mortality. There are a proportion of patients with poststroke depression (PSD) who do not respond to antidepressants. Repetitive Transcranial Magnetic Stimulation (rTMS) might be a safe and effective alternative in these refractory cases. METHODS: We conducted a randomized, parallel, double-blind study of active versus sham left prefrontal rTMS in patients with refractory PSD. After discontinuing antidepressants, patients were randomly assigned to receive 10 sessions of active (10 Hz, 110% of the motor threshold, 20 trains of 5 seconds duration) or sham left prefrontal rTMS. Efficacy measures included HAM-D scores, response and remission rates. Patients completed a neuropsychological battery at baseline and after completing the protocol. RESULTS: When compared with sham stimulation, 10 sessions of active rTMS of the left dorsolateral prefrontal cortex were associated with a significant reduction of depressive symptoms. This reduction was not influenced by patient's age, type or location of stroke, volume of left frontal leukoaraiosis or by the distance of the stimulating coil to the prefrontal cortex. However, there was a significant positive correlation between the percentage of reduction of Ham-D scores and frontal gray and white matter volumes. There were no significant changes in cognitive functioning between the active and the sham stimulation groups. In addition, there were few and mild adverse effects that were equally distributed among groups. CONCLUSIONS: Taken together, these preliminary findings suggest that rTMS may be an effective and safe treatment alternative for patients with refractory depression and stroke.

The effect of early versus late antidepressant treatment on physical impairment associated with poststroke depression: is there a time-related therapeutic window?

Impairments in activities of daily living (ADL) are common after stroke and may be related to poststroke depression. We have demonstrated that remission of poststroke major depression was associated with improvement in ADL. The administration of antidepressants within the first 3 months after stroke has been shown to prevent poststroke depression, early administration might also improve recovery of ADL among patients with stroke. This study examines the effect of early versus late treatment with antidepressants on recovery in ADL. Among 62 patients after stroke, the therapeutic effect of a 3-month course of antidepressants begun during the first month after stroke was compared with the effect of treatment begun after 1 month. The severity of impairment was measured using the Functional Independence Measure (FIM) and post-treatment outcome was assessed over the following 21 months. Although both the early and late treatment groups showed improvements in FIM scores during the 3 months of treatment, the early treatment group improved significantly more than the late treatment group. After the treatment, the early treatment group maintained this improvement over 2 years while the late treatment group deteriorated over time. There were no significant differences in the 2 groups that would explain the findings. Recovery in ADL impairment after stroke appeared to be enhanced by the use of antidepressant medication if treatment was started within the first month after stroke. These findings are consistent with the hypothesis that there may be a time-related therapeutic window in the treatment of physical impairment associated with poststroke depression.

Does cognitive recovery after treatment of poststroke depression last? A 2-year follow-up of cognitive function associated with poststroke depression.

OBJECTIVE: Cognitive impairment is common after stroke and may be caused by poststroke depression. Remission of poststroke major depression after treatment has been associated with improvement in cognitive function. The current study was designed to examine how long that cognitive improvement lasts and to compare depressed patients' cognitive status with that of nondepressed patients with comparable lesions. METHOD: Seventeen patients with poststroke depression and cognitive impairment who had early and sustained remission of their depression during a double-blind treatment study were compared with 42 nondepressed stroke patients who remained nondepressed throughout the follow-up. Mood and cognitive function were followed-up over 2 years with the Hamilton Depression Rating Scale and Mini-Mental State Examination (MMSE). RESULTS: In the patients with early and sustained remission of depression, there was rapid improvement of cognitive function, which was maintained over 2 years. Their initial MMSE score of 23.3 (SD=4.2) improved to 26.6 (SD=3.5) at 3 months and was 26.1 (SD=3.6) at 2 years. The nondepressed patients showed essentially no change in cognitive function over 2 years (initial MMSE score: mean=26.3, SD=3.1; score at 2-year follow-up: mean=25.7, SD=4.1). CONCLUSIONS: Cognitive function, once improved after remission of poststroke depression, is likely to remain stable over the next 2 years in the absence of subsequent reinjury to the central nervous system. Cognitive impairment due to poststroke depression is reversible and can be quantified separately from cognitive impairment on the basis of the location and extent of ischemic brain damage.

Stroke-related depression.

Stroke represents a major health problem in the United States and most European and Asian countries. Depression is probably the most common and serious emotional disorder following stroke. Post-stroke depression (PSD) has frequently been overlooked and left untreated. Prevention of PSD or successful intervention in the early phase may prevent premature deaths as well as facilitate rehabilitation, reduce costs, and improve quality of life. Stroke is clearly a risk factor for depression, and recent evidence suggests that depression increases the risk for stroke, although the mechanisms by which depression leads to stroke remain to be clarified. Once PSD has developed, numerous studies have documented its adverse effect on cognitive recovery, physical recovery, and mortality. Taken together, these studies support the necessity of identifying and treating this condition.

Preventing poststroke depression: a 12-week double-blind randomized treatment trial and 21-month follow-up.

This study examined the effect of antidepressants in preventing depression after stroke. Nondepressed poststroke patients (N = 48) were randomly assigned to receive nortriptyline, fluoxetine, or placebo for 3 months by using double-blind methodology and were followed-up for 21 months by using a naturalistic design. During the treatment period, one minor depression developed in the nortriptyline group (n = 13 at 3 months), one minor depression developed in the fluoxetine group (n = 13), and five minor depressions developed in the placebo group (n = 15; p <.05). When treatment was discontinued, nortriptyline-treated patients were more likely to develop depression and had significantly more severe depressive symptoms during the next 6 months compared with patients in the other two groups. Both nortriptyline and fluoxetine appeared to be efficacious in preventing depression after stroke. However, nortriptyline produced an increased vulnerability to depression for more than 6 months after it was discontinued. This finding suggests the need to extend prophylactic treatment and monitor patients carefully after the discontinuation of nortriptyline.