scholarly journals Highly Predictive Transdiagnostic Features Shared across Schizophrenia, Bipolar Disorder, and ADHD Identified Using a Machine Learning Based Approach

2018 ◽  
Author(s):  
Yuelu Liu ◽  
Monika S. Mellem ◽  
Humberto Gonzalez ◽  
Matthew Kollada ◽  
Atul R. Mahableshwarkar ◽  
...  
Keyword(s):  
Machine Learning ◽  
Bipolar Disorder ◽  
Psychiatric Disorders ◽  
Patient Group ◽  
Attention Deficit ◽  
The United States ◽  
Self Report ◽  
Healthy Controls ◽  
Cohen’S D ◽  
Cohen's D

AbstractThe Diagnostic and Statistical Manual of Mental Disorders (DSM) is the standard for diagnosing psychiatric disorders in the United States. However, evidence has suggested that symptoms in psychiatric disorders are not restricted to the boundaries between DSM categories, implying an underlying latent transdiagnostic structure of psychopathology. Here, we applied an importance-guided machine learning technique for model selection to item-level data from self-reported instruments contained within the Consortium for Neuropsychiatric Phenomics dataset. From 578 questionnaire items, we identified a set of features which consisted of 85 items that were shared across diagnoses of schizophrenia (SCZ), bipolar disorder (BD), and attention deficit/hyperactivity disorder (ADHD). A classifier trained on the transdiagnostic features reliably distinguished the patient group as a whole from healthy controls (classification AUC = 0.95) and only 10 items were needed to attain the performance level of AUC being 0.90. A sum score created from the items produced high separability between patients and healthy controls (Cohen’s d = 2.85), and it outperformed predefined sum scores and sub-scores within the instruments (Cohen’s d ranging between 0.13 and 1.21). The transdiagnostic features comprised both symptom domains (e.g. dysregulated mood, attention deficit, and anhedonia) and personality traits (e.g. neuroticism, impulsivity, and extraversion). Moreover, by comparing the features that were common across the three patient groups with those that were most predictive of a single patient category, we can describe the unique features for each patient group superimposed on the transdiagnostic feature structure. Overall, our results reveal a latent transdiagnostic symptom/behavioral phenotypic structure shared across SCZ, BD, and ADHD and present a new perspective to understand insights offered by self-report psychiatric instruments.

scholarly journals Responsiveness to Change of Self-Report and Device-Based Physical Activity Measures in the Living Well With Diabetes Trial

2015 ◽  
Vol 12 (8) ◽  
pp. 1082-1087 ◽  
Author(s):  
Winnie Y.H. Lee ◽  
Bronwyn K. Clark ◽  
Elisabeth Winkler ◽  
Elizabeth G. Eakin ◽  
Marina M. Reeves
Keyword(s):  
Physical Activity ◽  
Usual Care ◽  
Intervention Group ◽  
The United States ◽  
Telephone Counseling ◽  
Self Report ◽  
Responsiveness Index ◽  
Cohen’S D ◽  
Cohen's D ◽  
Responsiveness To Change

Background:This study evaluated the responsiveness to change in physical activity of 2 self-report measures and an accelerometer in the context of a weight loss intervention trial.Methods:302 participants (aged 20 to 75 years) with type 2 diabetes were randomized into telephone counseling (n = 151) or usual care (n = 151) groups. Physical activity (minutes/week) was assessed at baseline and 6-months using the Active Australia Survey (AAS), the United States National Health Interview Survey (USNHIS) walking for exercise items, and accelerometer (Actigraph GT1M; ≥1952 counts/minute). Responsiveness to change was calculated as responsiveness index (RI), Cohen’s d (postscores) and Cohen’s d (change-scores).Results:All instruments showed significant improvement in the intervention group (P < .001) and no significant change for usual care (P > .05). Accelerometer consistently ranked as the most responsive instrument while the least responsive was the USHNIS (responsiveness index) or AAS (Cohen’s d). RIs for AAS, USNHIS and accelerometer did not differ significantly and were, respectively: 0.45 (95% CI: 0.26–0.65); 0.38 (95% CI: 0.20–0.56); and, 0.49 (95% CI: 0.23–0.74).Conclusions:Accelerometer tended to have the highest responsiveness but differences were small and not statistically significant. Consideration of factors, such as validity, feasibility and cost, in addition to responsiveness, is important for instrument selection in future trials

scholarly journals T157. THE COURSE OF SCHIZOPHRENIA-RELATED NEURAL FINGERPRINTS OVER NINE YEARS - A LONGITUDINAL POPULATION-BASED MACHINE LEARNING STUDY

