BMC Medical Informatics and Decision Making最新文献

Responding to the rising global prevalence of noncommunicable diseases (NCDs) requires improvements in the management of high blood pressure. Therefore, this study aims to develop an explainable machine learning model for predicting high blood pressure, a key NCD risk factor, using data from the STEPwise approach to NCD risk factor surveillance (STEPS) surveys. Nationally representative samples of adults aged 18-69 years were acquired from 57 countries spanning six World Health Organization (WHO) regions. Data harmonization and processing were performed to standardize the selected predictors and synchronize features across countries, yielding 41 variables, including demographic, behavioural, physical, and biochemical factors. Five machine learning models - logistic regression, k-nearest neighbours, random forest, XGBoost, and a fully connected neural network - were trained and evaluated at global, regional, and country-specific levels using an 80/20 train-test split. The models' performance was assessed using accuracy, precision, recall, and F1 score. Feature importance analysis identified age, weight, heart rate, waist circumference, and height as key predictors of blood pressure. Across the 57 countries studied, model performances varied considerably, with accuracy ranging from as low as 58.96% in some models for specific countries to as high as 81.41% in others, underscoring the need for region and country-specific adaptations in modelling approaches. The explainable model offers an opportunity for population-level screening and continuous risk assessment in resource-limited settings.

Background: The increasing demand for remote medical care, driven by digital healthcare advancements and the COVID-19 pandemic, necessitates effective solutions tailored to patients and healthcare practitioners. Co-design, involving collaboration between software developers, patients, and healthcare practitioners, prioritizes end-user needs. Research indicates that integrating patient perspectives enhances user experience and usability. However, its application in healthcare has been limited to small projects. This work focuses on co-designing a technological solution to enhance the monitoring and visual rehabilitation of individuals with Age-Related Macular Degeneration (AMD), a condition that significantly impacts the quality of life in people over 60. Current vision rehabilitation systems lack personalization, motivation, and effective progress monitoring. Involving patients and healthcare practitioners in the design process aims to ensure the final product meets their needs.

Methods: The project employs iterative and collaborative principles, involving a vision rehabilitation expert and two AMD patients as active users in the application's development and validation. The process begins by establishing requirements for user accounts and rehabilitation exercises. It continues with an initial approach extended through user validation. Co-design is facilitated by specific workshops marking each project iteration, totaling four workshops, along with continuous communication sessions between experts and developers to validate design decisions. Initial requirements gathering and constant feedback from end-users, the visual rehabilitator, and patients are crucial for refining the product effectively.

Results: The workshops produced a prototype featuring a test to monitor changes and progression and 15 visual rehabilitation exercises. Numerous patient and vision rehabilitation-driven software modifications led to a final design that is responsive and adaptive to end-user needs.

Conclusions: The Rehab-AMD pilot project aims to develop a collaborative and adaptive software solution for AMD rehabilitation by actively involving stakeholders and applying iterative design principles. Co-design in the Rehab-AMD solution proves to be a methodology that identifies usability issues and needs from the initial design stages. This approach ensures that software developers create a final product that is genuinely useful and manageable for people with AMD and the targeted vision rehabilitators.

Background: Maxillary expansion is an important treatment method for maxillary transverse hypoplasia. Different methods of maxillary expansion should be carried out depending on the midpalatal suture maturation levels, and the diagnosis was validated by palatal plane cone beam computed tomography (CBCT) images by orthodontists, while such a method suffered from low efficiency and strong subjectivity. This study develops and evaluates an enhanced vision transformer (ViT) to automatically classify CBCT images of midpalatal sutures with different maturation stages.

Methods: In recent years, the use of convolutional neural network (CNN) to classify images of midpalatal suture with different maturation stages has brought positive significance to the decision of the clinical maxillary expansion method. However, CNN cannot adequately learn the long-distance dependencies between images and features, which are also required for global recognition of midpalatal suture CBCT images. The Self-Attention of ViT has the function of capturing the relationship between long-distance pixels of the image. However, it lacks the inductive bias of CNN and needs more data training. To solve this problem, a CNN-enhanced ViT model based on transfer learning is proposed to classify midpalatal suture CBCT images. In this study, 2518 CBCT images of the palate plane are collected, and the images are divided into 1259 images as the training set, 506 images as the verification set, and 753 images as the test set. After the training set image preprocessing, the CNN-enhanced ViT model is trained and adjusted, and the generalization ability of the model is tested on the test set.

