Healthcare Informatics Research最新文献

Objectives: A substantial portion of the data contained in Electronic Health Records (EHR) is unstructured, often appearing as free text. This format restricts its potential utility in clinical decision-making. Named entity recognition (NER) methods address the challenge of extracting pertinent information from unstructured text. The aim of this study was to outline the current NER methods and trace their evolution from 2011 to 2022.

Methods: We conducted a methodological literature review of NER methods, with a focus on distinguishing the classification models, the types of tagging systems, and the languages employed in various corpora.

Results: Several methods have been documented for automatically extracting relevant information from EHRs using natural language processing techniques such as NER and relation extraction (RE). These methods can automatically extract concepts, events, attributes, and other data, as well as the relationships between them. Most NER studies conducted thus far have utilized corpora in English or Chinese. Additionally, the bidirectional encoder representation from transformers using the BIO tagging system architecture is the most frequently reported classification scheme. We discovered a limited number of papers on the implementation of NER or RE tasks in EHRs within a specific clinical domain.

Conclusions: EHRs play a pivotal role in gathering clinical information and could serve as the primary source for automated clinical decision support systems. However, the creation of new corpora from EHRs in specific clinical domains is essential to facilitate the swift development of NER and RE models applied to EHRs for use in clinical practice.

Objectives: Artificial intelligence (AI) technologies are developing very rapidly in the medical field, but have yet to be actively used in actual clinical settings. Ensuring reliability is essential to disseminating technologies, necessitating a wide range of research and subsequent social consensus on requirements for trustworthy AI.

Methods: This review divided the requirements for trustworthy medical AI into explainability, fairness, privacy protection, and robustness, investigated research trends in the literature on AI in healthcare, and explored the criteria for trustworthy AI in the medical field.

Results: Explainability provides a basis for determining whether healthcare providers would refer to the output of an AI model, which requires the further development of explainable AI technology, evaluation methods, and user interfaces. For AI fairness, the primary task is to identify evaluation metrics optimized for the medical field. As for privacy and robustness, further development of technologies is needed, especially in defending training data or AI algorithms against adversarial attacks.

Conclusions: In the future, detailed standards need to be established according to the issues that medical AI would solve or the clinical field where medical AI would be used. Furthermore, these criteria should be reflected in AI-related regulations, such as AI development guidelines and approval processes for medical devices.

Objectives: Distributed research networks (DRNs) facilitate multicenter research by enabling the use of multicenter data; therefore, they are increasingly utilized in healthcare fields. Despite the numerous advantages of DRNs, it is crucial to understand researchers' acceptance of these networks to ensure their effective application in multicenter research. In this study, we sought to identify the factors influencing the adoption of DRNs among researchers in Korea.

Methods: We used snowball sampling to collect data from 149 researchers between July 7 and August 28, 2020. Five factors were used to formulate the hypotheses and research model: data accessibility, usefulness, ease of use, data security risk, and intention to use DRNs. We applied a structural equation model to identify relationships within the research model.

Results: Data accessibility and data security were critical to the acceptance and use of DRNs. The usefulness of DRNs partially mediated the relationship between data accessibility and the intention to use DRNs. Interestingly, ease of use did not influence the intention to use DRNs, but it was affected by data accessibility. Furthermore, ease of use impacted the perceived usefulness of DRNs.

Conclusions: This study highlighted major factors that can promote the broader adoption and utilization of DRNs. Consequently, these findings can contribute to the expansion of active multicenter research using DRNs in the field of healthcare research.

Objectives: Enhancing critical care efficacy involves evaluating and improving system functioning. Benchmarking, a retrospective comparison of results against standards, aids risk-adjusted assessment and helps healthcare providers identify areas for improvement based on observed and predicted outcomes. The last two decades have seen the development of several models using machine learning (ML) for clinical outcome prediction. ML is a field of artificial intelligence focused on creating algorithms that enable computers to learn from and make predictions or decisions based on data. This narrative review centers on key discoveries and outcomes to aid clinicians and researchers in selecting the optimal methodology for critical care benchmarking using ML.

Methods: We used PubMed to search the literature from 2003 to 2023 regarding predictive models utilizing ML for mortality (592 articles), length of stay (143 articles), or mechanical ventilation (195 articles). We supplemented the PubMed search with Google Scholar, making sure relevant articles were included. Given the narrative style, papers in the cohort were manually curated for a comprehensive reader perspective.

Results: Our report presents comparative results for benchmarked outcomes and emphasizes advancements in feature types, preprocessing, model selection, and validation. It showcases instances where ML effectively tackled critical care outcome-prediction challenges, including nonlinear relationships, class imbalances, missing data, and documentation variability, leading to enhanced results.

Conclusions: Although ML has provided novel tools to improve the benchmarking of critical care outcomes, areas that require further research include class imbalance, fairness, improved calibration, generalizability, and long-term validation of published models.

Objectives: This article explores the secondary use provisions of the European Health Data Space (EHDS), proposed by the European Commission in May 2022, and offers policy recommendations for South Korea.

Methods: The authors analyzed the texts of the EHDS proposal and other documents published by the European Union, as well as surveyed the relevant literature.

Results: The EHDS proposal seeks to create new patient rights over electronic health data collected and used for primary care; and establish a data sharing system for the re-use of electronic health data for secondary purposes, including research, the provision of personalized healthcare, and developing healthcare artificial intelligence (AI) applications. These provisions envisage requiring both private and public data holders to share certain types of electronic health data on a mandatory basis with third parties. New government bodies, called health data access bodies, would review data access applications and issue data permits.

