Forecasting Depression in Bipolar Disorder

Moore, Pearl; Little, Max A.; McSharry, Patrick E.; Geddes, John; Goodwin, Guy M.

doi:10.1109/tbme.2012.2210715

Cited by 40 publications

(34 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Investigators have used clinical information to forecast violent behavior among outpatients with schizophrenia (Tzeng, Lin, & Hsieh, 2004) achieving moderate success of 76.2% positive prediction of later violent behavior. In contrast, ML has failed in forecasting the course of bipolar disorder from clinical data (Moore, Little, McSharry, Geddes, & Goodwin, 2012). A review of studies forecasting the risk for psychotic disorders (Strobl, Eack, Swaminathan, & Visweswaran, 2012) showed an advantage for ML-based Support Vector Machines (SVMs) classification.…”

Section: Introductionmentioning

confidence: 99%

Quantitative forecasting of PTSD from early trauma responses: A Machine Learning application

Galatzer‐Levy

Karstoft

Statnikov

et al. 2014

Journal of Psychiatric Research

179

132

View full text Add to dashboard Cite

There is broad interest in predicting the clinical course of mental disorders from early, multimodal clinical and biological information. Current computational models, however, constitute a significant barrier to realizing this goal. The early identification of trauma survivors at risk of post-traumatic stress disorder (PTSD) is plausible given the disorder’s salient onset and the abundance of putative biological and clinical risk indicators. This work evaluates the ability of Machine Learning (ML) forecasting approaches to identify and integrate a panel of unique predictive characteristics and determine their accuracy in forecasting non-remitting PTSD from information collected within 10 days of a traumatic event. Data on event characteristics, emergency department observations, and early symptoms were collected in 957 trauma survivors, followed for fifteen months. An ML feature selection algorithm identified a set of predictors that rendered all others redundant. Support Vector Machines (SVMs) as well as other ML classification algorithms were used to evaluate the forecasting accuracy of i) ML selected features, ii) all available features without selection, and iii) Acute Stress Disorder (ASD) symptoms alone. SVM also compared the prediction of a) PTSD diagnostic status at 15 months to b) posterior probability of membership in an empirically derived non-remitting PTSD symptom trajectory. Results are expressed as mean Area Under Receiver Operating Characteristics Curve (AUC). The feature selection algorithm identified 16 predictors, present in ≥95% cross-validation trials. The accuracy of predicting non-remitting PTSD from that set (AUC=.77) did not differ from predicting from all available information (AUC=.78). Predicting from ASD symptoms was not better then chance (AUC =.60). The prediction of PTSD status was less accurate than that of membership in a non-remitting trajectory (AUC=.71). ML methods may fill a critical gap in forecasting PTSD. The ability to identify and integrate unique risk indicators makes this a promising approach for developing algorithms that infer probabilistic risk of chronic posttraumatic stress psychopathology based on complex sources of biological, psychological, and social information.

show abstract

Section: Introductionmentioning

confidence: 99%

Quantitative forecasting of PTSD from early trauma responses: A Machine Learning application

Galatzer‐Levy

Karstoft

Statnikov

et al. 2014

Journal of Psychiatric Research

179

132

View full text Add to dashboard Cite

show abstract

“…Personalized text messaging has been used to manage appointments among youth with mental illness, to record mood state in bipolar disorder, in assessment of schizophrenic patients, to prevent relapse in alcohol use disorder, support patients with bulimia nervosa, evaluate mood among patients with depression, communicate medication changes and provide expressions of support (Furber et al, 2011;Spaniel et al, 2008;Granholm et al, 2012;Bopp et al, 2010;Moore et al, 2012;Agyapong et al, 2013;Mä kela et al, 2010). Personalized text messages have also been used for substance cessation (Free et al, 2009;Rodgers et al, 2005).…”

Section: Introductionmentioning

confidence: 99%

‘SMS’ for mental health – Feasibility and acceptability of using text messages for mental health promotion among young women from urban low income settings in India

Chandra

Sowmya

Mehrotra

et al. 2014

Asian Journal of Psychiatry

View full text Add to dashboard Cite

“…Lots of studies have used the HWES method with both additive and multiplicative approaches to analyze time series data in medical areas. [20][21][22][23] Limitations of this study are that the study was done according to the patient's records in hospital and we did not have access to information before 2008.…”

Section: Discussionmentioning

confidence: 99%

Forecasting Schizophrenia Incidence Frequencies Using Time Series Approach

Ghaffari

Ghaleiha

Taslimi

et al. 2017

Int Clin Neurosci J

View full text Add to dashboard Cite

IntroductionSchizophrenia is a disabling number of brain disorders characterized by symptoms such as hallucinations, delusions, disorganized interaction, poor planning, reduced incentive, and blunted influence.1 Schizophrenia is associated with deficits in various cognitive processes that result in disorders of complex thinking and ideation, resulting in difficulty in dealing with 'psychological and social challenges in daily life.2 Schizophrenia is a devastating psychiatric disorder that affects approximately 1% of the population.3 For several years, it was believed that the prevalence of schizophrenia varied little between sites. 4,5 It is, in fact, the case that the estimates of the prevalence of schizophrenia are seen as a multiplicity of variations. 1,[6][7][8] Major advancements have been made in our understanding of the epidemiology of schizophrenia. We now understand that the illness is somewhat more common and severe in young men, and that the occurrence may differ geographically and temporally. Risk factors have been elucidated; biological risks include a family history and ancestors of the complaint, advanced paternal age, obstetric difficulties, and abuse of drugs such as stimulants and cannabis. Furthermore, new research has also recognized social risk factors such as being born and brought up in a city, migration, and certain types of childhood difficulty such as physical misuse and bullying, as well as social separation and opposing events in adult lifetime. To conclude, the epidemiological evidence suggests that schizophrenia is a multifactorial disorder in which genes connect to the other person and with environmental factors to push individuals more than a threshold into expression of the disorder. 9 Studies that estimate the occurrence of schizophrenia are required to be able to recognize gradients across time and/or place. Forecasting Schizophrenia Incidence Frequencies Using Time Series Approach Conclusion:Our study showed that a significant increase happens in the frequency of schizophrenia from 2016. Although the development is not constant and the same for all months, the amount of increase is considerably high compared to before 2016.

show abstract

Forecasting Depression in Bipolar Disorder

Cited by 40 publications

References 26 publications

Quantitative forecasting of PTSD from early trauma responses: A Machine Learning application

Quantitative forecasting of PTSD from early trauma responses: A Machine Learning application

‘SMS’ for mental health – Feasibility and acceptability of using text messages for mental health promotion among young women from urban low income settings in India

Forecasting Schizophrenia Incidence Frequencies Using Time Series Approach

Contact Info

Product

Resources

About