Results: The classification accuracy of our proposed ViT model is 95.75%, and its Macro-averaging Area under the receiver operating characteristic Curve (AUC) and Micro-averaging AUC are 97.89% and 98.36% respectively on our data test set. The classification accuracy of the best performing CNN model EfficientnetV2_S was 93.76% on our data test set. The classification accuracy of the clinician is 89.10% on our data test set.

Conclusions: The experimental results show that this method can effectively complete CBCT images classification of midpalatal suture maturation stages, and the performance is better than a clinician. Therefore, the model can provide a valuable reference for orthodontists and assist them in making correct a diagnosis.

Background: Electronic health records (EHRs) are currently gaining popularity in emerging economies because they provide options for exchanging patient data, increasing operational efficiency, and improving patient outcomes. This study examines how service providers at Ghana's Komfo Anokye Teaching Hospital adopt and use an electronic health records (EHRs) system. The emphasis is on identifying factors impacting adoption and the problems that healthcare personnel encounter in efficiently using the EHRs system.

Method: A quantitative cross-sectional technique was utilised to collect data from 234 trauma and emergency department staff members via standardised questionnaires. The participants were selected using the purposive sampling method. The Pearson Chi-square Test was used to examine the relationship between respondents' acceptability and use of EHRs.

Results: The study discovered that a sizable number of respondents (86.8%) embraced and actively used the EHRs system. However, other issues were noted, including insufficient system training and malfunctions (35.9%), power outages (18.8%), privacy concerns (9.4%), and insufficient maintenance (4.7%). The respondents' comfortability in using the electronic health record system (X²=11.30, p=0.001), system dependability (X²=30.74, p=0.0001), and EHR's ability to reduce patient waiting time (X²=14.39, p=0.0001) were all strongly associated with their degree of satisfaction with the system. Furthermore, respondents who said elects increase patient care (X²= 75.59, p = 0.0001) and income creation (X²= 8.48, p = 0.004), which is related to the acceptability of the electronic health records system.

Conclusion: The study revealed that comfort, reliability, and improved care quality all had an impact on the EHRs system's acceptability and utilization. Challenges, including equipment malfunctions and power outages, were found. Continuous professional training was emphasized as a means of increasing employee confidence, as did the construction of a power backup system to combat disruptions. Patient data privacy was highlighted. In conclusion, this study highlights the relevance of EHRs system adoption and usability in healthcare. While the benefits are obvious, addressing obstacles through training, technical support, and infrastructure improvements is critical for increasing system effectiveness.

Background: Patients with airway stenosis (AS) are associated with considerable morbidity and mortality after lung transplantation (LTx). This study aims to develop and validate machine learning (ML) models to predict AS requiring clinical intervention in patients after LTx.

Methods: Patients who underwent LTx between January 2017 and December 2019 were reviewed. The conventional logistic regression (LR) model was fitted by the independent risk factors which were determined by multivariate LR. The optimal ML model was determined based on 7 feature selection methods and 8 ML algorithms. Model performance was assessed by the area under the curve (AUC) and brier score, which were internally validated by the bootstrap method.

Results: A total of 381 LTx patients were included, and 40 (10.5%) patients developed AS. Multivariate analysis indicated that male, pulmonary arterial hypertension, and postoperative 6-min walking test were significantly associated with AS (all P < 0.001). The conventional LR model showed performance with an AUC of 0.689 and brier score of 0.091. In total, 56 ML models were developed and the optimal ML model was the model fitted using a random forest algorithm with a determination coefficient feature selection method. The optimal model exhibited the highest AUC and brier score values of 0.760 (95% confidence interval [CI], 0.666-0.864) and 0.085 (95% CI, 0.058-0.117) among all ML models, which was superior to the conventional LR model.

Conclusions: The optimal ML model, which was developed by clinical characteristics, allows for the satisfactory prediction of AS in patients after LTx.

Problem: Sepsis, a life-threatening condition, accounts for the deaths of millions of people worldwide. Accurate prediction of sepsis outcomes is crucial for effective treatment and management. Previous studies have utilized machine learning for prognosis, but have limitations in feature sets and model interpretability.

Aim: This study aims to develop a machine learning model that enhances prediction accuracy for sepsis outcomes using a reduced set of features, thereby addressing the limitations of previous studies and enhancing model interpretability.

