This case study presents a process that was iteratively developed for clinical informaticians to identify, analyse, and respond to safety events related to health information technologies (HIT) in community care settings (This research was supported by the CIHR Health Systems Impact Fellowship Program. We would also like to thank Vancouver Coastal Health for their valuable contributions.). The goal was to build capacity within a clinical informatics team to integrate patient safety into their work and to help them recognize and respond to HIT-related safety events. The technology-related safety event analysis process that was ultimately developed included three key components: 1) an internal workflow to analyse voluntarily reported HIT-related safety events using a sociotechnical model, 2) safety huddles to amplify learnings from reviewed events, and 3) a cumulative analysis of all events over time to identify and respond to patterns. A systematic approach to quickly identify and understand HIT safety concerns enables informatics teams to proactively reduce risks and prevent harm.

BACKGROUND: Accurate projections of procedural case durations are complex but critical to the planning of perioperative staffing, operating room resources, and patient communication. Nonlinear prediction models using machine learning methods may provide opportunities for hospitals to improve upon current estimates of procedure duration.
OBJECTIVE: The aim of this study was to determine whether a machine learning algorithm scalable across multiple centers could make estimations of case duration within a tolerance limit because there are substantial resources required for operating room functioning that relate to case duration.
METHODS: Deep learning, gradient boosting, and ensemble machine learning models were generated using perioperative data available at 3 distinct time points: the time of scheduling, the time of patient arrival to the operating or procedure room (primary model), and the time of surgical incision or procedure start. The primary outcome was procedure duration, defined by the time between the arrival and the departure of the patient from the procedure room. Model performance was assessed by mean absolute error (MAE), the proportion of predictions falling within 20% of the actual duration, and other standard metrics. Performance was compared with a baseline method of historical means within a linear regression model. Model features driving predictions were assessed using Shapley additive explanations values and permutation feature importance.
RESULTS: A total of 1,177,893 procedures from 13 academic and private hospitals between 2016 and 2019 were used. Across all procedures, the median procedure duration was 94 (IQR 50-167) minutes. In estimating the procedure duration, the gradient boosting machine was the best-performing model, demonstrating an MAE of 34 (SD 47) minutes, with 46% of the predictions falling within 20% of the actual duration in the test data set. This represented a statistically and clinically significant improvement in predictions compared with a baseline linear regression model (MAE 43 min; P<.001; 39% of the predictions falling within 20% of the actual duration). The most important features in model training were historical procedure duration by surgeon, the word \"free\" within the procedure text, and the time of day.
CONCLUSIONS: Nonlinear models using machine learning techniques may be used to generate high-performing, automatable, explainable, and scalable prediction models for procedure duration.

Sharing data from clinical studies can accelerate scientific progress, improve transparency, and increase the potential for innovation and collaboration. However, privacy concerns remain a barrier to data sharing. Certain concerns, such as reidentification risk, can be addressed through the application of anonymization algorithms, whereby data are altered so that it is no longer reasonably related to a person. Yet, such alterations have the potential to influence the data set\'s statistical properties, such that the privacy-utility trade-off must be considered. This has been studied in theory, but evidence based on real-world individual-level clinical data is rare, and anonymization has not broadly been adopted in clinical practice.
The goal of this study is to contribute to a better understanding of anonymization in the real world by comprehensively evaluating the privacy-utility trade-off of differently anonymized data using data and scientific results from the German Chronic Kidney Disease (GCKD) study.
The GCKD data set extracted for this study consists of 5217 records and 70 variables. A 2-step procedure was followed to determine which variables constituted reidentification risks. To capture a large portion of the risk-utility space, we decided on risk thresholds ranging from 0.02 to 1. The data were then transformed via generalization and suppression, and the anonymization process was varied using a generic and a use case-specific configuration. To assess the utility of the anonymized GCKD data, general-purpose metrics (ie, data granularity and entropy), as well as use case-specific metrics (ie, reproducibility), were applied. Reproducibility was assessed by measuring the overlap of the 95% CI lengths between anonymized and original results.
Reproducibility measured by 95% CI overlap was higher than utility obtained from general-purpose metrics. For example, granularity varied between 68.2% and 87.6%, and entropy varied between 25.5% and 46.2%, whereas the average 95% CI overlap was above 90% for all risk thresholds applied. A nonoverlapping 95% CI was detected in 6 estimates across all analyses, but the overwhelming majority of estimates exhibited an overlap over 50%. The use case-specific configuration outperformed the generic one in terms of actual utility (ie, reproducibility) at the same level of privacy.
Our results illustrate the challenges that anonymization faces when aiming to support multiple likely and possibly competing uses, while use case-specific anonymization can provide greater utility. This aspect should be taken into account when evaluating the associated costs of anonymized data and attempting to maintain sufficiently high levels of privacy for anonymized data.
German Clinical Trials Register DRKS00003971; https://drks.de/search/en/trial/DRKS00003971.
RR2-10.1093/ndt/gfr456.