2020 ◽  
Vol 46 (Supplement_1) ◽  
pp. S290-S291
Author(s):  
Johannes Lieslehto ◽  
Erika Jääskeläinen ◽  
Jouko Miettunen ◽  
Matti Isohanni ◽  
Dominic Dwyer ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sensitivity And Specificity ◽  
Verbal Learning ◽  
Clinical Variable ◽  
Support Vector ◽  
Cohen’S D ◽  
Low Degree ◽  
Cohen's D ◽  
Over Time

Abstract Background Previous machine learning studies using structural MRI (sMRI) have been able to separate schizophrenia from controls with relatively high (about 80%) sensitivity and specificity (Kambeitz et al. Neuropsychopharmacology 2015). Interestingly, prediction accuracy in first-episode psychosis is lower compared to older and probably more chronic patients. One possibility is that the appearance of the neurodiagnostic fingerprints (NF) originated from the schizophrenia vs. controls classifier become more visible over time in schizophrenia due to the progressive nature of the disorder. Methods Using the Cobre sample (70 schizophrenia and 74 controls), we trained support vector machine (SVM) to differentiate schizophrenia from controls using sMRI. Next, we utilized the Northern Finland Birth Cohort 1966 (NFBC 1966) sample of 29 schizophrenia and 61 non-psychotic controls who participated in the nine-year follow-up. We applied the Cobre-trained SVM models at the baseline (participants 34 years old) and the follow-up (participants 43 years old) using out of sample cross-validation without any in-between retraining. Two independent schizophrenia datasets (the Neuromorphometry by Computer Algorithm Chicago [NMorphCH] and the Consortium for Neuropsychiatric Phenomics [CNP]) were utilized for replication analyses of the SVM generalizability. To address the possibility that the NF mainly capture some general psychopathology, we tested whether the NF generalize to depression using two independent MDD samples from Munich and Münster, Germany. Results Using the Cobre-trained SVM models for schizophrenia vs. controls differentiation in the NFBC 1966, we found balanced accuracy (i.e. mean of sensitivity and specificity, [BAC]) of 72.8% (sensitivity=58.6%, specificity=86.9%) at the baseline and BAC of 79.7% (sensitivity=75.9%, specificity=83.6%) at the follow-up. In the NFBC 1966 schizophrenia patients, we found that SVM decision scores varied as a function of timepoint into the direction of more schizophrenia-likeness at the follow-up (paired T-test, Cohen’s d=0.58, P=0.004). The same was not true in controls (Cohen’s d=0.09, P=0.49). The SVM decision score difference*timepoint interaction related to the decrease of hippocampus and medial prefrontal cortex. The SVM models’ performance was also validated at the two replication samples (BAC of 77.5% in the CNP and BAC of 69.1% in the NMorphCH). In the NFBC 1966 the strongest clinical variable correlating with the trajectory of SVM decision scores over the follow-up was poor performance in the California Verbal Learning Test. This finding was also replicated in the CNP dataset. Further, in the NFBC 1966, those schizophrenia patients with a low degree of SVM decision scores had a higher probability of being in remission, being able to work, and being without antipsychotic medication at the follow-up. The generalization of the SVM models to MDD was worse compared to schizophrenia classification (DeLong’s tests for the two ROC curves: P&lt;0.001). Discussion The degree of schizophrenia-related neurodiagnostic fingerprints appear to magnify over time in schizophrenia. By contrast, the discernibility of these fingerprints in controls does not change over time. This indicates that the NF captures some schizophrenia-related progressive neural changes, and not, e.g., normal aging-related brain volume loss. The fingerprints were also generalizable to other schizophrenia samples. Further, the fingerprints seem to have some disorder specificity as the SVM models do not generalize to depression. Lastly, it appears that a low degree of schizophrenia-related NF in schizophrenia might possess some value in predicting patients’ future remission and recovery-related factors.

scholarly journals Pharmacogenomic Biomarkers and Their Applications in Psychiatry

Genes ◽  
2020 ◽  
Vol 11 (12) ◽  
pp. 1445
Author(s):  
Heejin Kam ◽  
Hotcherl Jeong
Keyword(s):  
Bipolar Disorder ◽  
Attention Deficit Hyperactivity Disorder ◽  
Precision Medicine ◽  
Psychiatric Disorders ◽  
Antiepileptic Drugs ◽  
Attention Deficit ◽  
Neurological Disorder ◽  
Morbidity And Mortality ◽  
Social Burden ◽  
Hyperactivity Disorder

Realizing the promise of precision medicine in psychiatry is a laudable and beneficial endeavor, since it should markedly reduce morbidity and mortality and, in effect, alleviate the economic and social burden of psychiatric disorders. This review aims to summarize important issues on pharmacogenomics in psychiatry that have laid the foundation towards personalized pharmacotherapy and, in a broader sense, precision medicine. We present major pharmacogenomic biomarkers and their applications in a variety of psychiatric disorders, such as depression, attention-deficit/hyperactivity disorder (ADHD), narcolepsy, schizophrenia, and bipolar disorder. In addition, we extend the scope into epilepsy, since antiepileptic drugs are widely used to treat psychiatric disorders, although epilepsy is conventionally considered to be a neurological disorder.

