BMC Medical Informatics and Decision Making最新文献

{"title":"Hierarchical embedding attention for overall survival prediction in lung cancer from unstructured EHRs.","authors":"Domenico Paolo, Carlo Greco, Alessio Cortellini, Sara Ramella, Paolo Soda, Alessandro Bria, Rosa Sicilia","doi":"10.1186/s12911-025-02998-6","DOIUrl":"https://doi.org/10.1186/s12911-025-02998-6","url":null,"abstract":"<p><p>The automated processing of Electronic Health Records (EHRs) poses a significant challenge due to their unstructured nature, rich in valuable, yet disorganized information. Natural Language Processing (NLP), particularly Named Entity Recognition (NER), has been instrumental in extracting structured information from EHR data. However, existing literature primarly focuses on extracting handcrafted clinical features through NLP and NER methods without delving into their learned representations. In this work, we explore the untapped potential of these representations by considering their contextual richness and entity-specific information. Our proposed methodology extracts representations generated by a transformer-based NER model on EHRs data, combines them using a hierarchical attention mechanism, and employs the obtained enriched representation as input for a clinical prediction model. Specifically, this study addresses Overall Survival (OS) in Non-Small Cell Lung Cancer (NSCLC) using unstructured EHRs data collected from an Italian clinical centre encompassing 838 records from 231 lung cancer patients. Whilst our study is applied on EHRs written in Italian, it serves as use case to prove the effectiveness of extracting and employing high level textual representations that capture relevant information as named entities. Our methodology is interpretable because the hierarchical attention mechanism highlights the information in EHRs that the model considers the most crucial during the decision-making process. We validated this interpretability by measuring the agreement of domain experts on the importance assigned by the hierarchical attention mechanism to EHRs information through a questionnaire. Results demonstrate the effectiveness of our method, showcasing statistically significant improvements over traditional manually extracted clinical features.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"169"},"PeriodicalIF":3.3,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007135/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143974160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A machine learning-based severity stratification tool for high altitude pulmonary edema.","authors":"Luobu Gesang, Yangzong Suona, Zhuoga Danzeng, Bai Ci, Quzhen Gesang, WangJiu Cidan, Qiangba Dingzeng, Zhuoga Baima, Quzhen Zhaxi","doi":"10.1186/s12911-025-02992-y","DOIUrl":"https://doi.org/10.1186/s12911-025-02992-y","url":null,"abstract":"<p><p>This study aimed to identify key predictors for the severity of High Altitude Pulmonary Edema (HAPE) to assist clinicians in promptly recognizing severely affected patients in the emergency department, thereby reducing associated mortality rates. Multinomail logistic regression, random forest, and decision tree methods were utilized to determine important predictor variables and evaluate model performance. A total of 508 patients diagnosed with HAPE were included in the study, with 53 variables analyzed. Lung rales, sputum sputuming, heart rate, and oxygen saturation were identified as the most relevant predictors for the LASSO model. Subsequently, Multinomail logistic regression, decision tree, and random forest models were trained and evaluated using these factors on a test set. The random forest model showed the highest performance, with an accuracy of 77.94%, precision of 70.27%, recall of 68.22%, and F1 score of 68.96%, outperforming the other models. Further analysis revealed significant differences in predictive capabilities among the models for HAPE patients at varying severity levels. The random forest model demonstrated high predictive accuracy across all severity levels of HAPE, particularly excelling in identifying severely ill patients with an impressive AUC of 0.86. The study assessed the reliability and effectiveness of the HAPE severity scoring model by validating Multinomail logistic regression and random forest models. This study introduces a valuable screening tool for categorizing the severity of HAPE, aiding healthcare providers in recognizing individuals with severe HAPE, enabling prompt treatment and the formulation of suitable therapeutic approaches.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"171"},"PeriodicalIF":3.3,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12008950/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143977243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Applications of machine learning approaches for pediatric asthma exacerbation management: a systematic review.","authors":"Chunni Zhou, Liu Shuai, Hao Hu, Carolina Oi Lam Ung, Yunfeng Lai, Lijun Fan, Wei Du, Yan Wang, Meng Li","doi":"10.1186/s12911-025-02990-0","DOIUrl":"https://doi.org/10.1186/s12911-025-02990-0","url":null,"abstract":"<p><strong>Background: </strong>Pediatric asthma is a common chronic respiratory disease worldwide, and its acute exacerbation events significantly impact children's health and quality of life. Machine learning, an advanced data analysis technique, has shown great potential in healthcare applications in recent years. This systematic review aims to assess the application of ML techniques in pediatric asthma exacerbation and explore their effectiveness and potential value.