Objectives To investigate the potential value of combining information from electronic health records from Dutch general practitioners (GPs) and preventive youth healthcare professionals (PYHPs) in... Show moreObjectives To investigate the potential value of combining information from electronic health records from Dutch general practitioners (GPs) and preventive youth healthcare professionals (PYHPs) in predicting child mental health problems (MHPs). Design Population-based retrospective cohort study. Setting General practice, children who were registered with 76 general practice centres from the Leiden University Medical Centre (LUMC) primary care academic network Extramural LUMC Academic Network in the Leiden area, the Netherlands. For the included children we obtained data regarding a child's healthy development from preventive youth healthcare. Participants 48 256 children aged 0-19 years old who were registered with participating GPs between 2007 and 2017 and who also had data available from PYHPs from the period 2010-2015. Children with MHPs before 2007 were excluded (n=3415). Primary outcome First MHPs based on GP data. Results In 51% of the children who had MHPs according to GPs, PYPHs also had concerns for MHPs. In 31% of the children who had no MHPs according to GPs, PYHPs had recorded concerns for MHPs. Combining their information did not result in better performing prediction models than the models based on GP data alone (c-statistics ranging from 0.62 to 0.64). Important determinants of identification of MHPs by PYHPs 1 year later were concerns from PHYPs about MHPs, borderline or increased problem scores on mental health screening tools, life events, family history of MHPs and an extra visit to preventive youth healthcare. Conclusions Although the use of combined information from PYHPs and GPs did not improve prediction of MHPs compared with the use of GP data alone, this study showed the feasibility of analysing a combined dataset from different healthcare providers what has the potential to inform future studies aimed at improving child MHP identification. Show less
This thesis aims to improve the early identification of mental healthproblems (MHPs) in children by developing a prediction model for MHPs inchildren based on readily available information from... Show moreThis thesis aims to improve the early identification of mental healthproblems (MHPs) in children by developing a prediction model for MHPs inchildren based on readily available information from electronic patient recordsfrom general practice.The prediction models for child MHPs, based on the data from the electronichealth records of general practitioners (GPs), have not yet performed wellenough to be used safely in daily practice. A number of relevant predictivecharacteristics have been identified: characteristics such as physicalcomplaints (e.g. abdominal pain or headache) and characteristics related tohigher health care use (e.g. more than two GP visits or a laboratoryexamination in the previous year) were age-independent predictors of MHPs.Awareness of (a combination of) these characteristics can help GPs to identifyMHPs at an early stage.To investigate whether merging information from preventive youth healthcare(PYH) and GPs in one algorithm can improve the identification of MHPs, wecombined information from the electronic files of PYH and GPs. However, themodels based on these combined data did not outperform the models based on GPdata alone. Several individual characteristics measured in PYH turned out to bepredictors for MHPs in general practice. Show less
Background and Objectives: Early identification of child mental health problems (MHPs) is important to provide adequate, timely treatment. Dutch preventive youth healthcare monitors all aspects of... Show moreBackground and Objectives: Early identification of child mental health problems (MHPs) is important to provide adequate, timely treatment. Dutch preventive youth healthcare monitors all aspects of a child's healthy development. We explored the usefulness of their electronic health records (EHRs) in scientific research and aimed to develop prediction models for child MHPs.Methods: Population-based cohort study with anonymously extracted electronic healthcare data from preventive youth healthcare centers in the Leiden area, the Netherlands, from the period 2005-2015. Data was analyzed with respect to its continuity, percentage of cases and completeness. Logistic regression analyses were conducted to develop prediction models for the risk of a first recorded concern for MHPs in the next scheduled visit at age 3/4, 5/6, 10/11, and 13/14 years.Results: We included 26,492 children. The continuity of the data was low and the number of concerns for MHPs varied greatly. A large number of determinants had missing data for over 80% of the children. The discriminatory performance of the prediction models were poor.Conclusions: This is the first study exploring the usefulness of EHRs from Dutch preventive youth healthcare in research, especially in predicting child MHPs. We found the usefulness of the data to be limited and the performance of the developed prediction models was poor. When data quality can be improved, e.g., by facilitating accurate recording, or by data enrichment from other available sources, the analysis of EHRs might be helpful for better identification of child MHPs. Show less
This study proposes a framework for mining temporal patterns from Electronic Medical Records. A new scoring scheme based on the Wilson interval is provided to obtain frequent and predictive... Show moreThis study proposes a framework for mining temporal patterns from Electronic Medical Records. A new scoring scheme based on the Wilson interval is provided to obtain frequent and predictive patterns, as well as to accelerate the mining process by reducing the number of patterns mined. This is combined with a case study using data from general practices in the Netherlands to identify children at risk of suffering from mental disorders. To develop an accurate model, feature engineering methods such as one hot encoding and frequency transformation are proposed, and the pattern selection is tailored to this type of clinical data. Six machine learning models are trained on five age groups, with XGBoost achieving the highest AUC values (0.75-0.79) with sensitivity and specificity above 0.7 and 0.6 respectively. An improvement is demonstrated by the models learning from patterns in addition to non-temporal features. Show less