Methods: This study analyzes intensive care patient outcomes using the MIMIC-IV database, focusing on adult sepsis cases. Employing the latest data extraction tools, such as Google BigQuery, and following stringent selection criteria, we selected 38 features in this study. This selection is also informed by a comprehensive literature review and clinical expertise. Data preprocessing included handling missing values, regrouping categorical variables, and using the Synthetic Minority Over-sampling Technique (SMOTE) to balance the data. We evaluated several machine learning models: Decision Trees, Gradient Boosting, XGBoost, LightGBM, Multilayer Perceptrons (MLP), Support Vector Machines (SVM), and Random Forest. The Sequential Halving and Classification (SHAC) algorithm was used for hyperparameter tuning, and both train-test split and cross-validation methodologies were employed for performance and computational efficiency.

Results: The Random Forest model was the most effective, achieving an area under the receiver operating characteristic curve (AUROC) of 0.94 with a confidence interval of ±0.01. This significantly outperformed other models and set a new benchmark in the literature. The model also provided detailed insights into the importance of various clinical features, with the Sequential Organ Failure Assessment (SOFA) score and average urine output being highly predictive. SHAP (Shapley Additive Explanations) analysis further enhanced the model's interpretability, offering a clearer understanding of feature impacts.

Conclusion: This study demonstrates significant improvements in predicting sepsis outcomes using a Random Forest model, supported by advanced machine learning techniques and thorough data preprocessing. Our approach provided detailed insights into the key clinical features impacting sepsis mortality, making the model both highly accurate and interpretable. By enhancing the model's practical utility in clinical settings, we offer a valuable tool for healthcare professionals to make data-driven decisions, ultimately aiming to minimize sepsis-induced fatalities.

Background and aims: Systematic reviews and medical guidelines are widely used in clinical practice. However, these are often not up-to-date and focussed on the average patient. We therefore aimed to evaluate a guideline add-on, TherapySelector (TS), which is based on monthly updated data of all available high-quality studies, classified in specific patient profiles.

Methods: We evaluated the TS for the treatment of hepatitis C (HCV) in an international cohort of patients treated with direct-acting antivirals between 2015 and 2020. The primary outcome was the number of patients receiving one of the two preferred treatment options of the HCV TS, based on the highest level of evidence, cure rate, absence of ribavirin-associated adverse effects, and treatment duration.

Results: We enrolled 567 patients. The number of patients treated with one of the two preferred treatment options according to the HCV TS ranged between 27% (2015) and 60% (2020; p < 0.001). Most of the patients received a regimen with a longer treatment-duration (up to 34%) and/or addition of ribavirin (up to 14%). The effect on the expected cure-rate was minimal (1-6% higher) when the first preferred TherapySelector option was given compared to the actual treatment.

Conclusions: Medical decision-making can be optimised by a guideline add-on; in HCV its use appears to minimise adverse effects and cost. The use of such an add-on might have a greater impact in diseases with suboptimal cure-rates, high costs or adverse effects, for which treatment options rely on specific patient characteristics.

Background: There is a growing demand for advanced methods to improve the understanding and prediction of illnesses. This study focuses on Sepsis, a critical response to infection, aiming to enhance early detection and mortality prediction for Sepsis-3 patients to improve hospital resource allocation.

Methods: In this study, we developed a Machine Learning (ML) framework to predict the 30-day mortality rate of ICU patients with Sepsis-3 using the MIMIC-III database. Advanced big data extraction tools like Snowflake were used to identify eligible patients. Decision tree models and Entropy Analyses helped refine feature selection, resulting in 30 relevant features curated with clinical experts. We employed the Light Gradient Boosting Machine (LightGBM) model for its efficiency and predictive power.

Results: The study comprised a cohort of 9118 Sepsis-3 patients. Our preprocessing techniques significantly improved both the AUC and accuracy metrics. The LightGBM model achieved an impressive AUC of 0.983 (95% CI: [0.980-0.990]), an accuracy of 0.966, and an F1-score of 0.910. Notably, LightGBM showed a substantial 6% improvement over our best baseline model and a 14% enhancement over the best existing literature. These advancements are attributed to (I) the inclusion of the novel and pivotal feature Hospital Length of Stay (HOSP_LOS), absent in previous studies, and (II) LightGBM's gradient boosting architecture, enabling robust predictions with high-dimensional data while maintaining computational efficiency, as demonstrated by its learning curve.

Conclusions: Our preprocessing methodology reduced the number of relevant features and identified a crucial feature overlooked in previous studies. The proposed model demonstrated high predictive power and generalization capability, highlighting the potential of ML in ICU settings. This model can streamline ICU resource allocation and provide tailored interventions for Sepsis-3 patients.