BACKGROUND: Advances in health have highlighted the need to implement technologies as a fundamental part of the diagnosis, treatment, and recovery of patients at risk of or with health alterations. For this purpose, digital platforms have demonstrated their applicability in the identification of care needs. Nursing is a fundamental component in the care of patients with cardiovascular disorders and plays a crucial role in diagnosing human responses to these health conditions. Consequently, the validation of nursing diagnoses through ongoing research processes has become a necessity that can significantly impact both patients and health care professionals.
OBJECTIVE: We aimed to describe the process of developing a mobile app to validate the nursing diagnosis \"intolerance to physical activity\" in patients with acute myocardial infarction.
METHODS: We describe the development and pilot-testing of a mobile system to support data collection for validating the nursing diagnosis of activity intolerance. This was a descriptive study conducted with 11 adults (aged ≥18 years) who attended a health institution for highly complex needs with a suspected diagnosis of coronary syndrome between August and September 2019 in Floridablanca, Colombia. An app for the clinical validation of activity intolerance (North American Nursing Diagnosis Association [NANDA] code 00092) in patients with acute coronary syndrome was developed in two steps: (1) operationalization of the nursing diagnosis and (2) the app development process, which included an evaluation of the initial requirements, development and digitization of the forms, and a pilot test. The agreement level between the 2 evaluating nurses was evaluated with the κ index.
RESULTS: We developed a form that included sociodemographic data, hospital admission data, medical history, current pharmacological treatment, and thrombolysis in myocardial infarction risk score (TIMI-RS) and GRACE (Global Registry of Acute Coronary Events) scores. To identify the defining characteristics, we included official guidelines, physiological measurements, and scales such as the Piper fatigue scale and Borg scale. Participants in the pilot test (n=11) had an average age of 63.2 (SD 4.0) years and were 82% (9/11) men; 18% (2/11) had incomplete primary schooling. The agreement between the evaluators was approximately 80% for most of the defining characteristics. The most prevalent characteristics were exercise discomfort (10/11, 91%), weakness (7/11, 64%), dyspnea (3/11, 27%), abnormal heart rate in response to exercise (2/10, 20%), electrocardiogram abnormalities (1/10, 9%), and abnormal blood pressure in response to activity (1/10, 10%).
CONCLUSIONS: We developed a mobile app for validating the diagnosis of \"activity intolerance.\" Its use will guarantee not only optimal data collection, minimizing errors to perform validation, but will also allow the identification of individual care needs.

OBJECTIVE: The study aimed to characterize the experiences of primary caregivers of children with medical complexity (CMC) in engaging with other members of the child\'s caregiving network, thereby informing the design of health information technology (IT) for the caregiving network. Caregiving networks include friends, family, community members, and other trusted individuals who provide resources, information, health, or childcare.
METHODS: We performed a secondary analysis of two qualitative studies. Primary studies conducted semi-structured interviews (n = 50) with family caregivers of CMC. Interviews were held in the Midwest (n = 30) and the mid-Atlantic region (n = 20). Interviews were transcribed verbatim for thematic analysis. Emergent themes were mapped to implications for the design of future health IT.
RESULTS: Thematic analysis identified 8 themes characterizing a wide range of primary caregivers\' experiences in constructing, managing, and ensuring high-quality care delivery across the caregiving network.
CONCLUSIONS: Findings evidence a critical need to create flexible and customizable tools designed to support hiring/training processes, coordinating daily care across the caregiving network, communicating changing needs and care updates across the caregiving network, and creating contingency plans for instances where caregivers are unavailable to provide care to the CMC. Informaticists should additionally design accessible platforms that allow primary caregivers to connect with and learn from other caregivers while minimizing exposure to sensitive or emotional content as indicated by the user.
CONCLUSIONS: This article contributes to the design of health IT for CMC caregiving networks by uncovering previously underrecognized needs and experiences of CMC primary caregivers and drawing direct connections to design implications.

