BMC Medical Informatics and Decision Making最新文献

Background: The widespread adoption of Hospital Information Systems (HIS) has brought significant benefits in healthcare quality and workflow efficiency. However, downtimes for system maintenance are inevitable and pose a considerable challenge to continuous patient care. Existing strategies, including manual prescription methods, are no longer effective due to increasing reliance on digital systems.

Method: This study implemented two main strategies to mitigate the impact of scheduled downtimes. First, we created an "Emergency query program" that switches to a read-only backup server during downtimes, allowing clinicians to view essential patient data. Second, an "Emergency prescription system" was developed based on the Microsoft Power Platform and integrated into Microsoft Teams. This allows clinicians to perform digital prescriptions even during downtimes.

Results: During a planned 90-minute downtime, 282 users accessed the Emergency Prescription System, resulting in 22 prescriptions from various departments. Average times for prescription confirmation and completion were 8 min and 3 s, and 18 min and 40 s, respectively. A post-downtime evaluation revealed high user satisfaction.

Conclusion: Essential maintenance-induced HIS downtimes are inherently disruptive to patient care process. Our deployment of an emergency query program and a Microsoft Teams-integrated emergency prescription system demonstrated robust care continuity during HIS downtime.

Background: Antibiotic resistant infections cause over 700,000 deaths worldwide annually. As antimicrobial stewardship (AMS) helps minimise the emergence of antibiotic resistance resulting from inappropriate use of antibiotics in healthcare, we developed ePAMS+ (ePrescribing-based Anti-Microbial Stewardship), an ePrescribing and Medicines Administration (EPMA) system decision-support tool complemented by educational, behavioural and organisational elements.

Methods: We conducted a non-randomised before-and-after feasibility trial, implementing ePAMS+ in two English hospitals using the Cerner Millennium EPMA system. Wards of several specialties were included. Patient participants were blinded to whether ePAMS+ was in use; prescribers were not. A mixed-methods evaluation aimed to establish: acceptability and usability of ePAMS+ and trial processes; feasibility of ePAMS+ implementation and quantitative outcome recording; and a Fidelity Index measuring the extent to which ePAMS+ was delivered as intended. Longitudinal semi-structured interviews of doctors, nurses and pharmacists, alongside non-participant observations, gathered qualitative data; we extracted quantitative prescribing data from the EPMA system. Normal linear modelling of the defined daily dose (DDD) of antibiotic per admission quantified its variability, to inform sample size calculations for a future trial of ePAMS+ effectiveness.

Results: The research took place during the SARS-CoV-2 pandemic, from April 2021 to November 2022. 60 qualitative interviews were conducted (33 before ePAMS+ implementation, 27 after). 1,958 admissions (1,358 before ePAMS+ implementation; 600 after) included 24,884 antibiotic orders. Qualitative interviews confirmed that some aspects of ePAMS+ , its implementation and training were acceptable, while other features (e.g. enabling combinations of antibiotics to be prescribed) required further development. ePAMS+ uptake was low (28 antibiotic review records from 600 admissions; 0.047 records per admission), preventing full development of a Fidelity Index. Normal linear modelling of antibiotic DDD per admission showed a residual variance of 1.086 (log-transformed scale). Unavailability of indication data prevented measurement of some outcomes (e.g. number of antibiotic courses per indication).

Conclusions: This feasibility trial encountered unforeseen circumstances due to contextual factors and a global pandemic, highlighting the need for careful adaptation of complex intervention implementations to the local setting. We identified key refinements to ePAMS+ to support its wider adoption in clinical practice, requiring further piloting before a confirmatory effectiveness trial.

Trial registration: ISRCTN Registry ISRCTN13429325, 24 March 2022.

Background: Social and behavioral determinants of health (SBDH) are associated with a variety of health and utilization outcomes, yet these factors are not routinely documented in the structured fields of electronic health records (EHR). The objective of this study was to evaluate different machine learning approaches for detection of SBDH from the unstructured clinical notes in the EHR.

