Optimizing existing mental health screening methods in a dementia screening and risk-factor app: An Observational, machine learning study (Preprint)

2021 ◽  
Author(s):  
Narayan Kuleindiren ◽  
Raphael Paul Rifkin-Zybutz ◽  
Monika Johal ◽  
Hamza Selim ◽  
Itai Palmon ◽  
...  
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Risk Factors ◽  
Regression Models ◽  
Superior Performance ◽  
Training Dataset ◽  
Screening Methods ◽  
Depression And Anxiety ◽  
Dementia Screening ◽  
Fold Cross Validation

BACKGROUND Mindset4Dementia is an app that aims to improve dementia screening by assessing cognition and risk factors. It considers important clinical risk factors, including prodromal symptoms, mental health disorders, and differential diagnoses of dementia. The PHQ-9 and GAD-7 are widely validated, and commonly used scales used in screening for depression and anxiety disorders respectively. Shortened versions of both (PHQ-2/GAD-2) have been produced. OBJECTIVE We sought to develop a method that maintained the brevity of these shorter questionnaires while maintaining the better precision of the original questionnaires METHODS Single questions were designed to encompass symptoms covered in the original questionnaires. Answers to these questions were combined with the PHQ-2/GAD-2 and anonymized risk factors collected by Mindset4Dementia. Machine learning models were trained to use these single questions in combination with data already collected by the app - age, response to a joke and reporting of functional impairment to predict binary and continuous outcomes as measured by the PHQ-9/GAD-7. Our model was developed with a training dataset using ten-fold cross-validation and a hold-out testing datasets and compared to results from using the shorter questionnaires (PHQ-2/GAD-2) alone to benchmark performance. RESULTS We were able to achieve superior performance in predicting PHQ-9/GAD-7 screening cut-offs than the PHQ-2 (difference In AUC 0.04, 95% CI 0.00 – 0.08, P = 0.02) but not to GAD-2 (difference in AUC 0.00, 95% CI -0.02 – 0.03, P = 0.42). In regression models we were able to accurately predict total questionnaire scores; PHQ-9 (R2 = 0.655, MAE = 2.267), GAD-7 (R2 = 0.837, MAE = 1.780). CONCLUSIONS We have developed a short screening tool for affective disorders with superior or equivalent performance to well established methods.

Schoolchildren’ Depression and Anxiety Prediction Using Machine Learning Algorithms (Preprint)

2021 ◽  
Author(s):  
Radwan Qasrawi ◽  
Stephanny Vicuna Polo ◽  
Diala Abu Al-Halawah ◽  
Sameh Hallaq ◽  
Ziad Abdeen
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Risk Factors ◽  
Cognitive Development ◽  
Random Forest ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Depression And Anxiety ◽  
Factors Associated ◽  
Learning Techniques

BACKGROUND : Depression and anxiety symptoms in early childhood have a major effect on children's mental health growth and cognitive development. Studying the effect of mental health problems on cognitive development has gained researchers' attention for the last two decades OBJECTIVE In this paper, we seek to use machine learning techniques to predict the risk factors associated with school children's depression and anxiety METHODS The study data consisted of 5685 students in grades 5-9, aged 10-17 years, studying at public and refugee schools in the West Bank. The data were collected using the health behaviors school children questionnaire in the 2012-2013 academic year and analyzed using machine learning to predict the risk factors associated with student mental health symptoms. Five machine learning techniques (Random Forest, Neural Network, Decision Tree, Support Vector Machine, and Naïve Bayes) were used for the prediction. RESULTS The results indicated that the Random Forest model had the highest accuracy levels (72.6%, 68.5%) for depression and anxiety respectively. Thus, the Random Forest had the best performance in classifying and predicting the student's depression and anxiety. The results showed that school violence and bullying, home violence, academic performance, and family income were the most important factors affecting depression and anxiety scales CONCLUSIONS Overall, machine learning proved to be an efficient tool for identifying and predicting the associated factors that influence student depression and anxiety. The deployment of machine learning within the school information systems might facilitate the development of health prevention and intervention programs that will enhance students’ mental health and cognitive development.

