Potential of Large Language Models in Health Care: Delphi Study.

BACKGROUND: A large language model (LLM) is a machine learning model inferred from text data that captures subtle patterns of language use in context. Modern LLMs are based on neural network architectures that incorporate transformer methods. They allow the model to relate words together through attention to multiple words in a text sequence. LLMs have been shown to be highly effective for a range of tasks in natural language processing (NLP), including classification and information extraction tasks and generative applications. OBJECTIVE: The aim of this adapted Delphi study was to collect researchers' opinions on how LLMs might influence health care and on the strengths, weaknesses, opportunities, and threats of LLM use in health care. METHODS: We invited researchers in the fields of health informatics, nursing informatics, and medical NLP to share their opinions on LLM use in health care. We started the first round with open questions based on our strengths, weaknesses, opportunities, and threats framework. In the second and third round, the participants scored these items. RESULTS: The first, second, and third rounds had 28, 23, and 21 participants, respectively. Almost all participants (26/28, 93% in round 1 and 20/21, 95% in round 3) were affiliated with academic institutions. Agreement was reached on 103 items related to use cases, benefits, risks, reliability, adoption aspects, and the future of LLMs in health care. Participants offered several use cases, including supporting clinical tasks, documentation tasks, and medical research and education, and agreed that LLM-based systems will act as health assistants for patient education. The agreed-upon benefits included increased efficiency in data handling and extraction, improved automation of processes, improved quality of health care services and overall health outcomes, provision of personalized care, accelerated diagnosis and treatment processes, and improved interaction between patients and health care professionals. In total, 5 risks to health care in general were identified: cybersecurity breaches, the potential for patient misinformation, ethical concerns, the likelihood of biased decision-making, and the risk associated with inaccurate communication. Overconfidence in LLM-based systems was recognized as a risk to the medical profession. The 6 agreed-upon privacy risks included the use of unregulated cloud services that compromise data security, exposure of sensitive patient data, breaches of confidentiality, fraudulent use of information, vulnerabilities in data storage and communication, and inappropriate access or use of patient data. CONCLUSIONS: Future research related to LLMs should not only focus on testing their possibilities for NLP-related tasks but also consider the workflows the models could contribute to and the requirements regarding quality, integration, and regulations needed for successful implementation in practice.

Katherine P. Andriole - A trailblazer in medical informatics and radiology.

In a traditionally male-dominated field, the journey of Dr. Andriole represents a pioneering path in the realms of radiology and medical imaging informatics. Her career has not only reshaped the landscape of radiology but also championed diversity, equity, and inclusion in healthcare technology. Through a comprehensive exploration of Dr. Andriole's career trajectory, we navigate her transition from analog to digital radiology, her influential role in pioneering picture archiving communication systems (PACS), and her dedication to mentorship and education in the field. Dr. Andriole's journey underscores the growing influence of women in radiology and informatics, exemplified by her Gold Medal accolades from esteemed organizations. Dr. Andriole's career serves as a beacon for aspiring radiologists and informaticians, emphasizing the significance of passion, mentorship, and collaborative teamwork in advancing the fields of radiology and informatics.

Recommendations for the Quality Management of Patient-Generated Health Data in Remote Patient Monitoring: Mixed Methods Study.