Generalized Anxiety Disorder Symptom Improvement Following Mindfulness-Based Stress Reduction in a General Hospital Setting

2020 ◽  
Vol 1 (1) ◽  
pp. 19-27 ◽  
Author(s):  
Holly Hazlett-Stevens
Keyword(s):  
General Hospital ◽  
Hospital Setting ◽  
Self Report ◽  
Symptom Improvement ◽  
Effective Treatment Option ◽  
Large Hospital ◽  
Medical Settings ◽  
Cohen’S D ◽  
Heterogeneous Groups ◽  
Cohen's D

Background: GAD symptom complaints are common in general medical settings, yet psychosocial intervention options provided within such settings are limited. Randomized controlled trials have found that MBSR is effective for symptom reduction, but such research typically delivered MBSR to small diagnostically homogeneous patient groups rather than to larger heterogeneous groups as provided in medical settings. Objective: The current research examined what proportion of patients already enrolled in a general hospital MBSR program presented with symptoms of GAD and whether such symptoms reduced after delivering MBSR in large diagnostically heterogeneous groups. Methods: Twenty-six (40%) of 65 participants enrolled in a large hospital MBSR program indicated moderate to severe GAD symptom severity at the first MBSR session. Of these, 19 voluntarily completed brief self-report measures at the beginning and end of their MBSR course. Results: Statistically significant reductions pre to post-MBSR were found on the GAD-7 (Cohen’s d = 1.95), Penn State Worry Questionnaire (Cohen’s d = 0.76) and the DASS21 Anxiety (Cohen’s d = 0.71) and Stress (Cohen’s d = 1.31) scales. Fifteen (79%) GAD participants scored below the GAD-7 screening measure cutoff at the final MBSR session. Forty-seven percent showed clinically significant improvement on PSWQ scores. Conclusions: MBSR, as typically delivered in general hospital settings, may provide an acceptable and effective treatment option for GAD patients seeking care in medical settings.

scholarly journals Cerebellum and psychiatric disorders

2008 ◽  
Vol 30 (3) ◽  
pp. 281-289 ◽  
Author(s):  
Leonardo Baldaçara ◽  
João Guilherme Fiorani Borgio ◽  
Acioly Luiz Tavares de Lacerda ◽  
Andrea Parolin Jackowski
Keyword(s):  
Magnetic Resonance Imaging ◽  
Bipolar Disorder ◽  
Attention Deficit Hyperactivity Disorder ◽  
Anxiety Disorders ◽  
Psychiatric Disorders ◽  
Attention Deficit ◽  
Resonance Imaging ◽  
Imaging Studies ◽  
Hyperactivity Disorder

OBJECTIVE: The objective of this update article is to report structural and functional neuroimaging studies exploring the potential role of cerebellum in the pathophysiology of psychiatric disorders. METHOD: A non-systematic literature review was conducted by means of Medline using the following terms as a parameter: "cerebellum", "cerebellar vermis", "schizophrenia", "bipolar disorder", "depression", "anxiety disorders", "dementia" and "attention deficit hyperactivity disorder". The electronic search was done up to April 2008. DISCUSSION: Structural and functional cerebellar abnormalities have been reported in many psychiatric disorders, namely schizophrenia, bipolar disorder, major depressive disorder, anxiety disorders, dementia and attention deficit hyperactivity disorder. Structural magnetic resonance imaging studies have reported smaller total cerebellar and vermal volumes in schizophrenia, mood disorders and attention deficit hyperactivity disorder. Functional magnetic resonance imaging studies using cognitive paradigms have shown alterations in cerebellar activity in schizophrenia, anxiety disorders and attention deficit hyperactivity disorder. In dementia, the cerebellum is affected in later stages of the disease. CONCLUSION: Contrasting with early theories, cerebellum appears to play a major role in different brain functions other than balance and motor control, including emotional regulation and cognition. Future studies are clearly needed to further elucidate the role of cerebellum in both normal and pathological behavior, mood regulation, and cognitive functioning.