scholarly journals Accurate estimation of isoelectric point of protein and peptide based on amino acid sequences

2015 ◽  
Vol 32 (6) ◽  
pp. 821-827 ◽  
Author(s):  
Enrique Audain ◽  
Yassel Ramos ◽  
Henning Hermjakob ◽  
Darren R. Flower ◽  
Yasset Perez-Riverol
Keyword(s):  
Machine Learning ◽  
Isoelectric Point ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Basis Set ◽  
Superior Performance ◽  
Supplementary Information ◽  
Training Dataset ◽  
Accurate Estimation ◽  
Prediction Methods

Abstract Motivation: In any macromolecular polyprotic system—for example protein, DNA or RNA—the isoelectric point—commonly referred to as the pI—can be defined as the point of singularity in a titration curve, corresponding to the solution pH value at which the net overall surface charge—and thus the electrophoretic mobility—of the ampholyte sums to zero. Different modern analytical biochemistry and proteomics methods depend on the isoelectric point as a principal feature for protein and peptide characterization. Protein separation by isoelectric point is a critical part of 2-D gel electrophoresis, a key precursor of proteomics, where discrete spots can be digested in-gel, and proteins subsequently identified by analytical mass spectrometry. Peptide fractionation according to their pI is also widely used in current proteomics sample preparation procedures previous to the LC-MS/MS analysis. Therefore accurate theoretical prediction of pI would expedite such analysis. While such pI calculation is widely used, it remains largely untested, motivating our efforts to benchmark pI prediction methods. Results: Using data from the database PIP-DB and one publically available dataset as our reference gold standard, we have undertaken the benchmarking of pI calculation methods. We find that methods vary in their accuracy and are highly sensitive to the choice of basis set. The machine-learning algorithms, especially the SVM-based algorithm, showed a superior performance when studying peptide mixtures. In general, learning-based pI prediction methods (such as Cofactor, SVM and Branca) require a large training dataset and their resulting performance will strongly depend of the quality of that data. In contrast with Iterative methods, machine-learning algorithms have the advantage of being able to add new features to improve the accuracy of prediction. Contact: [email protected] Availability and Implementation: The software and data are freely available at https://github.com/ypriverol/pIR. Supplementary information: Supplementary data are available at Bioinformatics online.

scholarly journals Beta Inflated Regression Models on the Physical and Mental Health of Nigerian Stroke Survivors

2021 ◽  
Vol 7 (3) ◽  
pp. 302-312
Author(s):  
KS Oritogun ◽  
OO Oyewole
Keyword(s):  
Mental Health ◽  
Risk Factors ◽  
Blood Pressure ◽  
Health Risk ◽  
Physical Health ◽  
Regression Models ◽  
Outcome Variable ◽  
Stroke Survivors ◽  
Physical And Mental Health ◽  
Health Risk Factors

Background: Stroke is one of the major public health problems worldwide. Physical and mental health data of stroke survivors are often expressed in proportions. Therefore, the Beta Regression models family for data between zero and one will be appropriate. Objectives: To identify a suitable model and the likely risk factors of physical and mental health of stroke survivors. Method: Secondary data of stroke survivors from two tertiary health Institutions in Ogun State, Nigeria, were analysed. Inflated Beta (BEINF) and Inflated-at-one-Beta (BEINF1) models were compared using Deviance (DEV), Akaike Information Criterion (AIC) and Bayesian Information Criteria (BIC) for model selection. The model with minimum DEV, AIC and BIC was considered to be better. Results: The deviance (-86.0604,), AIC (-46.0604) and BIC (6.4391) values of the BEINF1 model for physical health and the deviance (-20.1217), AIC (19.8783) and BIC (72.3778) values of BEINF1 model for mental health were smaller than BEINF models. Therefore, BEINF1 was the better model to identify the health risk factors of stroke survivors. Age, marital status, diastolic blood pressure, disability duration and systolic blood pressure had a significant association with physical health, while BMI had a significant positive association with mental health.  Conclusion: The beta-inflated-at-one (BEINF1) model is suitable for identifying health risk factors of stroke survivors when the outcome variable is a proportion. Both demographic and clinical characteristics were significantly associated with the health of stroke survivors. This study would assist researchers in knowing the appropriate model for analysing proportion or percentage response variables.