BACKGROUND: Patient-generated health data (PGHD) collected from innovative wearables are enabling health care to shift to outside clinical settings through remote patient monitoring (RPM) initiatives. However, PGHD are collected continuously under the patient's responsibility in rapidly changing circumstances during the patient's daily life. This poses risks to the quality of PGHD and, in turn, reduces their trustworthiness and fitness for use in clinical practice. OBJECTIVE: Using a sociotechnical health informatics lens, we developed a data quality management (DQM) guideline for PGHD captured from wearable devices used in RPM with the objective of investigating how DQM principles can be applied to ensure that PGHD can reliably inform clinical decision-making in RPM. METHODS: First, clinicians, health information specialists, and MedTech industry representatives with experience in RPM were interviewed to identify DQM challenges. Second, these stakeholder groups were joined by patient representatives in a workshop to co-design potential solutions to meet the expectations of all the stakeholders. Third, the findings, along with the literature and policy review results, were interpreted to construct a guideline. Finally, we validated the guideline through a Delphi survey of international health informatics and health information management experts. RESULTS: The guideline constructed in this study comprised 19 recommendations across 7 aspects of DQM. It explicitly addressed the needs of patients and clinicians but implied that there must be collaboration among all stakeholders to meet these needs. CONCLUSIONS: The increasing proliferation of PGHD from wearables in RPM requires a systematic approach to DQM so that these data can be reliably used in clinical care. The developed guideline is an important next step toward safe RPM.

Digital Technology in Hospital Administration: A Strategic Choice.

Digital technology has encompassed all aspects of healthcare. There are many international and national organizations, guidelines, and formats available in health information systems (HIS), but many are presently still not being used in India. The aim is to give a flawless, secure, and user-friendly health information technology (IT) system for Indian healthcare. We discuss the timeline of digital technology in hospital administration, administrative applications, and the importance of clinical quality in health. Clinical perspectives of clinical information systems (CIS), both in acute as well as chronic clinical care models. Cross-integration of healthcare in IT (HIT) in electronic health records (EHR) or electronic medical records (EMRs), in chronic disease management (CDM) systems, and in clinical decision support systems (CDSS) are elaborated. Also, practical strategic application methods are discussed. The limitations of the current HIS software in India are mostly used for transaction reporting, prescription, and administrative tools. They lack CIS and strategic business applications as compared to mature multinational company (MNC) HIS software. Along with this, various features and levels of HIS Software, challenges of HIT adoption, Indian health IT standards, and the future framework of IT in health in India are systematically analyzed. We aim at all physicians in India and at all levels of practice, from individuals, group practices, health institutes, or corporate hospitals, and to encourage them to make strategic use of CIS and strategic IT applications in their individual practice and hospital management. This will improve clinical outcomes, patient safety, practitioner performance, adherence to treatment guidelines, and reduction in medical errors, along with efficiency improvements and cost reductions. How to cite this article: Taneja D, Kulkarni SV, Sinha S, et al. Digital Technology in Hospital Administration: A Strategic Choice. J Assoc Physicians India 2023;71(10):83-88.

Question Answering System Based on Knowledge Graph in Traditional Chinese Medicine Diagnosis and Treatment of Viral Hepatitis B.

This article uses the real medical records and web pages of Chinese medicine diagnosis and treatment of hepatitis B to extract structured medical knowledge, and obtains a total of 8,563 entities, 96,896 relationships, 32 entity types, and 40 relationship types. The structured data was stored in the Neo4j graph structure database, and a knowledge graph of Chinese medical diagnosis and treatment of hepatitis B was constructed. The knowledge map is used as a structured data source to provide high-quality knowledge information for the medical question and answer system based on hepatitis B disease. Applying the deep learning method to the question identification and knowledge response of the question answering system makes the hepatitis B medical intelligent question answering system has important research and application significance. The question-and-answer system takes aim at hepatitis B, a public health problem in the world and leverages the advantages of traditional Chinese medicine for diagnosis and treatment. It provides a reference for doctors' disease diagnosis, treatment, and patient self-care. Its value is important for the treatment of hepatitis B disease.

Artificial Intelligence Technology-Based Medical Information Processing and Emergency First Aid Nursing Management.

