BMC Medical Informatics and Decision Making最新文献

Background: Diabetic retinopathy (DR), a prevalent complication in patients with type 2 diabetes, has attracted increasing attention. Recent studies have explored a plausible association between retinopathy and significant liver fibrosis. The aim of this investigation was to develop a sophisticated machine learning (ML) model, leveraging comprehensive clinical datasets, to forecast the likelihood of significant liver fibrosis in patients with retinopathy and to interpret the ML model by applying the SHapley Additive exPlanations (SHAP) method.

Methods: This inquiry was based on data from the National Health and Nutrition Examination Survey 2005-2008 cohort. Utilizing the Fibrosis-4 index (FIB-4), liver fibrosis was stratified across a spectrum of grades (F0-F4). The severity of retinopathy was determined using retinal imaging and segmented into four discrete gradations. A ten-fold cross-validation approach was used to gauge the propensity towards liver fibrosis. Eight ML methodologies were used: Extreme Gradient Boosting, Random Forest, multilayer perceptron, Support Vector Machines, Logistic Regression (LR), Plain Bayes, Decision Tree, and k-nearest neighbors. The efficacy of these models was gauged using metrics, such as the area under the curve (AUC). The SHAP method was deployed to unravel the intricacies of feature importance and explicate the inner workings of the ML model.

Results: The analysis included 5,364 participants, of whom 2,116 (39.45%) exhibited notable liver fibrosis. Following random allocation, 3,754 individuals were assigned to the training set and 1,610 were allocated to the validation cohort. Nine variables were curated for integration into the ML model. Among the eight ML models scrutinized, the LR model attained zenith in both AUC (0.867, 95% CI: 0.855-0.878) and F1 score (0.749, 95% CI: 0.732-0.767). In internal validation, this model sustained its superiority, with an AUC of 0.850 and an F1 score of 0.736, surpassing all other ML models. The SHAP methodology unveils the foremost factors through importance ranking.

Conclusion: Sophisticated ML models were crafted using clinical data to discern the propensity for significant liver fibrosis in patients with retinopathy and to intervene early.

Practice implications: Improved early detection of liver fibrosis risk in retinopathy patients enhances clinical intervention outcomes.

Importance: The homepage of medical records holds significant importance for national performance assessments, DIP settlement lists, and DRG payments. Coders, as auditors of the codes, wield a crucial influence on the quality of the medical records' homepage.

Objective: To analyze the general situation of the allocation of medical record full-time coders in China.

Data source: CNKI, Wanfang, VIP, PubMed and other databases were searched from database inception to November 31, 2023.

Main outcomes and measures: The primary outcome was the allocation of medical records to full-time coders, with the workload of the coders being the primary focus. Secondary outcomes encompassed the professional background of the coders, including their academic qualifications, professional titles, possession of medical coding certificates, and years of experience in coding.

Results: Eleven studies, comprising data from 1783 hospitals and 4448 coders, were analyzed. Among the coders, 61% had a medical-related professional background, 62% held a bachelor's degree or higher, 54% possessed an intermediate title or higher, 61% had coding certificates, and 51% had less than 5 years of work experience. The summary findings regarding the number of coders and coded medical records in secondary and tertiary hospitals indicated an average discharge rate of 22,704.0 per hospital in China. The number of coded cases averaged around 11,300. Specifically, coders in tertiary hospitals coded approximately 12,049 medical records on average, while those in secondary hospitals coded around 7,399 medical records.

Conclusion and relevance: Our study highlights the shortage of medical record coding personnel in the majority of hospitals, coupled with a significant coding workload, low educational qualifications among staff, short working hours, and an imbalanced title structure. Given these findings, hospitals and relevant management authorities should prioritize the recruitment of highly educated professionals, streamline the assessment process for professional titles, alleviate the coding workload, and enhance coding quality.

Background: Post-stroke dementia (PSD), a common complication, diminishes rehabilitation efficacy and affects disease prognosis in stroke patients. Many factors may be related to PSD, including demographic, comorbidities, and examination characteristics. However, most existing methods are qualitative evaluations of independent factors, which ignore the interaction amongst various factors. Therefore, the purpose of this study is to explore the applicability of machine learning (ML) methods for predicting PSD.

Methods: 9 acceptable features were screened out by the Spearman correlation analysis and Boruta algorithm. We developed and evaluated 8 ML models: logistic regression, elastic net, k-nearest neighbors, decision tree, extreme gradient boosting, support vector machine, random forest, and multilayer perceptron.

