Construction and validation of machine learning algorithm for predicting depression among home-quarantined individuals during the large-scale COVID-19 outbreak: based on Adaboost model

OBJECTIVES

COVID-19 epidemics often lead to elevated levels of depression. To accurately identify and predict depression levels in home-quarantined individuals during a COVID-19 epidemic, this study constructed a depression prediction model based on multiple machine learning algorithms and validated its effectiveness.

METHODS

A cross-sectional method was used to examine the depression status of individuals quarantined at home during the epidemic via the network. Characteristics included variables on sociodemographics, COVID-19 and its prevention and control measures, impact on life, work, health and economy after the city was sealed off, and PHQ-9 scale scores. The home-quarantined subjects were randomly divided into training set and validation set according to the ratio of 7:3, and the performance of different machine learning models were compared by 10-fold cross-validation, and the model algorithm with the best performance was selected from 15 models to construct and validate the depression prediction model for home-quarantined subjects. The validity of different models was compared based on accuracy, precision, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC), and the best model suitable for the data framework of this study was identified.

RESULTS

The prevalence of depression among home-quarantined individuals during the epidemic was 31.66% (202/638), and the constructed Adaboost depression prediction model had an ACC of 0.7917, an accuracy of 0.7180, and an AUC of 0.7803, which was better than the other 15 models on the combination of various performance measures. In the validation sets, the AUC was greater than 0.83.

CONCLUSIONS

The Adaboost machine learning algorithm developed in this study can be used to construct a depression prediction model for home-quarantined individuals that has better machine learning performance, as well as high effectiveness, robustness, and generalizability.

[Research on adolescent depression associated with parental depression]

At the crossroads of a global pandemic, here and there where public discourse misuses the concepts of depression, research has begun on a public health issue, that of adolescent depression. The Adodesp study (adolescent depression associated with parental depression) aims to study the interest of a preventive identification of adolescent depression, based on that of parental figures, while evaluating the orientation towards a care system articulated between primary care and mental health devices. To date, this study has included 42 adolescents based on the identification of 30 depressed parents. Preliminary results show that 45% of adolescents are depressed and support the need for systematic identification of adolescent depression in children of depressed parents. They also underline the difficulties and pitfalls of this identification by general practitioners and conclude that it would be useful to strengthen the link between primary care and mental health services.

Nine Forward-Backward Translations of the Hopkins Symptom Checklist-25 With Cultural Checks

Introduction: The Hopkins Symptom Checklist-25 (HSCL-25) is an effective, reliable, and ergonomic tool that can be used for depression diagnosis and monitoring in daily practice. To allow its broad use by family practice physicians (FPs), it was translated from English into nine European languages (Greek, Polish, Bulgarian, Croatian, Catalan, Galician, Spanish, Italian, and French) and the translation homogeneity was confirmed. This study describes this process. Methods: First, two translators (an academic translator and an FP researcher) were recruited for the forward translation (FT). A panel of English-speaking FPs that included at least 15 experts (researchers, teachers, and practitioners) was organized in each country to finalize the FT using a Delphi procedure. Results: One or two Delphi procedure rounds were sufficient for each translation. Then, a different translator, who did not know the original version of the HSCL-25, performed a backward translation in English. An expert panel of linguists compared the two English versions. Differences were listed and a multicultural consensus group determined whether they were due to linguistic problems or to cultural differences. All versions underwent cultural check. Conclusion: All nine translations were finalized without altering the original meaning.