Abstract 196: Development and Validation of Machine Learning-based Race-specific Models to Predict 10-year Risk of Heart Failure: A Multi-cohort Analysis

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Matthew W Segar ◽  
Byron Jaeger ◽  
Kershaw V Patel ◽  
Vijay Nambi ◽  
Chiadi E Ndumele ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Heart Failure ◽  
Risk Prediction ◽  
Prediction Models ◽  
External Validation ◽  
Superior Performance ◽  
Risk Models ◽  
Black And White ◽  
White Adults

Introduction: Heart failure (HF) risk and the underlying biological risk factors vary by race. Machine learning (ML) may improve race-specific HF risk prediction but this has not been fully evaluated. Methods: The study included participants from 4 cohorts (ARIC, DHS, JHS, and MESA) aged > 40 years, free of baseline HF, and with adjudicated HF event follow-up. Black adults from JHS and white adults from ARIC were used to derive race-specific ML models to predict 10-year HF risk. The ML models were externally validated in subgroups of black and white adults from ARIC (excluding JHS participants) and pooled MESA/DHS cohorts and compared to prior established HF risk scores developed in ARIC and MESA. Harrell’s C-index and Greenwood-Nam-D’Agostino chi-square were used to assess discrimination and calibration, respectively. Results: In the derivation cohorts, 288 of 4141 (7.0%) black and 391 of 8242 (4.7%) white adults developed HF over 10 years. The ML models had excellent discrimination in both black and white participants (C-indices = 0.88 and 0.89). In the external validation cohorts for black participants from ARIC (excluding JHS, N = 1072) and MESA/DHS pooled cohorts (N = 2821), 131 (12.2%) and 115 (4.1%) developed HF. The ML model had adequate calibration and demonstrated superior discrimination compared to established HF risk models (Fig A). A consistent pattern was also observed in the external validation cohorts of white participants from the MESA/DHS pooled cohorts (N=3236; 100 [3.1%] HF events) (Fig A). The most important predictors of HF in both races were NP levels. Cardiac biomarkers and glycemic parameters were most important among blacks while LV hypertrophy and prevalent CVD and traditional CV risk factors were the strongest predictors among whites (Fig B). Conclusions: Race-specific and ML-based HF risk models that integrate clinical, laboratory, and biomarker data demonstrated superior performance when compared to traditional risk prediction models.

scholarly journals Identification of risk factors for involuntary psychiatric hospitalization: using environmental socioeconomic data and methods of machine learning to improve prediction

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
O. Karasch ◽  
M. Schmitz-Buhl ◽  
R. Mennicken ◽  
J. Zielasek ◽  
E. Gouzoulis-Mayfrank
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Risk Factors ◽  
Prediction Model ◽  
Psychiatric Hospitalization ◽  
Previous Analysis ◽  
Psychiatric Hospitals ◽  
Data Set ◽  
Interaction Detection ◽  
Socioeconomic Data