</p><p><strong>Methods: </strong>Studies from four electronic databases, including PubMed, EBSCO, Elsevier, and Web of Science, from Jan 2000 to Jan 2025, were searched. Studies applying the ML methods for pediatric asthma exacerbation and published in English were eligible. The risk of bias and applicability of the included studies was assessed using the Effective Public Health Practice Project (EPHPP) quality assessment tool.</p><p><strong>Results: </strong>A total of 23 studies were selected for inclusion in this review, covering different ML models such as decision trees, neural networks, and support vector machines. These studies focused on analyzing risk factors for asthma exacerbation, diagnosing and predicting, optimizing and allocating healthcare resources, and comprehensive asthma management. The results show that ML techniques have significant advantages in the application of pediatric asthma exacerbation and in the provision of personalized health care.</p><p><strong>Conclusions: </strong>ML techniques show great promise for application in pediatric asthma exacerbations. With further research and clinical validation, these techniques are expected to provide strong support for diagnosis, personalized treatment, and long-term management of pediatric asthma exacerbation.</p><p><strong>Clinical trial number: </strong>Not applicable, Prospero registration number CRD42024559232.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"170"},"PeriodicalIF":3.3,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12008861/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143953950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A machine learning-based framework for predicting postpartum chronic pain: a retrospective study.","authors":"Fan Liu, Ting Li, Dongxu Zhou, Shengnan Shi, Xingrui Gong","doi":"10.1186/s12911-025-03004-9","DOIUrl":"https://doi.org/10.1186/s12911-025-03004-9","url":null,"abstract":"<p><strong>Background: </strong>Postpartum chronic pain is prevalent, affecting many women after delivery. Machine learning algorithms have been widely used in predicting postoperative conditions. We investigated the prevalence of and risk factors for postpartum chronic pain, and aimed to develop a machine learning model for its prediction.</p><p><strong>Methods: </strong>Pregnant women in our tertiary hospital were screened from July 2021 to June 2022. Postoperative pain intensity was assessed using the numerical rating scale at 1, 3, and 6 months after delivery. Six machine learning algorithms were benchmarked using the nested resampling method, and their performance was evaluated based on classification error (CE). The algorithm with the best performance evaluation was used to establish the model for predicting chronic pain 6 months after delivery. Shapley additive explanations analysis was used to assess the contribution of each variable to the model.</p><p><strong>Results: </strong>A total of 1,398 postpartum women were included for analysis, among whom 383 developed chronic pain 6 months after delivery. The least absolute shrinkage selection operator identified five relevant factors: numerical rating scale at 3 days after delivery, body mass index before delivery, newborn weight, multiparous delivery, and back pain during gestation. The CEs for the algorithms were as follows: K-nearest neighbor, 0.212; logistic regression, 0.342; linear discriminant analysis, 0.343; naive Bayes, 0.346; ranger, 0.219; and extreme gradient boosting model, 0.147. The extreme gradient boosting model exhibited the best performance (CE = 0.147, F1 = 0.851) and was selected for model establishment. Visualization using Shapley additive explanations facilitated the interpretation of the influence of the five variables in the model.</p><p><strong>Conclusions: </strong>The extreme gradient boosting algorithm, which incorporates five risk factors, demonstrated strong performance in predicting postpartum chronic pain.</p><p><strong>Trial registration: </strong>https//www.chictr.org.cn/ (ChiCTR2300070514).</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"168"},"PeriodicalIF":3.3,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007194/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143967770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated machine learning for early prediction of systemic inflammatory response syndrome in acute pancreatitis.","authors":"Rufa Zhang, Shiqi Zhu, Li Shi, Hao Zhang, Xiaodan Xu, Bo Xiang, Min Wang","doi":"10.1186/s12911-025-02997-7","DOIUrl":"https://doi.org/10.1186/s12911-025-02997-7","url":null,"abstract":"<p><strong>Background: </strong>Systemic inflammatory response syndrome (SIRS) is a frequent and serious complication of acute pancreatitis (AP), often associated with increased mortality. This study aims to leverage automated machine learning (AutoML) algorithms to create a model for the early and precise prediction of SIRS in AP.