Protecting Personal Health Data through Privacy Awareness

Digital health data is important to keep secure, and patients' perception around the privacy of it is essential to the development of digital health records. In this paper we present people's perceptions of the communication of data protection, in relation to their personal health data and the access to it; we focused particularly on people with chronic or long-term illness. Based on their use of personally accessible health records, we inquired into their explicit perception of security and sense of data privacy in relation to their health data. Our goal was to provide insights and guidelines to designers and developers on the communication of data protection in health records in an accessible way for the users. We analyzed their approach to and experience with their own health care records and describe the details of their challenges. A conceptual framework called "Privacy Awareness' was developed from the findings and reflects the perspectives of the users. The conceptual framework forms the basis of a proposal for design guidelines for Digital Health Record systems, which aim to address, facilitate and improve the users' awareness of the protection of their online health data.

Artificial intelligence, machine learning, and deep learning for clinical outcome prediction

AI is a broad concept, grouping initiatives that use a computer to perform tasks that would usually require a human to complete. AI methods are well suited to predict clinical outcomes. In practice, AI methods can be thought of as functions that learn the outcomes accompanying standardized input data to produce accurate outcome predictions when trialed with new data. Current methods for cleaning, creating, accessing, extracting, augmenting, and representing data for training AI clinical prediction models are well defined. The use of AI to predict clinical outcomes is a dynamic and rapidly evolving arena, with new methods and applications emerging. Extraction or accession of electronic health care records and combining these with patient genetic data is an area of present attention, with tremendous potential for future growth. Machine learning approaches, including decision tree methods of Random Forest and XGBoost, and deep learning techniques including deep multi-layer and recurrent neural networks, afford unique capabilities to accurately create predictions from high dimensional, multimodal data. Furthermore, AI methods are increasing our ability to accurately predict clinical outcomes that previously were difficult to model, including time-dependent and multi-class outcomes. Barriers to robust AI-based clinical outcome model deployment include changing AI product development interfaces, the specificity of regulation requirements, and limitations in ensuring model interpretability, generalizability, and adaptability over time.

Delayed Tuberculosis Diagnosis in a Low Incidence Country and its Effect on Cost of Care

Background Tuberculosis elimination (TB) is a global priority that requires high-quality timely care to be achieved. In low TB incidence countries such as Ireland, delayed diagnosis is common. Despite cost being central to policy making, it is not known if delayed care affects care cost among TB patients in a low-incidence setting. Methods Health care records of patients with signs and symptoms of TB evaluated by a tertiary service in Ireland between July 1st 2018 and December 31st 2019 were reviewed to measure and determine predictors of patient-related delays, health care-provider related delay and the cost of TB care. Benchmarks against which the outcomes were compared were derived from the literature. Results Thirty-seven patients were diagnosed with TB and 51% (19/37) had pulmonary TB (PTB). The median patient-related delay was 60 days among those with PTB, greater than the benchmark derived from the literature (38 days). The median health care provider-related delay among patients with PTB was 16 days and, although similar to the benchmark (median 22 days, minimum 11 days, maximum 36 days) could be improved. The health care-provider related delay among patients with EPTB was 66 days, greater than the benchmark (42 days). The cost of care was €8298, and while similar to that reported in the literature (median €9,319, minimum €6,486, maximum €14,750) could be improved. Patient-related delay among those with PTB predicted care costs. Conclusion Patient-related and health care-related delays in TB diagnosis in Ireland must be reduced. Initiatives to do so should be resourced.

Associations between ambient air pollutants and hospital admissions: more needs to be done

Deaths from air pollution in the UK are higher by a factor of 10 than from car crashes, 7 for drug-related deaths and 52 for murders, and yet awareness seems to be lacking in local government. We conducted an 18-year retrospective cohort study using routinely collected health care records from Ninewells Hospital, Dundee, and Perth Royal Infirmary, in Tayside, Scotland, UK, from 2000 to 2017. Hospitalisation events and deaths were linked to daily nitric oxides (NOX, NO, NO2), and particulate matter 10 (PM10) levels extracted from publicly available data over this same time period. Distributed lag models were used to estimate risk ratios for hospitalisation and mortality, adjusting for temperature, humidity, day of the week, month and public holiday. Nitric oxides and PM10 were associated with an increased risk of all hospital admissions and cardiovascular (CV) admissions on day of exposure to pollutant. This study shows a significant increase in all cause and CV hospital admissions, on high pollution days in Tayside, Scotland.

Finding Potential Adverse Events in the Unstructured Text of Electronic Health Care Records: Development of the Shakespeare Method

Background Big data tools provide opportunities to monitor adverse events (patient harm associated with medical care) (AEs) in the unstructured text of electronic health care records (EHRs). Writers may explicitly state an apparent association between treatment and adverse outcome (“attributed”) or state the simple treatment and outcome without an association (“unattributed”). Many methods for finding AEs in text rely on predefining possible AEs before searching for prespecified words and phrases or manual labeling (standardization) by investigators. We developed a method to identify possible AEs, even if unknown or unattributed, without any prespecifications or standardization of notes. Our method was inspired by word-frequency analysis methods used to uncover the true authorship of disputed works credited to William Shakespeare. We chose two use cases, “transfusion” and “time-based.” Transfusion was chosen because new transfusion AE types were becoming recognized during the study data period; therefore, we anticipated an opportunity to find unattributed potential AEs (PAEs) in the notes. With the time-based case, we wanted to simulate near real-time surveillance. We chose time periods in the hope of detecting PAEs due to contaminated heparin from mid-2007 to mid-2008 that were announced in early 2008. We hypothesized that the prevalence of contaminated heparin may have been widespread enough to manifest in EHRs through symptoms related to heparin AEs, independent of clinicians’ documentation of attributed AEs. Objective We aimed to develop a new method to identify attributed and unattributed PAEs using the unstructured text of EHRs. Methods We used EHRs for adult critical care admissions at a major teaching hospital (2001-2012). For each case, we formed a group of interest and a comparison group. We concatenated the text notes for each admission into one document sorted by date, and deleted replicate sentences and lists. We identified statistically significant words in the group of interest versus the comparison group. Documents in the group of interest were filtered to those words, followed by topic modeling on the filtered documents to produce topics. For each topic, the three documents with the maximum topic scores were manually reviewed to identify PAEs. Results Topics centered around medical conditions that were unique to or more common in the group of interest, including PAEs. In each use case, most PAEs were unattributed in the notes. Among the transfusion PAEs was unattributed evidence of transfusion-associated cardiac overload and transfusion-related acute lung injury. Some of the PAEs from mid-2007 to mid-2008 were increased unattributed events consistent with AEs related to heparin contamination. Conclusions The Shakespeare method could be a useful supplement to AE reporting and surveillance of structured EHR data. Future improvements should include automation of the manual review process.