Methods: Latent Semantic Indexing (LSI) was applied to 2,083,180 clinical notes corresponding to 46,146 patients in the MIMIC-III dataset. Using LSI, patients were ranked based on conceptual relevance to a set of keywords (lexicons) pertaining to 15 different SBDH categories. For Generative Pretrained Transformer (GPT) models, API requests were made with a Python script to connect to the OpenAI services in Azure, using gpt-3.5-turbo-1106 and gpt-4-1106-preview models. Prediction of SBDH categories were performed using a logistic regression model that included age, gender, race and SBDH ICD-9 codes.

Results: LSI retrieved patients according to 15 SBDH domains, with an overall average PPV $\ge$ 83%. Using manually curated gold standard (GS) sets for nine SBDH categories, the macro-F1 score of LSI (0.74) was better than ICD-9 (0.71) and GPT-3.5 (0.54), but lower than GPT-4 (0.80). Due to document size limitations, only a subset of the GS cases could be processed by GPT-3.5 (55.8%) and GPT-4 (94.2%), compared to LSI (100%). Using common GS subsets for nine different SBDH categories, the macro-F1 of ICD-9 combined with either LSI (mean 0.88, 95% CI 0.82-0.93), GPT-3.5 (0.86, 0.82-0.91) or GPT-4 (0.88, 0.83-0.94) was not significantly different. After including age, gender, race and ICD-9 in a logistic regression model, the AUC for prediction of six out of the nine SBDH categories was higher for LSI compared to GPT-4.0.

Conclusions: These results demonstrate that the LSI approach performs comparable to more recent large language models, such as GPT-3.5 and GPT-4.0, when using the same set of documents. Importantly, LSI is robust, deterministic, and does not have document-size limitations or cost implications, which make it more amenable to real-world applications in health systems.

Background: The use of machine learning (ML) in mental health (MH) research is increasing, especially as new, more complex data types become available to analyze. By examining the published literature, this review aims to explore the current applications of ML in MH research, with a particular focus on its use in studying diverse and vulnerable populations, including immigrants, refugees, migrants, and racial and ethnic minorities.

Methods: From October 2022 to March 2024, Google Scholar, EMBASE, and PubMed were queried. ML-related, MH-related, and population-of-focus search terms were strung together with Boolean operators. Backward reference searching was also conducted. Included peer-reviewed studies reported using a method or application of ML in an MH context and focused on the populations of interest. We did not have date cutoffs. Publications were excluded if they were narrative or did not exclusively focus on a minority population from the respective country. Data including study context, the focus of mental healthcare, sample, data type, type of ML algorithm used, and algorithm performance were extracted from each.

Results: Ultimately, 13 peer-reviewed publications were included. All the articles were published within the last 6 years, and over half of them studied populations within the US. Most reviewed studies used supervised learning to explain or predict MH outcomes. Some publications used up to 16 models to determine the best predictive power. Almost half of the included publications did not discuss their cross-validation method.

Conclusions: The included studies provide proof-of-concept for the potential use of ML algorithms to address MH concerns in these special populations, few as they may be. Our review finds that the clinical application of these models for classifying and predicting MH disorders is still under development.

Ovarian cancer is a formidable health challenge that demands accurate and timely survival predictions to guide clinical interventions. Existing methods, while commendable, suffer from limitations in harnessing the temporal evolution of patient data and capturing intricate interdependencies among different data elements. In this paper, we present a novel methodology which combines Temporal Analysis and Graph Neural Networks (GNNs) to significantly enhance ovarian cancer survival rate predictions. The shortcomings of current processes originate from their disability to correctly seize the complex interactions amongst diverse scientific information units in addition to the dynamic modifications that arise in a affected person`s nation over time. By combining temporal information evaluation and GNNs, our cautioned approach overcomes those drawbacks and, whilst as compared to preceding methods, yields a noteworthy 8.3% benefit in precision, 4.9% more accuracy, 5.5% more advantageous recall, and a considerable 2.9% reduction in prediction latency. Our method's Temporal Analysis factor uses longitudinal affected person information to perceive good-sized styles and tendencies that offer precious insights into the direction of ovarian cancer. Through the combination of GNNs, we offer a robust framework able to shoot complicated interactions among exclusive capabilities of scientific data, permitting the version to realize diffused dependencies that would affect survival results. Our paintings have tremendous implications for scientific practice. Prompt and correct estimation of the survival price of ovarian most cancers allows scientific experts to customize remedy regimens, manipulate assets efficiently, and provide individualized care to patients. Additionally, the interpretability of our version`s predictions promotes a collaborative method for affected person care via way of means of strengthening agreement among scientific employees and the AI-driven selection help system. The proposed approach not only outperforms existing methods but also has the possible to develop ovarian cancer treatment by providing clinicians through a reliable tool for informed decision-making. Through a fusion of Temporal Analysis and Graph Neural Networks, we conduit the gap among data-driven insights and clinical practice, proposing a capable opportunity for refining patient outcomes in ovarian cancer management operations.

