Search

Today, almost every psychiatric care institution registers information concerning the care they provide in an electronic health record (EHR). By analyzing these health care data with innovative and advanced techniques, they can be an important source of new knowledge in the near future, and thereby contribute to improving psychiatric care.To investigate how data from EHRs can provide relevant knowledge and insights for psychiatric care.We designed and discussed solutions for some technical, organizational and ethical barriers surrounding unlocking health care data, in order to make analysis possible. We then analyzed the obtained health care data using techniques from knowledge discovery, the process in which new and useful information is extracted from data. We used techniques from data visualization, machine learning and natural language processing, among others, to demonstrate which types of results can be achieved.Our approach showed that it is possible to find new and interesting insights that are hidden in EHRs on an aggregated level, in collaboration with healthcare professionals and patients. In particular we showed how the risk of violent behavior can effectively and accurately be assessed based on clinical text in the EHR.After addressing some of the important challenges surrounding analyzing EHR data, learning from data from EHRs is a new and interesting approach with clear potential for improving psychiatric care.

Obstructive sleep apnea (OSA) is a prevalent and multifaceted disease. To date, the presence and severity of objectively identified comorbidities and their association with specific OSA phenotypes, CPAP adherence, and survival remain to be elucidated. The aim of this study is to cluster patients with OSA based on 10 clinically important objectively identified comorbidities, and to characterize the comorbidity clusters in terms of clinical and polysomnographic characteristics, CPAP adherence, and survival.Seven hundred ten consecutive patients starting CPAP for moderate-to-severe OSA were included. Comorbidities were based on generally accepted cutoffs identified in the peer-reviewed literature. Self-organizing maps were used to order patients based on presence and severity of their comorbidities and to generate clusters.The majority of patients were men (80%). They were generally middle-aged (52 years) and obese (BMI: 31.5 kg/mComorbidity prevalence in patients with OSA is high, and different comorbidity clusters, demonstrating differences in cardiovascular risk, CPAP adherence, and survival, can be identified. These results further substantiate the need for a comprehensive assessment of patients with OSA beyond the AHI.

Background: Chronic obstructive pulmonary disease ( COPD) is associated with a significantly impaired health status and lost work productivity across all degrees of airflow limitation. The current study investigated whether an impaired health status is better represented by the recommended COPD Assessment Test (CAT) cut-point of I0 points, or the 95(th) percentile of the CAT score in a non-COPD population. Additionally, the impact of COPD on health status in a Dutch population, after stratification for work status, was measured. Methods: Demographics, clinical characteristics, post-bronchodilator spirometry, and CAT were assessed in subjects from the Longitudinal Aging Study Amsterdam ( LASA), a large Dutch population-based study. Normative values for the CAT score were described by percentiles using the mean, standard deviation, median and range. Results: In total, 8I0 COPD and non-COPD subjects (50.4% male, mean age 60.5 +/- 2.9 years) were analysed. Significant differences were observed in CAT scores between non-COPD and COPD subjects (6.7 +/- 5.2 vs. 9.5 +/- 5.9, p = I0 cut-point (50.0%) and applying the 95th percentile of CAT in non-COPD subjects (> I8 cut-point; 7.6%). Higher CAT scores were seen in working COPD patients compared with working non-COPD subjects (9.3 +/- 5.2 vs. 6.0 +/- 4.6, p I8 points to indicate an impaired health status in COPD. This would imply an adaptation of the current GOLD classification of the disease.

The association between physical activity and risk of hospitalisation for chronic obstructive pulmonary disease (COPD) is not yet clear. We conducted a systematic review of the literature to fill this gap in knowledge. Eight electronic databases were searched using a selection of controlled vocabulary and keywords. The search resulted in more than 1000 initial hits, of which four met the inclusion criteria. For each identified study, relevant data were extracted and appraised. The results indicate that less physically active patients with COPD were more likely to be admitted to hospital. Consistent with a lower level of physical activity, the patients tended to have shorter walking times as well as spend fewer hours outdoors. In multivariate regression analysis, self-reported physical activity predicted hospitalisation in patients from the general population and re-hospitalisation in patients admitted for an acute exacerbation. The evidence for an association between physical activity and risk of hospitalisation for COPD is limited to a few prospective cohort studies. More research is needed to quantify the degree of physical activity associated with reduced risk of hospitalisation.