BMC Medical Informatics and Decision Making最新文献

Background: Modeling patient data, particularly electronic health records (EHR), is one of the major focuses of machine learning studies in healthcare, as these records provide clinicians with valuable information that can potentially assist them in disease diagnosis and decision-making.

Methods: In this study, we present a multi-level graph-based framework called MedMGF, which models both patient medical profiles extracted from EHR data and their relationship network of health profiles in a single architecture. The medical profiles consist of several layers of data embedding derived from interval records obtained during hospitalization, and the patient-patient network is created by measuring the similarities between these profiles. We also propose a modification to the Focal Loss (FL) function to improve classification performance in imbalanced datasets without the need to imputate the data. MedMGF's performance was evaluated against several Graphical Convolutional Network (GCN) baseline models implemented with Binary Cross Entropy (BCE), FL, class balancing parameter $\alpha$ , and Synthetic Minority Oversampling Technique (SMOTE).

Results: Our proposed framework achieved high classification performance (AUC: 0.8098, ACC: 0.7503, SEN: 0.8750, SPE: 0.7445, NPV: 0.9923, PPV: 0.1367) on an extreme imbalanced pediatric sepsis dataset (n=3,014, imbalance ratio of 0.047). It yielded a classification improvement of 3.81% for AUC, 15% for SEN compared to the baseline GCN+ $\alpha$ FL (AUC: 0.7717, ACC: 0.8144, SEN: 0.7250, SPE: 0.8185, PPV: 0.1559, NPV: 0.9847), and an improvement of 5.88% in AUC and 22.5% compared to GCN+FL+SMOTE (AUC: 0.7510, ACC: 0.8431, SEN: 0.6500, SPE: 0.8520, PPV: 0.1688, NPV: 0.9814). It also showed a classification improvement of 3.86% for AUC, 15% for SEN compared to the baseline GCN+ $\alpha$ BCE (AUC: 0.7712, ACC: 0.8133, SEN: 0.7250, SPE: 0.8173, PPV: 0.1551, NPV: 0.9847), and an improvement of 14.33% in AUC and 27.5% in comparison to GCN+BCE+SMOTE (AUC: 0.6665, ACC: 0.7271, SEN: 0.6000, SPE: 0.7329, PPV: 0.0941, NPV: 0.9754).

Conclusion: When compared to all baseline models, MedMGF achieved the highest SEN and AUC results, demonstrating the potential for several healthcare applications.

Background: Successful deployment of clinical prediction models for clinical deterioration relates not only to predictive performance but to integration into the decision making process. Models may demonstrate good discrimination and calibration, but fail to match the needs of practising acute care clinicians who receive, interpret, and act upon model outputs or alerts. We sought to understand how prediction models for clinical deterioration, also known as early warning scores (EWS), influence the decision-making of clinicians who regularly use them and elicit their perspectives on model design to guide future deterioration model development and implementation.

Methods: Nurses and doctors who regularly receive or respond to EWS alerts in two digital metropolitan hospitals were interviewed for up to one hour between February 2022 and March 2023 using semi-structured formats. We grouped interview data into sub-themes and then into general themes using reflexive thematic analysis. Themes were then mapped to a model of clinical decision making using deductive framework mapping to develop a set of practical recommendations for future deterioration model development and deployment.

Results: Fifteen nurses (n = 8) and doctors (n = 7) were interviewed for a mean duration of 42 min. Participants emphasised the importance of using predictive tools for supporting rather than supplanting critical thinking, avoiding over-protocolising care, incorporating important contextual information and focusing on how clinicians generate, test, and select diagnostic hypotheses when managing deteriorating patients. These themes were incorporated into a conceptual model which informed recommendations that clinical deterioration prediction models demonstrate transparency and interactivity, generate outputs tailored to the tasks and responsibilities of end-users, avoid priming clinicians with potential diagnoses before patients were physically assessed, and support the process of deciding upon subsequent management.