Abstract Background The purpose of this study was to identify factors associated with a high risk of involuntary psychiatric in-patient hospitalization both on the individual level and on the level of mental health services and the socioeconomic environment that patients live in. Methods The present study expands on a previous analysis of the health records of 5764 cases admitted as in-patients in the four psychiatric hospitals of the Metropolitan City of Cologne, Germany, in the year 2011 (1773 cases treated under the Mental Health Act and 3991 cases treated voluntarily). Our previous analysis had included medical, sociodemographic and socioeconomic data of every case and used a machine learning-based prediction model employing chi-squared automatic interaction detection (CHAID). Our current analysis attempts to improve the previous one through (1) optimizing the machine learning procedures (use of a different type of decision-tree prediction model (Classification and Regression Trees (CART) and application of hyperparameter tuning (HT)), and (2) the addition of patients’ environmental socioeconomic data (ESED) to the data set. Results Compared to our previous analysis, model fit was improved. Main diagnoses of an organic mental or a psychotic disorder (ICD-10 groups F0 and F2), suicidal behavior upon admission, admission outside of regular service hours and absence of outpatient treatment prior to admission were confirmed as powerful predictors of detention. Particularly high risks were shown for (1) patients with an organic mental disorder, specifically if they were retired, admitted outside of regular service hours and lived in assisted housing, (2) patients with suicidal tendencies upon admission who did not suffer from an affective disorder, specifically if it was unclear whether there had been previous suicide attempts, or if the affected person lived in areas with high unemployment rates, and (3) patients with psychosis, specifically those who lived in densely built areas with a large proportion of small or one-person households. Conclusions Certain psychiatric diagnoses and suicidal tendencies are major risk factors for involuntary psychiatric hospitalization. In addition, service-related and environmental socioeconomic factors contribute to the risk for detention. Identifying modifiable risk factors and particularly vulnerable risk groups should help to develop suitable preventive measures.

scholarly journals Identification of risk factors for involuntary psychiatric hospitalization: Using environmental socioeconomic data and methods of machine learning to improve prediction

2020 ◽  
Author(s):  
Olaf Karasch ◽  
Mario Schmitz-Buhl ◽  
R Roman Mennicken ◽  
Jürgen Zielasek ◽  
Euphrosyne Gouzoulis-Mayfrank
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Risk Factors ◽  
Prediction Model ◽  
Suicide Attempts ◽  
Psychiatric Hospitalization ◽  
Previous Analysis ◽  
Data Set ◽  
Interaction Detection ◽  
Socioeconomic Data

Abstract Background: The purpose of this study was to identify factors associated with a high risk of involuntary psychiatric in-patient hospitalization both on the individual level and on the level of mental health services and the socioeconomic environment that patients live in. Methods: The present study expands on a previous analysis of the health records of 5764 cases admitted as in-patients in the four psy­chiat­ric hospitals of the Metropolitan City of Cologne, Germany, in the year 2011 (1773 cases treated under the Mental Health Act and 3991 cases trea­ted voluntarily). Our previous analysis had included medical, socio­demographic and socioeconomic data of every case and used a machine learning-based prediction model employing chi-squared automatic interaction detection (CHAID). Our current analysis attempts to improve the previous one through (1) optimizing the machine learning procedures (use of a different type of decision-tree prediction model (CART) and application of hyperparameter tuning), and (2) the addition of socioeconomic data on the patients’ environment to the data set. Results: Compared to our previous analysis, model fit was improved. Main diagnoses of an organic mental or a psychotic disorder (ICD-10 groups F0 and F2), suicidal behavior upon admission, admission outside of regular service hours and absence of outpatient treatment prior to admission were confirmed as powerful predictors of detention. Particularly high risks were shown for (1) patients with an organic mental disorder, specifically if they were retired, admitted outside of regular service hours and lived in assisted housing, (2) patients with suicidal tendencies upon admission who did not suffer from an affective disorder, specifically if it was unclear whether there had been previous suicide attempts, or if the affected person lived in areas with high unemployment rates, and (3) patients with psychosis, specifically those who lived in densely built areas with a large proportion of small or one-person households. Conclusions: Certain psychiatric diagnoses and suicidal tendencies are major risk factors for involuntary psychiatric hospitalization. In addition, service-related and environmental socioeconomic factors contribute to the risk for detention. Identifying modifiable risk factors and particularly vulnerable risk groups should help to develop suitable preventive measures.