This study was aimed at exploring the new management mode of medical information processing and emergency first aid nursing management under the new artificial intelligence technology. This study will use the artificial intelligence algorithm to optimize medical information processing and emergency first aid nursing management process, in order to improve the efficiency of emergency department and first aid efficiency. The successful rescue rates of hemorrhagic shock, coma, dyspnea, and more than three organs injury were 96.7%, 92.5%, 93.7%, and 87.2%, respectively, after the emergency first aid nursing mode was used in the hospital emergency center. The success rates of first aid within three years were compared, which were 91.8%, 93.4%, and 94.2%, respectively, showing an increasing trend year by year. 255 emergency patients in five batches in June and five batches in July were selected as the research objects by convenience sampling method. Among them, 116 cases in June were taken as the experimental group, and 139 cases in July were taken as the control group, which was used to verify the efficiency of the design model in this study. The results showed that the triage time of the two groups was 8.16 ± 2.07 min and 19.21 ± 6.36 min, respectively, and the difference was statistically significant (P < 0.01). The triage coincidence rates were 96.35% and 90.04%, respectively, and the difference was statistically significant (P < 0.05). The research proved that the design of intelligent medical information processing and emergency first aid nursing management research model can effectively improve the triage efficiency of the wounded, assist the efficiency of emergency nursing of medical staff, and improve the survival rate of emergency patients, which is worthy of clinical promotion.

Combining word embeddings to extract chemical and drug entities in biomedical literature.

BACKGROUND: Natural language processing (NLP) and text mining technologies for the extraction and indexing of chemical and drug entities are key to improving the access and integration of information from unstructured data such as biomedical literature. METHODS: In this paper we evaluate two important tasks in NLP: the named entity recognition (NER) and Entity indexing using the SNOMED-CT terminology. For this purpose, we propose a combination of word embeddings in order to improve the results obtained in the PharmaCoNER challenge. RESULTS: For the NER task we present a neural network composed of BiLSTM with a CRF sequential layer where different word embeddings are combined as an input to the architecture. A hybrid method combining supervised and unsupervised models is used for the concept indexing task. In the supervised model, we use the training set to find previously trained concepts, and the unsupervised model is based on a 6-step architecture. This architecture uses a dictionary of synonyms and the Levenshtein distance to assign the correct SNOMED-CT code. CONCLUSION: On the one hand, the combination of word embeddings helps to improve the recognition of chemicals and drugs in the biomedical literature. We achieved results of 91.41% for precision, 90.14% for recall, and 90.77% for F1-score using micro-averaging. On the other hand, our indexing system achieves a 92.67% F1-score, 92.44% for recall, and 92.91% for precision. With these results in a final ranking, we would be in the first position.

Medical data integration using HL7 standards for patient's early identification.

Integration between information systems is critical, especially in the healthcare domain, since interoperability requirements are related to patients' data confidentiality, safety, and satisfaction. The goal of this study is to propose a solution based on the integration between queue management solution (QMS) and the electronic medical records (EMR), using Health Level Seven (HL7) protocols and Extensible Markup Language (XML). The proposed solution facilitates the patient's self-check-in within a healthcare organization in UAE. The solution aims to help in minimizing the waiting times within the outpatient department through early identification of patients who hold the Emirates national ID cards, i.e., whether an Emirati or expatriates. The integration components, solution design, and the custom-designed XML and HL7 messages were clarified in this paper. In addition, the study includes a simulation experiment through control and intervention weeks with 517 valid appointments. The experiment goal was to evaluate the patient's total journey and each related clinical stage by comparing the "routine-based identification" with the "patient's self-check-in" processes in case of booked appointments. As a key finding, the proposed solution is efficient and could reduce the "patient's journey time" by more than 14 minutes and "time to identify" patients by 10 minutes. There was also a significant drop in the waiting time to triage and the time to finish the triage process. In conclusion, the proposed solution is considered innovative and can provide a positive added value for the patient's whole journey.

A Master-Slave Binary Grey Wolf Optimizer for Optimal Feature Selection in Biomedical Data Classification.