Background: In Jordan, the confluence of traffic congestion and overcrowding in public hospitals poses a significant challenge for patients to collect their medications timely. This challenge was further intensified during the COVID-19 pandemic. Recognizing this issue, the Ministry of Health (MOH) and Electronic Health Solutions (EHS) intend to establish a Medication Delivery System (MDS), designed to provide patients with home delivery of medications and ensure proper treatment. This paper outlines a comprehensive framework to guide requirements engineers in devising an effective MDS framework, with a focus on expediting the development and testing processes and mitigating the risks associated with constructing such a system.

Method: The proposed methodology entails a robust, structured approach to requirements development for an MDS that integrates an electronic health record system, billing system, pharmacy application, the patient-oriented My Hakeem app, and a delivery tracking system. The requirements elicitation and analysis processes were undertaken by a multidisciplinary committee from MOH and EHS teams, ensuring a diverse understanding of stakeholder needs and expectations. The requirement specifications were meticulously documented via a data dictionary, unified modeling language (UML), and context diagrams. The quality and accuracy of the requirements were verified through an extensive validation process, involving thorough review by various EHS teams and the MOH committee.

Results: The MDS was implemented across numerous MOH facilities within a timeline that was a third of the original projection, leveraging the same level of resources and expertise. Post the requirements development phase, there were no changes requested by any stakeholders, indicating a high level of requirement accuracy and satisfaction.

Conclusion: The study illustrates that our proposed methodology significantly results in a comprehensive, well-documented, and validated set of requirements, which streamlines the development and testing phases of the project and effectively eliminates requirement errors at an early stage of the requirements development process.

Background: Forecasting models predicting trends in hospitalization rates have the potential to inform hospital management during seasonal epidemics of respiratory diseases and the associated surges caused by acute hospital admissions. Hospital bed requirements for elective surgery could be better planned if it were possible to foresee upcoming peaks in severe respiratory illness admissions. Forecasting models can also guide the use of intervention strategies to decrease the spread of respiratory pathogens and thus prevent local health system overload. In this study, we explore the capability of forecasting models to predict the number of hospital admissions in Auckland, New Zealand, within a three-week time horizon. Furthermore, we evaluate probabilistic forecasts and the impact on model performance when integrating laboratory data describing the circulation of respiratory viruses.

Methods: The dataset used for this exploration results from active hospital surveillance, in which the World Health Organization Severe Acute Respiratory Infection (SARI) case definition was consistently used. This research nurse-led surveillance has been implemented in two public hospitals in Auckland and provides a systematic laboratory testing of SARI patients for nine respiratory viruses, including influenza, respiratory syncytial virus, and rhinovirus. The forecasting strategies used comprise automatic machine learning, one of the most recent generative pre-trained transformers, and established artificial neural network algorithms capable of univariate and multivariate forecasting.

Results: We found that machine learning models compute more accurate forecasts in comparison to naïve seasonal models. Furthermore, we analyzed the impact of reducing the temporal resolution of forecasts, which decreased the model error of point forecasts and made probabilistic forecasting more reliable. An additional analysis that used the laboratory data revealed strong season-to-season variations in the incidence of respiratory viruses and how this correlates with total hospitalization cases. These variations could explain why it was not possible to improve forecasts by integrating this data.