Conclusions: Prediction models for deteriorating inpatients may be more impactful if they are designed in accordance with the decision-making processes of acute care clinicians. Models should produce actionable outputs that assist with, rather than supplant, critical thinking.

Background: Data quality in health information systems has a complex structure and consists of several dimensions. This research conducted for identify Common data quality elements for health information systems.

Methods: A literature review was conducted and search strategies run in Web of Knowledge, Science Direct, Emerald, PubMed, Scopus and Google Scholar search engine as an additional source for tracing references. We found 760 papers, excluded 314 duplicates, 339 on abstract review and 167 on full-text review; leaving 58 papers for critical appraisal.

Results: Current review shown that 14 criteria are categorized as the main dimensions for data quality for health information system include: Accuracy, Consistency, Security, Timeliness, Completeness, Reliability, Accessibility, Objectivity, Relevancy, Understandability, Navigation, Reputation, Efficiency and Value- added. Accuracy, Completeness, and Timeliness, were the three most-used dimensions in literature.

Conclusions: At present, there is a lack of uniformity and potential applicability in the dimensions employed to evaluate the data quality of health information system. Typically, different approaches (qualitative, quantitative and mixed methods) were utilized to evaluate data quality for health information system in the publications that were reviewed. Consequently, due to the inconsistency in defining dimensions and assessing methods, it became imperative to categorize the dimensions of data quality into a limited set of primary dimensions.

The healthcare industry has been put to test the need to manage enormous amounts of data provided by various sources, which are renowned for providing enormous quantities of heterogeneous information. The data are collected and analyzed with different Data Analytic (DA) and machine learning algorithm approaches. Researchers, scientists, and industrialists must manage or select the best approach associated with DA in healthcare. This scientific study is based on decision analysis between the DA factors and alternatives. The information affects the whole system in a rational manner. This information is very important in healthcare sector for appropriate prediction and analysis. The evaluation discusses its benefits and presents an analytic framework. The Fuzzy Analytic Hierarchy Process (Fuzzy AHP) approach is used to address the weight of the factors. The Fuzzy Techniques for Order Preference by Similarity to Ideal Solution (Fuzzy TOPSIS) address the rank of the data analytic alternatives used in healthcare sector. The models used in the article briefly discuss the challenges of DA and approaches to address those challenges. The assorted factors of DA are capture, cleaning, storage, security, stewardship, reporting, visualization, updating, sharing, and querying. The DA alternatives include descriptive, diagnostic, predictive, prescriptive, discovery, regression, cohort and inferential analyses. The most influential factors of the DA and the most suitable approach for the DA are evaluated. The 'cleaning' factor has the highest weight, and 'updating' is achieved at least by the Fuzzy-AHP approach. The regression approach of data analysis had the highest rank, and the diagnostic analysis had the lowest rank. Decision analyses are necessary for data scientists and medical providers to predict diseases appropriately in the healthcare domain. This analysis also revealed the cost benefits to hospitals.

Ontologies and terminologies serve as the backbone of knowledge representation in biomedical domains, facilitating data integration, interoperability, and semantic understanding across diverse applications. However, the quality assurance and enrichment of these resources remain an ongoing challenge due to the dynamic nature of biomedical knowledge. In this editorial, we provide an introductory summary of seven articles included in this special supplement issue for quality assurance and enrichment of biological and biomedical ontologies and terminologies. These articles span a spectrum of topics, such as development of automated quality assessment frameworks for Resource Description Framework (RDF) resources, identification of missing concepts in SNOMED CT through logical definitions, and developing a COVID interface terminology to enable automatic annotations of COVID-19 related Electronic Health Records (EHRs). Collectively, these contributions underscore the ongoing efforts to improve the accuracy, consistency, and interoperability of biomedical ontologies and terminologies, thus advancing their pivotal role in healthcare and biomedical research.