A new master-slave binary grey wolf optimizer (MSBGWO) is introduced. A master-slave learning scheme is introduced to the grey wolf optimizer (GWO) to improve its ability to explore and get better solutions in a search space. Five high-dimensional biomedical datasets are used to test the ability of MSBGWO in feature selection. The experimental results of MSBGWO are superior in terms of classification accuracy, precision, recall, F-measure, and number of features selected when compared to those of the binary grey wolf optimizer version 2 (BGWO2), binary genetic algorithm (BGA), binary particle swarm optimization (BPSO), differential evolution (DE) algorithm, and sine-cosine algorithm (SCA).

A digital health platform for assisting the diagnosis and monitoring of COVID-19 progression: An adjuvant approach for augmenting the antiviral response and mitigating the immune-mediated target organ damage.

Coronavirus disease 2019 (COVID-19), which is a respiratory illness associated with high mortality, has been classified as a pandemic. The major obstacles for the clinicians to contain the disease are limited information availability, difficulty in disease diagnosis, predicting disease prognosis, and lack of disease monitoring tools. Additionally, the lack of valid therapies has further contributed to the difficulties in containing the pandemic. Recent studies have reported that the dysregulation of the immune system leads to an ineffective antiviral response and promotes pathological immune response, which manifests as ARDS, myocarditis, and hepatitis. In this study, a novel platform has been described for disseminating information to physicians for the diagnosis and monitoring of patients with COVID-19. An adjuvant approach using compounds that can potentiate antiviral immune response and mitigate COVID-19-induced immune-mediated target organ damage has been presented. A prolonged beneficial effect is achieved by implementing algorithm-based individualized variability measures in the treatment regimen.

Weakly supervised learning for classification of lung cytological images using attention-based multiple instance learning.

In cytological examination, suspicious cells are evaluated regarding malignancy and cancer type. To assist this, we previously proposed an automated method based on supervised learning that classifies cells in lung cytological images as benign or malignant. However, it is often difficult to label all cells. In this study, we developed a weakly supervised method for the classification of benign and malignant lung cells in cytological images using attention-based deep multiple instance learning (AD MIL). Images of lung cytological specimens were divided into small patch images and stored in bags. Each bag was then labeled as benign or malignant, and classification was conducted using AD MIL. The distribution of attention weights was also calculated as a color map to confirm the presence of malignant cells in the image. AD MIL using the AlexNet-like convolutional neural network model showed the best classification performance, with an accuracy of 0.916, which was better than that of supervised learning. In addition, an attention map of the entire image based on the attention weight allowed AD MIL to focus on most malignant cells. Our weakly supervised method automatically classifies cytological images with acceptable accuracy based on supervised learning without complex annotations.

Hybrid Gradient Descent Grey Wolf Optimizer for Optimal Feature Selection.

Feature selection is the process of decreasing the number of features in a dataset by removing redundant, irrelevant, and randomly class-corrected data features. By applying feature selection on large and highly dimensional datasets, the redundant features are removed, reducing the complexity of the data and reducing training time. The objective of this paper was to design an optimizer that combines the well-known metaheuristic population-based optimizer, the grey wolf algorithm, and the gradient descent algorithm and test it for applications in feature selection problems. The proposed algorithm was first compared against the original grey wolf algorithm in 23 continuous test functions. The proposed optimizer was altered for feature selection, and 3 binary implementations were developed with final implementation compared against the two implementations of the binary grey wolf optimizer and binary grey wolf particle swarm optimizer on 6 medical datasets from the UCI machine learning repository, on metrics such as accuracy, size of feature subsets, F-measure, accuracy, precision, and sensitivity. The proposed optimizer outperformed the three other optimizers in 3 of the 6 datasets in average metrics. The proposed optimizer showed promise in its capability to balance the two objectives in feature selection and could be further enhanced.

Health information technology to improve care for people with multiple chronic conditions.