Conclusions: Active SARI surveillance and consistent data collection over time enable these data to be used to predict hospital bed utilization. These findings show the potential of machine learning as support for informing systems for proactive hospital management.

Background: In recent years, mobile medical technology has made great progress in chronic disease management, but its application in patients with atrial fibrillation (AF) still needs to be clarified.

Objective: This study aims to determine whether the newly developed smartphone app for patients with AF (Alfalfa App) can improve anticoagulation knowledge, drug treatment compliance, and satisfaction of AF patients.

Methods: Alfalfa App integrates the functions of patient education, remote consultation, and medication reminder through a simple user interface. From June 2020 to December 2020, patients with AF were recruited in five large tertiary hospitals in China. Patients were randomly divided into the Alfalfa App or routine nursing groups. Patients' knowledge, medication adherence, and satisfaction with anticoagulation were assessed using validated questionnaires at baseline, 1 month, and 3 months.

Results: In this randomized controlled trial, 113 patients with AF were included, 57 patients were randomly assigned to the Alfalfa App group, and 56 patients were randomly assigned to the routine nursing group. Forty-eight patients in the Alfalfa App group completed a three-month follow-up, and 48 patients in the routine nursing group completed a three-month follow-up. Basic demographic data were comparable between the two groups. The average age of AF patients was 61.65 ± 11.01 years old, and 61.5% of them were male. With time (baseline to 3 months), the knowledge scores of the Alfalfa App group (P<.001) and the routine nursing group (P = .002) were significantly improved, the compliance scores of the routine nursing group(P<.001) and Alfalfa App group(P<.001) significantly improved. Compared with the routine nursing group, patients' knowledge level and medication compliance using the Alfalfa App at 1 month and 3 months were significantly higher (all P < .05). There were significant differences in knowledge and compliance scores between the two groups with time (all P < .05). The satisfaction degree of drug treatment in the Alfalfa App group was significantly better than that in the routine nursing group (all P < .05).

Conclusions: Alfalfa App significantly improved the anticoagulation knowledge, drug treatment compliance, and satisfaction of AF patients. In oral anticoagulation management for AF patients, mobile medical technology that integrates the functions of patient education, remote consultation, and medication reminder may be helpful.

Trial registration: Registration number, ChiCTR1900024455. Registered on July 12, 2019.

Purpose: Rare diseases pose significant challenges in diagnosis and treatment due to their low prevalence and heterogeneous clinical presentations. Unstructured clinical notes contain valuable information for identifying rare diseases, but manual curation is time-consuming and prone to subjectivity. This study aims to develop a hybrid approach combining dictionary-based natural language processing (NLP) tools with large language models (LLMs) to improve rare disease identification from unstructured clinical reports.

Methods: We propose a novel hybrid framework that integrates the Orphanet Rare Disease Ontology (ORDO) and the Unified Medical Language System (UMLS) to create a comprehensive rare disease vocabulary. SemEHR, a dictionary-based NLP tool, is employed to extract rare disease mentions from clinical notes. To refine the results and improve accuracy, we leverage various LLMs, including LLaMA3, Phi3-mini, and domain-specific models like OpenBioLLM and BioMistral. Different prompting strategies, such as zero-shot, few-shot, and knowledge-augmented generation, are explored to optimize the LLMs' performance.

Results: The proposed hybrid approach demonstrates superior performance compared to traditional NLP systems and standalone LLMs. LLaMA3 and Phi3-mini achieve the highest F1 scores in rare disease identification. Few-shot prompting with 1-3 examples yields the best results, while knowledge-augmented generation shows limited improvement. Notably, the approach uncovers a significant number of potential rare disease cases not documented in structured diagnostic records, highlighting its ability to identify previously unrecognized patients.

Conclusion: The hybrid approach combining dictionary-based NLP tools with LLMs shows great promise for improving rare disease identification from unstructured clinical reports. By leveraging the strengths of both techniques, the method demonstrates superior performance and the potential to uncover hidden rare disease cases. Further research is needed to address limitations related to ontology mapping and overlapping case identification, and to integrate the approach into clinical practice for early diagnosis and improved patient outcomes.