scholarly journals Prediction of Tumor Shrinkage Pattern to Neoadjuvant Chemotherapy Using a Multiparametric MRI-Based Machine Learning Model in Patients With Breast Cancer

2021 ◽  
Vol 9 ◽  
Author(s):  
Yuhong Huang ◽  
Wenben Chen ◽  
Xiaoling Zhang ◽  
Shaofu He ◽  
Nan Shao ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Cross Validation ◽  
Learning Model ◽  
Training Dataset ◽  
Tumor Shrinkage ◽  
Clinicopathologic Characteristics ◽  
Testing Dataset ◽  
Machine Learning Model ◽  
Fold Cross Validation

Aim: After neoadjuvant chemotherapy (NACT), tumor shrinkage pattern is a more reasonable outcome to decide a possible breast-conserving surgery (BCS) than pathological complete response (pCR). The aim of this article was to establish a machine learning model combining radiomics features from multiparametric MRI (mpMRI) and clinicopathologic characteristics, for early prediction of tumor shrinkage pattern prior to NACT in breast cancer.Materials and Methods: This study included 199 patients with breast cancer who successfully completed NACT and underwent following breast surgery. For each patient, 4,198 radiomics features were extracted from the segmented 3D regions of interest (ROI) in mpMRI sequences such as T1-weighted dynamic contrast-enhanced imaging (T1-DCE), fat-suppressed T2-weighted imaging (T2WI), and apparent diffusion coefficient (ADC) map. The feature selection and supervised machine learning algorithms were used to identify the predictors correlated with tumor shrinkage pattern as follows: (1) reducing the feature dimension by using ANOVA and the least absolute shrinkage and selection operator (LASSO) with 10-fold cross-validation, (2) splitting the dataset into a training dataset and testing dataset, and constructing prediction models using 12 classification algorithms, and (3) assessing the model performance through an area under the curve (AUC), accuracy, sensitivity, and specificity. We also compared the most discriminative model in different molecular subtypes of breast cancer.Results: The Multilayer Perception (MLP) neural network achieved higher AUC and accuracy than other classifiers. The radiomics model achieved a mean AUC of 0.975 (accuracy = 0.912) on the training dataset and 0.900 (accuracy = 0.828) on the testing dataset with 30-round 6-fold cross-validation. When incorporating clinicopathologic characteristics, the mean AUC was 0.985 (accuracy = 0.930) on the training dataset and 0.939 (accuracy = 0.870) on the testing dataset. The model further achieved good AUC on the testing dataset with 30-round 5-fold cross-validation in three molecular subtypes of breast cancer as following: (1) HR+/HER2–: 0.901 (accuracy = 0.816), (2) HER2+: 0.940 (accuracy = 0.865), and (3) TN: 0.837 (accuracy = 0.811).Conclusions: It is feasible that our machine learning model combining radiomics features and clinical characteristics could provide a potential tool to predict tumor shrinkage patterns prior to NACT. Our prediction model will be valuable in guiding NACT and surgical treatment in breast cancer.

scholarly journals Psychiatric Manifestations and Associated Risk Factors among Hospitalized Patients with COVID-19 in Edo State, Nigeria.

2021 ◽  
Author(s):  
Esther O Okogbenin ◽  
Omonefe J Seb-Akahomen ◽  
Osahogie I. Edeawe ◽  
Mary Ehimigbai ◽  
Helen Eboreime ◽  
...  
Keyword(s):  
Mental Health ◽  
Risk Factors ◽  
Mental Health Problems ◽  
Health Workers ◽  
Depression And Anxiety ◽  
Cross Sectional Survey ◽  
Prevalence Of Depression ◽  
Edo State ◽  
Associated Risk Factors ◽  
The Impact