The epidemic diseases such as COVID-19 are rapidly spreading all around the world. The diagnosis of epidemic at initial stage is of high importance to provide medical care to and recovery of infected people as well as protecting the uninfected population. In this paper, an automatic COVID-19 detection model using respiratory sound and medical image based on internet of health things (IoHT) is proposed. In this model, primarily to screen those people having suspected Coronavirus disease, the sound of coughing used to detect healthy people and those suffering from COVID-19, which finally obtained an accuracy of 94.999%. This approach not only expedites diagnosis and enhances accuracy but also facilitates swift screening in public places using simple equipment. Then, in the second step, in order to help radiologists to interpret medical images as best as possible, we use three pre-trained convolutional neural network models InceptionResNetV2, InceptionV3 and EfficientNetB4 and two data sets of chest radiology medical images, and CT Scan in a three-class classification. Utilizing transfer learning and pre-existing knowledge in these models leads to notable improvements in disease diagnosis and identification compared to traditional techniques. Finally, the best result obtained for CT-Scan images belonging to InceptionResNetV2 architecture with 99.414% accuracy and for radiology images related to InceptionV3 and EfficientNetB4 architectures with the accuracy is 96.943%. Therefore, the proposed model can help radiology specialists to confirm the initial assessments of the COVID-19 disease.

Background: Medical text, as part of an electronic health record, is an essential information source in healthcare. Although natural language processing (NLP) techniques for medical text are developing fast, successful transfer into clinical practice has been rare. Especially the hospital domain offers great potential while facing several challenges including many documents per patient, multiple departments and complex interrelated processes.

Methods: In this work, we survey relevant literature to identify and classify approaches which exploit NLP in the clinical context. Our contribution involves a systematic mapping of related research onto a prototypical patient journey in the hospital, along which medical documents are created, processed and consumed by hospital staff and patients themselves. Specifically, we reviewed which dataset types, dataset languages, model architectures and tasks are researched in current clinical NLP research. Additionally, we extract and analyze major obstacles during development and implementation. We discuss options to address them and argue for a focus on bias mitigation and model explainability.

Results: While a patient's hospital journey produces a significant amount of structured and unstructured documents, certain steps and documents receive more research attention than others. Diagnosis, Admission and Discharge are clinical patient steps that are researched often across the surveyed paper. In contrast, our findings reveal significant under-researched areas such as Treatment, Billing, After Care, and Smart Home. Leveraging NLP in these stages can greatly enhance clinical decision-making and patient outcomes. Additionally, clinical NLP models are mostly based on radiology reports, discharge letters and admission notes, even though we have shown that many other documents are produced throughout the patient journey. There is a significant opportunity in analyzing a wider range of medical documents produced throughout the patient journey to improve the applicability and impact of NLP in healthcare.

Conclusions: Our findings suggest that there is a significant opportunity to leverage NLP approaches to advance clinical decision-making systems, as there remains a considerable understudied potential for the analysis of patient journey data.

Background: To investigate how successfully the classification of patients with and without dental anomalies was achieved through four experiments involving different dental anomalies.

Methods: Lateral cephalometric radiographs (LCRs) from 526 individuals aged between 14 and 22 years were included. Four experiments involving different dental anomalies were created. Experiment 1 included the total dental anomaly group and control group (CG). Experiment 2 only had dental agenesis and a CG. Experiment 3 consisted of only palatally impacted canines and the CG. Experiment 4 comprised patients with various dental defects (transposition, hypodontia, agenesis-palatally affected canine, peg-shaped laterally, hyperdontia) and the CG. Twelve sella measurements and assessments of the ponticulus posticus and posterior arch deficiency were given as input. The target was to distinguish between anomalies and controls. The CatBoost algorithm was applied to classify patients with and without dental anomalies.