Results: A total of 539 stroke patients were included in this study. Among the 8 models used to predict PSD, extreme gradient boosting and random forest showed the highest area under the curve (AUC) of the receiver operating characteristic curve (ROC), with values of 0.7287 and 0.7285, respectively. The most important features for predicting PSD included age, high sensitivity C-reactive protein, stroke side and location, and the occurrence of cerebral hemorrhage.

Conclusion: Our findings suggest that ML models, especially extreme gradient boosting, can best predict the risk of PSD.

Background: Clinical data warehouses provide harmonized access to healthcare data for medical researchers. Informatics for Integrating Biology and the Bedside (i2b2) is a well-established open-source solution with the major benefit that data representations can be tailored to support specific use cases. These data representations can be defined and improved via an iterative approach together with domain experts and the medical researchers using the platform. To facilitate these discussions, it is important to understand how users interact with the system.

Objective: The objective of this work was to develop metrics for describing user interactions with clinical data warehouses in general and i2b2 in particular. Moreover, we aimed to develop a dashboard featuring interactive visualizations that inform data engineers and data stewards about potential improvements.

Methods: We first identified metrics for different data usage dimensions and extracted the relevant metadata about previous user queries from the i2b2 database schema for further analysis. We then implemented associated visualizations in Python and integrated the results into an interactive dashboard using Dash.

Results: The identified categories of metrics include frequency of use, session duration, and use of functionality and features. We created a dashboard that extends our local i2b2 data warehouse platform, focusing on the latter category, further broken down into the number of queries, frequently queried concepts, and query complexity. The implementation is available as open-source software.

Conclusion: A range of metrics can be derived from metadata logged in the i2b2 database schema to provide data engineers and data stewards with a comprehensive understanding of how users interact with the platform. This can help to identify the strengths and limitations of specific instances of the platform for specific use cases and aid their iterative improvement.

Background: In older adults with hypertension, hip fractures accompanied by preoperative acute heart failure significantly elevate surgical risks and adverse outcomes, necessitating timely identification and management to improve patient outcomes.

Research objective: This study aims to enhance the early recognition of acute heart failure in older hypertensive adults prior to hip fracture surgery by developing a predictive model using logistic regression (LR) and machine learning methods, optimizing preoperative assessment and management.

Methods: Employing a retrospective study design, we analyzed hypertensive older adults who underwent hip fracture surgery at Hebei Medical University Third Hospital from January 2018 to December 2022. Predictive models were constructed using LASSO regression and multivariable logistic regression, evaluated via nomogram charts. Five additional machine learning methods were utilized, with variable importance assessed using SHAP values and the impact of key variables evaluated through multivariate correlation analysis and interaction effects.

Results: The study included 1,370 patients. LASSO regression selected 18 key variables, including sex, age, coronary heart disease, pulmonary infection, ventricular arrhythmias, acute myocardial infarction, and anemia. The logistic regression model demonstrated robust performance with an AUC of 0.753. Although other models outperformed it in sensitivity and F1 score, logistic regression's discriminative ability was significant for clinical decision-making. The Gradient Boosting Machine model, notable for a sensitivity of 95.2%, indicated substantial capability in identifying patients at risk, crucial for reducing missed diagnoses.

Conclusion: We developed and compared efficacy of predictive models using logistic regression and machine learning, interpreting them with SHAP values and analyzing key variable interactions. This offers a scientific basis for assessing preoperative heart failure risk in older adults with hypertension and hip fractures, providing significant guidance for individualized treatment strategies and underscoring the value of applying machine learning in clinical settings.

Background: Shared decision-making is recommended for stroke rehabilitation. However, the complexity of the rehabilitation modalities exposes patients to decision-making conflicts, exacerbates their disabilities, and diminishes their quality of life. This study aimed to explore the experiences and needs of older patients with stroke in China during rehabilitation decision-making, providing a reference for developing decision-support strategies.

Methods: A qualitative phenomenological design was used to explore the experiences and needs of older patients with stroke in China. Purposive sampling was used to recruit 31 older Chinese patients with stroke. The participants participated in face-to-face, semi-structured, and in-depth interviews. Data were analyzed using inductive thematic analysis.

Results: The key themes identified include (1) mixed feelings in shared decision-making, (2) multiple barriers hinder the possibility of participating in shared decision-making, (3) Delegating rehabilitation decisions to surrogates, (4) gaps between reality and expectation, and (5) decision fatigue from lack of continuity in the rehabilitation health care system.