</p><p><strong>Methods: </strong>This study retrospectively analyzed patients diagnosed with AP across multiple centers from January 2017 to December 2021. Data from the First Affiliated Hospital of Soochow University and Changshu Hospital were used for training and internal validation, while testing was conducted with data from the Second Affiliated Hospital. Predictive models were constructed and validated using the least absolute shrinkage and selection operator (LASSO) and AutoML. A nomogram was developed based on multivariable logistic regression (LR) analysis, and the performance of the models was assessed through receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Additionally, the AutoML model's effectiveness and interpretability were assessed through DCA, feature importance, SHapley Additive exPlanation (SHAP) plots, and locally interpretable model-agnostic explanations (LIME).</p><p><strong>Results: </strong>A total of 1,224 patients were included, with 812 in the training cohort, 200 in validation, and 212 in testing. SIRS occurred in 33.7% of the training cohort, 34.0% in validation, and 22.2% in testing. AutoML models outperformed traditional LR, with the deep learning (DL) model achieving an area under the ROC curve of 0.843 in the training set, and 0.848 and 0.867 in validation and testing, respectively.</p><p><strong>Conclusion: </strong>The AutoML model using the DL algorithm is clinically significant for the early prediction of SIRS in AP.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"167"},"PeriodicalIF":3.3,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12007213/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143954778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lactate dehydrogenase to albumin ratio and poor prognosis after thrombolysis in ischemic stroke patients: developing a novel nomogram.","authors":"Xiao-Dan Zhang, Zong-Yong Zhang, Ming-Pei Zhao, Xiang-Tao Zhang, Neng Wang, Hong-Zhi Gao, Yuan-Xiang Lin, Zong-Qing Zheng","doi":"10.1186/s12911-025-02991-z","DOIUrl":"https://doi.org/10.1186/s12911-025-02991-z","url":null,"abstract":"<p><strong>Background: </strong>Ischemic stroke (IS) is associated with high disability and mortality. This study aimed to identify the prognostic predictors and develop a nomogram for a prediction model for ischemic stroke patients after thrombolysis.</p><p><strong>Methods: </strong>We retrospectively analyzed data from 359 IS patients who underwent thrombolysis. Clinical characteristics, laboratory parameters, and prognosis data were collected. One-third of the subjects were randomly selected as a validation set (n = 108) for internal validation. Logistic regression analysis was used to derive independent risk indicators. A nomogram was constructed using these indicators, and the performance of the nomogram was assessed by the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC). The agreement of the model predictions with actual observations was assessed via calibration curves, and the clinical utility of the nomogram was assessed via decision curve analysis.</p><p><strong>Results: </strong>Multivariate logistic regression analysis showed that age, leukocytes, Lactate Dehydrogenase to Albumin Ratio (LAR) and NIHSS were independent predictors of three-month post-thrombolysis prognosis in IS patients. We created a nomogram based on the weighting coefficients of these factors. The AUC curves showed that our model including age, leukocytes, LAR and NIHSS was more accurate in predicting prognosis than a single factor. The calibration curves showed a good fit between actual and predicted probabilities in both the training and validation groups.</p><p><strong>Conclusion: </strong>LAR has a good predictive power for the prognosis of IS patients 3 months after thrombolytic therapy and can be used as a new clinical indicator to establish a practical nomogram.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"166"},"PeriodicalIF":3.3,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12001606/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143977446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CRISP: A causal relationships-guided deep learning framework for advanced ICU mortality prediction.","authors":"Linna Wang, Xinyu Guo, Haoyue Shi, Yuehang Ma, Han Bao, Lihua Jiang, Li Zhao, Ziliang Feng, Tao Zhu, Li Lu","doi":"10.1186/s12911-025-02981-1","DOIUrl":"https://doi.org/10.1186/s12911-025-02981-1","url":null,"abstract":"<p><strong>Background: </strong>Mortality prediction is critical in clinical care, particularly in intensive care units (ICUs), where early identification of high-risk patients can inform treatment decisions. While deep learning (DL) models have demonstrated significant potential in this task, most suffer from limited generalizability, which hinders their widespread clinical application. Additionally, the class imbalance in electronic health records (EHRs) complicates model training. This study aims to develop a causally-informed prediction model that incorporates underlying causal relationships to mitigate class imbalance, enabling more stable mortality predictions.</p><p><strong>Methods: </strong>This study introduces the CRISP model (Causal Relationship Informed Superior Prediction), which leverages native counterfactuals to augment the minority class and constructs patient representations by incorporating causal structures to enhance mortality prediction. Patient data were obtained from the public MIMIC-III and MIMIC-IV databases, as well as an additional dataset from the West China Hospital of Sichuan University (WCHSU).