scholarly journals Can the MMPI Predict Adult ADHD? An Approach Using Machine Learning Methods

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 976
Author(s):  
Sunhae Kim ◽  
Hyekyung Lee ◽  
Kounseok Lee
Keyword(s):  
Machine Learning ◽  
Attention Deficit Hyperactivity Disorder ◽  
Random Forest ◽  
Attention Deficit ◽  
Adult Adhd ◽  
Minnesota Multiphasic Personality Inventory ◽  
Self Report ◽  
Adhd Symptoms ◽  
Linear Discriminant ◽  
Hyperactivity Disorder

(1) Background: Adult attention-deficit/hyperactivity disorder (ADHD) symptoms cause various social difficulties due to attention deficit and impulsivity. In addition, in contrast to ADHD in childhood, ADHD in adulthood is difficult to diagnose due to mixed psychopathologies. This study aimed to determine whether it is possible to predict ADHD symptoms in adults using the Minnesota Multiphasic Personality Inventory-2 (MMPI-2) with machine learning (ML) techniques; (2) Methods: Data collected from 5726 college students were analyzed. The MMPI-2-Restructured Form (MMPI-2-RF) was used, and ADHD symptoms in adults were evaluated using the Attention-Deficit/Hyperactivity Disorder Self-Report Scale (ASRS). For statistical analysis, three ML algorithms were used, i.e., K-nearest neighbors (KNN), linear discriminant analysis (LDA), and random forest, with the ASRS evaluation result as the dependent variable and the 50 MMPI-2-RF scales as predictors; (3) Results: When the KNN, LDA, and random forest techniques were applied, the accuracy was 93.1%, 91.2%, and 93.6%, respectively, and the area under the curve (AUC) was 0.722, 0.806, and 0.790, respectively. The AUC of the LDA method was the largest, with an excellent level of diagnostic accuracy; (4) Conclusions: ML using the MMPI-2 in a large group could provide reliable accuracy in screening for adult ADHD.

Cardioprotective potential of lithium and role of fractalkine in euthymic patients with bipolar disorder

2021 ◽  
pp. 000486742110625
Author(s):  
Pao-Huan Chen ◽  
Cheng-Yi Hsiao ◽  
Shuo-Ju Chiang ◽  
Ruei-Siang Shen ◽  
Yen-Kuang Lin ◽  
...  
Keyword(s):  
Bipolar Disorder ◽  
Cardiovascular Risk ◽  
Lithium Treatment ◽  
Structure And Function ◽  
Cardiac Structure ◽  
High Cardiovascular Risk ◽  
Cohen’S D ◽  
Cardiac Structure And Function ◽  
And Function ◽  
Cohen's D

Objective: Over a half century, lithium has been used as the first-line medication to treat bipolar disorder. Emerging clinical and laboratory studies suggest that lithium may exhibit cardioprotective effects in addition to neuroprotective actions. Fractalkine (CX3CL1) is a unique chemokine associated with the pathogenesis of mood disorders and cardiovascular diseases. Herein we aimed to ascertain whether lithium treatment is associated with favorable cardiac structure and function in relation to the reduced CX3CL1 among patients with bipolar disorder. Methods: We recruited 100 euthymic patients with bipolar I disorder aged over 20 years to undergo echocardiographic study and measurement of plasma CX3CL1. Associations between lithium treatment, cardiac structure and function and peripheral CX3CL1 were analyzed according to the cardiovascular risk. The high cardiovascular risk was defined as (1) age ⩾ 45 years in men or ⩾ 55 years in women or (2) presence of concurrent cardiometabolic diseases. Results: In the high cardiovascular risk group ( n = 61), patients who received lithium as the maintenance treatment had significantly lower mean values of left ventricular internal diameters at end-diastole (Cohen’s d = 0.65, p = 0.001) and end-systole (Cohen’s d = 0.60, p = 0.004), higher mean values of mitral valve E/A ratio (Cohen’s d = 0.51, p = 0.019) and superior performance of global longitudinal strain (Cohen’s d = 0.51, p = 0.037) than those without lithium treatment. In addition, mean plasma levels of CX3CL1 in the high cardiovascular risk group were significantly lower among patients with lithium therapy compared with those without lithium treatment ( p = 0.029). Multiple regression models showed that the association between lithium treatment and mitral value E/A ratio was contributed by CX3CL1. Conclusion: Data from this largest sample size study of the association between lithium treatment and echocardiographic measures suggest that lithium may protect cardiac structure and function in patients with bipolar disorder. Reduction of CX3CL1 may mediate the cardioprotective effects of lithium.

Sign in / Sign up

Export Citation Format

Share Document