Objective The Coronavirus Disease 2019 (COVID-19) has had devastating effects globally. These effects are likely to result in mental health problems at different levels. Although studies have reported the mental health burden of the pandemic on the general population and frontline health workers, the impact of the disease on the mental health of patients in COVID-19 treatment and isolation centres have been understudied in Africa. We estimated the prevalence of depression and anxiety and associated risk factors in hospitalized persons with COVID-19. Methods A cross-sectional survey was conducted among 489 patients with COVID-19 at the three government-designated treatment and isolation centres in Edo State, Nigeria. The 9-item Patient Health Questionnaire (PHQ-9) and the Generalized Anxiety Disorder-7 (GAD-7) tool were used to assess depression and anxiety respectively. Binary logistic regression was applied to determine risk factors of depression and anxiety. Results Of the 489 participants, 49.1% and 38.0% had depressive and anxiety symptoms respectively. The prevalence of depression, anxiety, and combination of both were 16.2%, 12.9% and 9.0% respectively. Moderate-severe symptoms of COVID-19, ≥14 days in isolation, worrying about the outcome of infection and stigma increased the risk of having depression and anxiety. Additionally, being separated/divorced increased the risk of having depression and having comorbidity increased the risk of having anxiety. Conclusion A substantial proportion of our participants experienced depression, anxiety and a combination of both especially in those who had the risk factors we identified. The findings underscore the need to address these risk factors early in the course of the disease and integrate mental health interventions into COVID-19 management guidelines.

scholarly journals Development and Validation of Machine Learning-Based Race-Specific Models to Predict 10-Year Risk of Heart Failure: A Multi-Cohort Analysis

Circulation ◽  
2021 ◽  
Author(s):  
Matthew W. Segar ◽  
Byron C. Jaeger ◽  
Kershaw V. Patel ◽  
Vijay Nambi ◽  
Chiadi E. Ndumele ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Heart Failure ◽  
Risk Prediction ◽  
Prediction Models ◽  
Cohort Analysis ◽  
Specific Model ◽  
Superior Performance ◽  
Risk Models ◽  
White Adults

Background: Heart failure (HF) risk and the underlying risk factors vary by race. Traditional models for HF risk prediction treat race as a covariate in risk prediction and do not account for significant parameters such as cardiac biomarkers. Machine learning (ML) may offer advantages over traditional modeling techniques to develop race-specific HF risk prediction models and elucidate important contributors of HF development across races. Methods: We performed a retrospective analysis of four large, community cohort studies (ARIC, DHS, JHS, and MESA) with adjudicated HF events. Participants were aged >40 years and free of HF at baseline. Race-specific ML models for HF risk prediction were developed in the JHS cohort (for Black race-specific model) and White adults from ARIC (for White rate-specific model). The models included 39 candidate variables across demographic, anthropometric, medical history, laboratory, and electrocardiographic domains. The ML models were externally validated and compared with prior established traditional and non-race specific ML models in race-specific subgroups of the pooled MESA/DHS cohort and Black participants of ARIC. Harrell's C-index and Greenwood-Nam-D'Agostino chi-square tests were used to assess discrimination and calibration, respectively. Results: The ML models had excellent discrimination in the derivation cohorts for Black (N=4,141 in JHS, C-index=0.88) and White (N=7,858 in ARIC, C-index=0.89) participants. In the external validation cohorts, the race-specific ML model demonstrated adequate calibration and superior discrimination (C-indices=0.80-0.83 [for Black individuals] and 0.82 [for White individuals]) compared with established HF risk models or with non-race specific ML models derived using race as a covariate. Among the risk factors, natriuretic peptide levels were the most important predictor of HF risk across both races, followed by troponin levels in Black and EKG-based Cornell voltage in White individuals. Other key predictors of HF risk among Black individuals were glycemic parameters and socioeconomic factors. In contrast, prevalent cardiovascular (CV) disease and traditional CV risk factors were stronger predictors of HF risk in White adults. Conclusions: Race-specific and ML-based HF risk models that integrate clinical, laboratory, and biomarker data demonstrated superior performance when compared with traditional HF risk and non-race specific ML models. This approach identifies distinct race-specific contributors of HF.

Sign in / Sign up

Export Citation Format

Share Document