Conclusions: The overarching aim of the EHDS proposal is to make electronic health data, which are currently held in the hands of a small number of organizations, available for re-use by third parties to stimulate innovation and research. While it will be very challenging for South Korea to adopt a similar scheme and require private entities to share their proprietary data with third parties, the South Korean government should consider making at least health data collected through publicly funded research more readily available for secondary use.

Objectives: The objective of this study was to develop and validate a multicenter-based, multi-model, time-series deep learning model for predicting drug-induced liver injury (DILI) in patients taking angiotensin receptor blockers (ARBs). The study leveraged a national-level multicenter approach, utilizing electronic health records (EHRs) from six hospitals in Korea.

Methods: A retrospective cohort analysis was conducted using EHRs from six hospitals in Korea, comprising a total of 10,852 patients whose data were converted to the Common Data Model. The study assessed the incidence rate of DILI among patients taking ARBs and compared it to a control group. Temporal patterns of important variables were analyzed using an interpretable timeseries model.

Results: The overall incidence rate of DILI among patients taking ARBs was found to be 1.09%. The incidence rates varied for each specific ARB drug and institution, with valsartan having the highest rate (1.24%) and olmesartan having the lowest rate (0.83%). The DILI prediction models showed varying performance, measured by the average area under the receiver operating characteristic curve, with telmisartan (0.93), losartan (0.92), and irbesartan (0.90) exhibiting higher classification performance. The aggregated attention scores from the models highlighted the importance of variables such as hematocrit, albumin, prothrombin time, and lymphocytes in predicting DILI.

Conclusions: Implementing a multicenter-based timeseries classification model provided evidence that could be valuable to clinicians regarding temporal patterns associated with DILI in ARB users. This information supports informed decisions regarding appropriate drug use and treatment strategies.

Objectives: Twitter has been used to express a diverse range of public opinions about cannabis legalization in Thailand. The purpose of this study was to observe changes in sentiments after cannabis legalization and to investigate health-related topics discussed on Twitter.

Methods: Tweets in Thai and English related to cannabis were scraped from Twitter between May 1 and June 13, 2022, during cannabis legalization in Thailand. Sentiment and topic-modeling analyses were used to compare the content of tweets before and after legalization. Health-related topics were manually grouped into categories by their content and rated according to the number of corresponding tweets.

Results: We collected 21,242 and 6,493 tweets, respectively, for Thai and English search terms. A sharp increase in the number of tweets related to cannabis legalization was detected at the time of its public announcement. Sentiment analysis in the Thai search group showed a significant change (p < 0.0001) in sentiment distribution after legalization, with increased negative and decreased positive sentiments. A significant change was not found in the English search group (p = 0.4437). Regarding cannabis-containing food as a leading issue, topic-modeling analysis revealed public concerns after legalization in the Thai search group, but not the English one. Topics related to cannabis tourism surfaced only in the English search group.

Conclusions: Since cannabis legalization, the primary health-related concern has been cannabis-containing food. Education and clear regulations on cannabis use are required to strengthen oversight of cannabis in the Thai population, as well as among medical tourists.

Objectives: The number of deaths from cardiovascular disease is projected to reach 23.3 million by 2030. As a contribution to preventing this phenomenon, this paper proposed a machine learning (ML) model to predict patients with arteriosclerotic heart disease (AHD). We also interpreted the prediction model results based on the ML approach and deployed modelagnostic ML methods to identify informative features and their interpretations.

Methods: We used a hematology Electronic Health Record (EHR) with information on erythrocytes, hematocrit, hemoglobin, mean corpuscular hemoglobin, mean corpuscular hemoglobin concentration, leukocytes, thrombocytes, age, and sex. To detect and predict AHD, we explored random forest (RF), XGBoost, and AdaBoost models. We examined the prediction model results based on the confusion matrix and accuracy measures. We used the Shapley Additive exPlanations (SHAP) framework to interpret the ML model and quantify the contribution of features to predictions.

Results: Our study included data from 6,837 patients, with 4,702 records from patients diagnosed with AHD and 2,135 records from patients without an AHD diagnosis. AdaBoost outperformed RF and XGBoost, achieving an accuracy of 0.78, precision of 0.82, F1-score of 0.85, and recall of 0.88. According to the SHAP summary bar plot method, hemoglobin was the most important attribute for detecting and predicting AHD patients. The SHAP local interpretability bar plot revealed that hemoglobin and mean corpuscular hemoglobin concentration had positive impacts on AHD prediction based on a single observation.

Conclusions: ML models based on real clinical data can be used to predict AHD.

Objectives: Intraoperative navigation reduces the risk of major complications and increases the likelihood of optimal surgical outcomes. This paper presents an augmented reality (AR)-based simulation technique for ventriculostomy that visualizes brain deformations caused by the movements of a surgical instrument in a three-dimensional brain model. This is achieved by utilizing a position-based dynamics (PBD) physical deformation method on a preoperative brain image.

Methods: An infrared camera-based AR surgical environment aligns the real-world space with a virtual space and tracks the surgical instruments. For a realistic representation and reduced simulation computation load, a hybrid geometric model is employed, which combines a high-resolution mesh model and a multiresolution tetrahedron model. Collision handling is executed when a collision between the brain and surgical instrument is detected. Constraints are used to preserve the properties of the soft body and ensure stable deformation.

Results: The experiment was conducted once in a phantom environment and once in an actual surgical environment. The tasks of inserting the surgical instrument into the ventricle using only the navigation information presented through the smart glasses and verifying the drainage of cerebrospinal fluid were evaluated. These tasks were successfully completed, as indicated by the drainage, and the deformation simulation speed averaged 18.78 fps.

Conclusions: This experiment confirmed that the AR-based method for external ventricular drain surgery was beneficial to clinicians.