OBJECTIVE: To review evidence regarding the use of Health Information Technology (health IT) interventions aimed at improving care for people living with multiple chronic conditions (PLWMCC) in order to identify critical knowledge gaps. DATA SOURCES: We searched MEDLINE, CINAHL, PsycINFO, EMBASE, Compendex, and IEEE Xplore databases for studies published in English between 2010 and 2020. STUDY DESIGN: We identified studies of health IT interventions for PLWMCC across three domains as follows: self-management support, care coordination, and algorithms to support clinical decision making. DATA COLLECTION/EXTRACTION METHODS: Structured search queries were created and validated. Abstracts were reviewed iteratively to refine inclusion and exclusion criteria. The search was supplemented by manually searching the bibliographic sections of the included studies. The search included a forward citation search of studies nested within a clinical trial to identify the clinical trial protocol and published clinical trial results. Data were extracted independently by two reviewers. PRINCIPAL FINDINGS: The search yielded 1907 articles; 44 were included. Nine randomized controlled trials (RCTs) and 35 other studies including quasi-experimental, usability, feasibility, qualitative studies, or development/validation studies of analytic models were included. Five RCTs had positive results, and the remaining four RCTs showed that the interventions had no effect. The studies address individual patient engagement and assess patient-centered outcomes such as quality of life. Few RCTs assess outcomes such as disability and none assess mortality. CONCLUSIONS: Despite a growing body of literature on health IT interventions or multicomponent interventions including a health IT component for chronic disease management, current evidence for applying health IT solutions to improve care for PLWMCC is limited. The body of literature included in this review provides critical information on the state of the science as well as the many gaps that need to be filled for digital health to fulfill its promise in supporting care delivery that meets the needs of PLWMCC.

Detection algorithms and attentive points of safety signal using spontaneous reporting systems as a clinical data source.

Continuous evaluation of drug safety is needed following approval to determine adverse events (AEs) in patient populations with diverse backgrounds. Spontaneous reporting systems are an important source of information for the detection of AEs not identified in clinical trials and for safety assessments that reflect the real-world use of drugs in specific populations and clinical settings. The use of spontaneous reporting systems is expected to detect drug-related AEs early after the launch of a new drug. Spontaneous reporting systems do not contain data on the total number of patients that use a drug; therefore, signal detection by disproportionality analysis, focusing on differences in the ratio of AE reports, is frequently used. In recent years, new analyses have been devised, including signal detection methods focused on the difference in the time to onset of an AE, methods that consider the patient background and those that identify drug-drug interactions. However, unlike commonly used statistics, the results of these analyses are open to misinterpretation if the method and the characteristics of the spontaneous reporting system cannot be evaluated properly. Therefore, this review describes signal detection using data mining, considering traditional methods and the latest knowledge, and their limitations.

Diagnosis of Wilson Disease and Its Phenotypes by Using Artificial Intelligence.

WD is caused by ATP7B variants disrupting copper efflux resulting in excessive copper accumulation mainly in liver and brain. The diagnosis of WD is challenged by its variable clinical course, onset, morbidity, and ATP7B variant type. Currently it is diagnosed by a combination of clinical symptoms/signs, aberrant copper metabolism parameters (e.g., low ceruloplasmin serum levels and high urinary and hepatic copper concentrations), and genetic evidence of ATP7B mutations when available. As early diagnosis and treatment are key to favorable outcomes, it is critical to identify subjects before the onset of overtly detrimental clinical manifestations. To this end, we sought to improve WD diagnosis using artificial neural network algorithms (part of artificial intelligence) by integrating available clinical and molecular parameters. Surprisingly, WD diagnosis was based on plasma levels of glutamate, asparagine, taurine, and Fischer's ratio. As these amino acids are linked to the urea-Krebs' cycles, our study not only underscores the central role of hepatic mitochondria in WD pathology but also that most WD patients have underlying hepatic dysfunction. Our study provides novel evidence that artificial intelligence utilized for integrated analysis for WD may result in earlier diagnosis and mechanistically relevant treatments for patients with WD.