Conclusions: Older patients with stroke in China have complex rehabilitation decision-making experiences and needs and face multiple obstacles when participating in shared decision-making. They lack an effective shared decision-making support system to assist them. Providing patients with comprehensive support (such as emotional and informational), strengthening the construction of a continuous rehabilitation system, alleviating economic pressure, and promoting patient participation in rehabilitation decision-making are necessary.

Deprivation of oxygen in an infant during and after birth leads to birth asphyxia, which is considered one of the leading causes of death in the neonatal period. Adequate resuscitation activities are performed immediately after birth to save the majority of newborns. The primary resuscitation activities include ventilation, stimulation, drying, suction, and chest compression. While resuscitation guidelines exist, little research has been conducted on measured resuscitation episodes. Objective data collected for measuring and registration of the executed resuscitation activities can be used to generate temporal timelines. This paper is primarily aimed to introduce methods for analyzing newborn resuscitation activity timelines, through visualization, aggregation, redundancy and dimensionality reduction. We are using two datasets: 1) from Stavanger University Hospital with 108 resuscitation episodes, and 2) from Haydom Lutheran Hospital with 76 episodes. The resuscitation activity timelines were manually annotated, but in future work we will use the proposed method on automatically generated timelines from video and sensor data. We propose an encoding generator with unique codes for combination of activities. A visualization of aggregated episodes is proposed using sparse nearest neighbor graph, shown to be useful to compare datasets and give insights. Finally, we propose a method consisting of an autoencoder trained for reducing redundancy in encoded resuscitation timeline descriptions, followed by a neighborhood component analysis for dimensionality reduction. Visualization of the resulting features shows very good class separability and potential for clustering the resuscitation files according to the outcome of the newborns as dead, admitted to NICU or normal. This shows great potential for extracting important resuscitation patterns when tested on larger datasets.

Background: Severe acute pancreatitis (SAP) can be fatal if left unrecognized and untreated. The purpose was to develop a machine learning (ML) model for predicting the 30-day all-cause mortality risk in SAP patients and to explain the most important predictors.

Methods: This research utilized six ML methods, including logistic regression (LR), k-nearest neighbors(KNN), support vector machines (SVM), naive Bayes (NB), random forests(RF), and extreme gradient boosting(XGBoost), to construct six predictive models for SAP. An extensive evaluation was conducted to determine the most effective model and then the Shapley Additive exPlanations (SHAP) method was applied to visualize key variables. Utilizing the optimized model, stratified predictions were made for patients with SAP. Further, the study employed multivariable Cox regression analysis and Kaplan-Meier survival curves, along with subgroup analysis, to explore the relationship between the machine learning-based score and 30-day mortality.

Results: Through LASSO regression and recursive feature elimination (RFE), 25 optimal feature variables are selected. The XGBoost model performed best, with an area under the curve (AUC) of 0.881, a sensitivity of 0.5714, a specificity of 0.9651 and an F1 score of 0.64. The first six most important feature variables were the use of vasopressor, high Charlson comorbidity index, low blood oxygen saturation, history of malignant tumor, hyperglycemia and high APSIII score. Based on the optimal threshold of 0.62, patients were divided into high and low-risk groups, and the 30-day survival rate in the high-risk group decreased significantly. COX regression analysis further confirmed the positive correlation between high-risk scores and 30-day mortality. In the subgroup analysis, the model showed good risk stratification ability in patients with different gender, renal replacement therapy and with or without a history of malignant tumor, but it was not effective in predicting peripheral vascular disease.

Conclusions: the XGBoost model effectively predicts the severity of SAP, serving as a valuable tool for clinicians to identify SAP early.

Clinical decision support systems are software tools that help clinicians to make medical decisions. However, their acceptance by clinicians is usually rather low. A known problem is that they often require clinicians to manually enter a lot of patient data, which is long and tedious. Existing solutions, such as the automatic data extraction from electronic health record, are not fully satisfying, because of low data quality and availability. In practice, many systems still include long questionnaire for data entry. In this paper, we propose an original solution to simplify patient data entry, using an adaptive questionnaire, i.e. a questionnaire that evolves during user interaction, showing or hiding questions dynamically. Considering a rule-based decision support systems, we designed methods for determining the relationships between rules and translating the system's clinical rules into display rules that determine the items to show in the questionnaire, and methods for determining the optimal order of priority among the items in the questionnaire. We applied this approach to a decision support system implementing STOPP/START v2, a guideline for managing polypharmacy. We show that it permits reducing by about two thirds the number of clinical conditions displayed in the questionnaire, both on clinical cases and real patient data. Presented to clinicians during focus group sessions, the adaptive questionnaire was found "pretty easy to use". In the future, this approach could be applied to other guidelines, and adapted for data entry by patients.