Advanced technology innovations allow cost-effective, high-throughput profiling of biological systems. It enabled genome sequencing in days using advanced technologies (e.g., next-generation sequencing, microarrays, and mass spectrometry). Since technology has been developed, massive biological data (e.g., genomics, proteomics) has been produced cheaply, allowing the \"big data\" era to create new opportunities to solve medical and biological complications in many disciplines-preventive medicine, biology, Personalized Medicine, gene sequencing, healthcare, and industry. Computational biology and bioinformatics are interdisciplinary fields that develop and apply computational methods (e.g., analytical methods, mathematical modeling, and simulation) to analyze large collections of biological data, such as genetic sequences, cell populations, or protein samples, to make new predictions or discover new biology. Biological data storage, mining, and analysis have challenges because data is much more heterogeneous. In this study, the big data resources of genomics, proteomics, and metabolomics have been explored to solve biological problems using big data analysis approaches. The goal is to build a network of relationship-based gene-disease associations to prioritize phenotypes common to epilepsy and seizure disease. Through network analysis, The 10 seed genes, 22 associated genes, 132 microRNAs, and 38 transcription factors have been identified that have a direct effect on all forms of epilepsy and seizures. The majority of seed genes, according to the results of a functional analysis of seed genes, are involved in the acetylcholine-gated channel complex (10%) and the heterotrimeric G-protein complex (10%) pathways related to cellular components, followed by a role in the regulation of action potential (20%) and positive regulation of vascular endothelial growth factor production (20%) in Epilepsy and Seizures pathways related to biological processes. This study might provide insight into the workings of the disease and shows the importance of continued research into epilepsy and other conditions that can trigger seizure activity.

BACKGROUND: Over the last decade, the frequency and size of cyberattacks in the health care industry have increased, ranging from breaches of processes or networks to encryption of files that restrict access to data. These attacks may have multiple consequences for patient safety, as they can, for example, target electronic health records, access to critical information, and support for critical systems, thereby causing delays in hospital activities. The effects of cybersecurity breaches are not only a threat to patients\' lives but also have financial consequences due to causing inactivity in health care systems. However, publicly available information on these incidents quantifying their impact is scarce.
OBJECTIVE: We aim, while using public domain data from Portugal, to (1) identify data breaches in the public national health system since 2017 and (2) measure the economic impact using a hypothesized scenario as a case study.
METHODS: We retrieved data from multiple national and local media sources on cybersecurity from 2017 until 2022 and built a timeline of attacks. In the absence of public information on cyberattacks, reported drops in activity were estimated using a hypothesized scenario for affected resources and percentages and duration of inactivity. Only direct costs were considered for estimates. Data for estimates were produced based on planned activity through the hospital contract program. We use sensitivity analysis to illustrate how a midlevel ransomware attack might impact health institutions\' daily costs (inferring a potential range of values based on assumptions). Given the heterogeneity of our included parameters, we also provide a tool for users to distinguish such impacts of different attacks on institutions according to different contract programs, served population size, and proportion of inactivity.
RESULTS: From 2017 to 2022, we were able to identify 6 incidents in Portuguese public hospitals using public domain data (there was 1 incident each year and 2 in 2018). Financial impacts were obtained from a cost point of view, where estimated values have a minimum-to-maximum range of €115,882.96 to €2,317,659.11 (a currency exchange rate of €1=US $1.0233 is applicable). Costs of this range and magnitude were inferred assuming different percentages of affected resources and with different numbers of working days while considering the costs of external consultation, hospitalization, and use of in- and outpatient clinics and emergency rooms, for a maximum of 5 working days.
CONCLUSIONS: To enhance cybersecurity capabilities at hospitals, it is important to provide robust information to support decision-making. Our study provides valuable information and preliminary insights that can help health care organizations better understand the costs and risks associated with cyber threats and improve their cybersecurity strategies. Additionally, it demonstrates the importance of adopting effective preventive and reactive strategies, such as contingency plans, as well as enhanced investment in improving cybersecurity capabilities in this critical area while aiming to achieve cyber-resilience.