Biomolecule and Bioentity Interaction Databases in Systems Biology: A Comprehensive Review.

Technological advances in high-throughput techniques have resulted in tremendous growth of complex biological datasets providing evidence regarding various biomolecular interactions. To cope with this data flood, computational approaches, web services, and databases have been implemented to deal with issues such as data integration, visualization, exploration, organization, scalability, and complexity. Nevertheless, as the number of such sets increases, it is becoming more and more difficult for an end user to know what the scope and focus of each repository is and how redundant the information between them is. Several repositories have a more general scope, while others focus on specialized aspects, such as specific organisms or biological systems. Unfortunately, many of these databases are self-contained or poorly documented and maintained. For a clearer view, in this article we provide a comprehensive categorization, comparison and evaluation of such repositories for different bioentity interaction types. We discuss most of the publicly available services based on their content, sources of information, data representation methods, user-friendliness, scope and interconnectivity, and we comment on their strengths and weaknesses. We aim for this review to reach a broad readership varying from biomedical beginners to experts and serve as a reference article in the field of Network Biology.

Development of a core competency framework for clinical informatics.

OBJECTIVES: Until this point there was no national core competency framework for clinical informatics in the UK. We report on the final two iterations of work carried out in the formation of a national core competency framework. This follows an initial systematic literature review of existing skills and competencies and a job listing analysis.MethodsAn iterative approach was applied to framework development. Using a mixed-methods design we carried out semi-structured interviews with participants involved in informatics (n=15). The framework was updated based on the interview findings and was subsequently distributed as part of a bespoke online digital survey for wider participation (n=87). The final version of the framework is based on the findings of the survey. RESULTS: Over 102 people reviewed the framework as part of the interview or survey process. This led to a final core competency framework containing 6 primary domains with 36 subdomains containing 111 individual competencies. CONCLUSIONS: An iterative mixed-methods approach for competency development involving the target community was appropriate for development of the competency framework. There is some contention around the depth of technical competencies required. Care is also needed to avoid professional burnout, as clinicians and healthcare practitioners already have clinical competencies to maintain. Therefore, how the framework is applied in practice and how practitioners meet the competencies requires careful consideration.

Systems-Level Opportunities in the Management of Primary Hyperparathyroidism: An Informatics-based Assessment.

CONTEXT: Primary hyperparathyroidism (PHPT), a leading cause of hypercalcemia and secondary osteoporosis, is underdiagnosed. OBJECTIVE: This work aims to establish a foundation for an electronic medical record-based intervention that would prompt serum parathyroid hormone (PTH) assessment in patients with persistent hypercalcemia and identify care gaps in their management. METHODS: A retrospective cohort study was conducted in a tertiary academic health system of outpatients with persistent hypercalcemia, who were categorized as having classic or normohormonal PHPT. Main outcome measures included the frequencies of serum PTH measurement in patients with persistent hypercalcemia, and their subsequent workup with bone mineral density (BMD) assessment, and ultimately, medical therapy or parathyroidectomy. RESULTS: Among 3151 patients with persistent hypercalcemia, 1526 (48%) had PTH measured, of whom 1377 (90%) were confirmed to have classic (49%) or normohormonal (41%) PHPT. PTH was measured in 65% of hypercalcemic patients with osteopenia or osteoporosis (P < .001). At median 2-year follow-up, bone density was assessed in 275 (20%) patients with either variant of PHPT (P = .003). Of women aged 50 years or older with classic PHPT, 95 (19%) underwent BMD assessment. Of patients with classic or normohormonal PHPT, 919 patients (67%) met consensus criteria for surgical intervention, though only 143 (15%) underwent parathyroidectomy. CONCLUSION: Within a large academic health system, more than half of patients with confirmed hypercalcemia were not assessed for PHPT, including many patients with preexisting bone disease. Care gaps in BMD assessment and medical or surgical therapy represent missed opportunities to avoid skeletal and other complications of PHPT.