Results: In order from lowest to highest, the predictive accuracies of the experiments were as follows: experiment 4 < experiment 2 < experiment 3 < experiment 1. The sella area (SA) (mm2) was the most important variable in experiment 1. The most significant variable in prediction model of experiment 2 was sella height posterior (SHP) (mm). Sella area (SA) (mm2) was again the most relevant variable in experiment 3. The most important variable in experiment 4 was sella height median (SHM) (mm).

Conclusions: Every prediction model from the four experiments prioritized different variables. These findings may suggest that related research should focus on specific traits from a diagnostic perspective.

Background: Systemic inflammatory response syndrome (SIRS) is a predictor of serious infectious complications, organ failure, and death in patients with severe polytrauma and is one of the reasons for delaying early total surgical treatment. To determine the risk of SIRS within 24 h after hospitalization, we developed six machine learning models.

Materials and methods: Using retrospective data about the patient, the nature of the injury, the results of general and standard biochemical blood tests, and coagulation tests, six models were developed: decision tree, random forest, logistic regression, support vector and gradient boosting classifiers, logistic regressor, and neural network. The effectiveness of the models was assessed through internal and external validation.

Results: Among the 439 selected patients with severe polytrauma in 230 (52.4%), SIRS was diagnosed within the first 24 h of hospitalization. The SIRS group was more strongly associated with class II bleeding (39.5% vs. 60.5%; OR 1.81 [95% CI: 1.23-2.65]; P = 0.0023), long-term vasopressor use (68.4% vs. 31.6%; OR 5.51 [95% CI: 2.37-5.23]; P < 0.0001), risk of acute coagulopathy (67.8% vs. 32.2%; OR 2.4 [95% CI: 1.55-3.77]; P < 0.0001), and greater risk of pneumonia (59.5% vs. 40.5%; OR 1.74 [95% CI: 1.19-2.54]; P = 0.0042), longer ICU length of stay (5 ± 6.3 vs. 2.7 ± 4.3 days; P < 0.0001) and mortality rate (64.5% vs. 35.5%; OR 10.87 [95% CI: 6.3-19.89]; P = 0.0391). Of all the models, the random forest classifier showed the best predictive ability in the internal (AUROC 0.89; 95% CI: 0.83-0.96) and external validation (AUROC 0.83; 95% CI: 0.75-0.91) datasets.

Conclusions: The developed model made it possible to accurately predict the risk of developing SIRS in the early period after injury, allowing clinical specialists to predict patient management tactics and calculate medication and staffing needs for the patient.

Level of evidence: Level 3.

Trial registration: The study was retrospectively registered in the ClinicalTrials.gov database of the National Library of Medicine (NCT06323096).

Efforts to enhance the accuracy of protein sequence classification are of utmost importance in driving forward biological analyses and facilitating significant medical advancements. This study presents a cutting-edge model called ProtICNN-BiLSTM, which combines attention-based Improved Convolutional Neural Networks (ICNN) and Bidirectional Long Short-Term Memory (BiLSTM) units seamlessly. Our main goal is to improve the accuracy of protein sequence classification by carefully optimizing performance through Bayesian Optimisation. ProtICNN-BiLSTM combines the power of CNN and BiLSTM architectures to effectively capture local and global protein sequence dependencies. In the proposed model, the ICNN component uses convolutional operations to identify local patterns. Captures long-range associations by analyzing sequence data forward and backwards. In advanced biological studies, Bayesian Optimisation optimizes model hyperparameters for efficiency and robustness. The model was extensively confirmed with PDB-14,189 and other protein data. We found that ProtICNN-BiLSTM outperforms traditional categorization models. Bayesian Optimization's fine-tuning and seamless integration of local and global sequence information make it effective. The precision of ProtICNN-BiLSTM improves comparative protein sequence categorization. The study improves computational bioinformatics for complex biological analysis. Good results from the ProtICNN-BiLSTM model improve protein sequence categorization. This powerful tool could improve medical and biological research. The breakthrough protein sequence classification model is ProtICNN-BiLSTM. Bayesian optimization, ICNN, and BiLSTM analyze biological data accurately.