Medical Informatics brings methods and solutions that could support reducing healthcare\'s ecological footprint. Initial frameworks for Green Medical Informatics solutions are available, however these do not address organizational and human factors. Including these factors in evaluation or analysis of (technical) interventions aimed at making healthcare more sustainable, is essential for improving usability as well as effectiveness of these interventions. Interviews with healthcare professionals from Dutch hospitals led to preliminary insights into which organizational and human factors impact the implementation and adoption of sustainable solutions. Results indicate that forming multi-disciplinary teams is considered an important factor for realizing intended outcomes in terms of reducing carbon emissions and waste. Some other key factors mentioned are formalizing tasks, allocating budget and time, creating awareness and changing protocols to promote sustainable diagnosis and treatment procedures.

Background This study aimed to evaluate the efficacy of ChatGPT, an advanced natural language processing model, in adapting and synthesizing clinical guidelines for diabetic ketoacidosis (DKA) by comparing and contrasting different guideline sources. Methodology We employed a comprehensive comparison approach and examined three reputable guideline sources: Diabetes Canada Clinical Practice Guidelines Expert Committee (2018), Emergency Management of Hyperglycaemia in Primary Care, and Joint British Diabetes Societies (JBDS) 02 The Management of Diabetic Ketoacidosis in Adults. Data extraction focused on diagnostic criteria, risk factors, signs and symptoms, investigations, and treatment recommendations. We compared the synthesized guidelines generated by ChatGPT and identified any misreporting or non-reporting errors. Results ChatGPT was capable of generating a comprehensive table comparing the guidelines. However, multiple recurrent errors, including misreporting and non-reporting errors, were identified, rendering the results unreliable. Additionally, inconsistencies were observed in the repeated reporting of data. The study highlights the limitations of using ChatGPT for the adaptation of clinical guidelines without expert human intervention. Conclusions Although ChatGPT demonstrates the potential for the synthesis of clinical guidelines, the presence of multiple recurrent errors and inconsistencies underscores the need for expert human intervention and validation. Future research should focus on improving the accuracy and reliability of ChatGPT, as well as exploring its potential applications in other areas of clinical practice and guideline development.

BACKGROUND: The importance of the health information system faces multiple challenges such as supply, acceptance, and pressure from other professions in Ethiopia. Work-related challenges might cause low professional satisfaction and hinder service provision. There is a paucity of evidence for policy decisions to improve these challenges. Therefore, this study aims to assess Health Informatics professional satisfaction in the Ethiopian health system and associated factors to provide evidence for future improvements.
METHODS: We conducted an institutions-based cross-sectional study on health informatics professionals in three zones in Southern Ethiopia in 2020. We used a simple random sampling technique to select 215 participants. The local health officials were contacted regarding the research questions, and letters of permission were collected for data collection.
RESULTS: Out of 211(98%) Health Informatics professionals who accepted the interview, 50.8% (95%CI: 47.74%-53.86%) were satisfied. Age (AOR = 0.57; 95% CI: 0.53, 0.95), experience (AOR = 5; 95% CI: 1.50, 19.30), working time (AOR = 1.35; 95% CI: 1.10, 1.70), working as HMIS officers (AOR 2.30; 95% CI: 3.80, 13), single marital status (AOR = 9.60; 95% CI: 2.88, 32), and urban residence (AOR = 8.10; 95% CI: 2.95, 22) were some of the associated factors.
CONCLUSIONS: We found low satisfaction among health informatics professionals compared to other studies. It was suggested that the responsible bodies must keep experienced professionals and reduce pressure from other professions through panel discussions. Work departments and working hours need consideration, as they are the determinants of satisfaction. Improving educational opportunities and career structure is the potential implication area.