</p><p><strong>Results: </strong>A total of 69,190 ICU cases were included, with 30,844 cases from MIMIC-III, 27,362 cases from MIMIC-IV, and 10,984 cases from WCHSU. The CRISP model demonstrated stable performance in mortality prediction across the 3 datasets, achieving AUROC (0.9042-0.9480) and AUPRC (0.4771-0.7611). CRISP's data augmentation module showed predictive performance comparable to commonly used interpolation-based oversampling techniques.</p><p><strong>Conclusion: </strong>CRISP achieves better generalizability across different patient groups, compared to various baseline algorithms, thereby enhancing the practical application of DL in clinical decision support.</p><p><strong>Trial registration: </strong>Trial registration information for the WCHSU data is available on the Chinese Clinical Trial Registry website ( http://www.chictr.org.cn ), with the registration number ChiCTR1900025160. The recruitment period for the data was from August 5, 2019, to August 31, 2021.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"165"},"PeriodicalIF":3.3,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12001402/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143964827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative evaluation of artificial intelligence models GPT-4 and GPT-3.5 in clinical decision-making in sports surgery and physiotherapy: a cross-sectional study.","authors":"Sönmez Saglam, Veysel Uludag, Zekeriya Okan Karaduman, Mehmet Arıcan, Mücahid Osman Yücel, Raşit Emin Dalaslan","doi":"10.1186/s12911-025-02996-8","DOIUrl":"https://doi.org/10.1186/s12911-025-02996-8","url":null,"abstract":"<p><strong>Background: </strong>The integration of artificial intelligence (AI) in healthcare has rapidly expanded, particularly in clinical decision-making. Large language models (LLMs) such as GPT-4 and GPT-3.5 have shown potential in various medical applications, including diagnostics and treatment planning. However, their efficacy in specialized fields like sports surgery and physiotherapy remains underexplored. This study aims to compare the performance of GPT-4 and GPT-3.5 in clinical decision-making within these domains using a structured assessment approach.</p><p><strong>Methods: </strong>This cross-sectional study included 56 professionals specializing in sports surgery and physiotherapy. Participants evaluated 10 standardized clinical scenarios generated by GPT-4 and GPT-3.5 using a 5-point Likert scale. The scenarios encompassed common musculoskeletal conditions, and assessments focused on diagnostic accuracy, treatment appropriateness, surgical technique detailing, and rehabilitation plan suitability. Data were collected anonymously via Google Forms. Statistical analysis included paired t-tests for direct model comparisons, one-way ANOVA to assess performance across multiple criteria, and Cronbach's alpha to evaluate inter-rater reliability.</p><p><strong>Results: </strong>GPT-4 significantly outperformed GPT-3.5 across all evaluated criteria. Paired t-test results (t(55) = 10.45, p < 0.001) demonstrated that GPT-4 provided more accurate diagnoses, superior treatment plans, and more detailed surgical recommendations. ANOVA results confirmed the higher suitability of GPT-4 in treatment planning (F(1, 55) = 35.22, p < 0.001) and rehabilitation protocols (F(1, 55) = 32.10, p < 0.001). Cronbach's alpha values indicated higher internal consistency for GPT-4 (α = 0.478) compared to GPT-3.5 (α = 0.234), reflecting more reliable performance.</p><p><strong>Conclusions: </strong>GPT-4 demonstrates superior performance compared to GPT-3.5 in clinical decision-making for sports surgery and physiotherapy. These findings suggest that advanced AI models can aid in diagnostic accuracy, treatment planning, and rehabilitation strategies. However, AI should function as a decision-support tool rather than a substitute for expert clinical judgment. Future studies should explore the integration of AI into real-world clinical workflows, validate findings using larger datasets, and compare additional AI models beyond the GPT series.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"163"},"PeriodicalIF":3.3,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11998439/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143984150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards interpretable sleep stage classification with a multi-stream fusion network.","authors":"Jingrui Chen, Xiaomao Fan, Ruiquan Ge, Jing Xiao, Ruxin Wang, Wenjun Ma, Ye Li","doi":"10.1186/s12911-025-02995-9","DOIUrl":"https://doi.org/10.1186/s12911-025-02995-9","url":null,"abstract":"<p><p>Sleep stage classification is a significant measure in assessing sleep quality and diagnosing sleep disorders. Many researchers have investigated automatic sleep stage classification methods and achieved promising results. However, these methods ignored the heterogeneous information fusion of the spatial-temporal and spectral-temporal features among multiple-channel sleep monitoring signals. In this study, we propose an interpretable multi-stream fusion network, named MSF-SleepNet, for sleep stage classification. Specifically, we employ Chebyshev graph convolution and temporal convolution to obtain the spatial-temporal features from body-topological information of sleep monitoring signals. Meanwhile, we utilize a short time Fourier transform and gated recurrent unit to learn the spectral-temporal features from sleep monitoring signals. After fusing the spatial-temporal and spectral-temporal features, we use a contrastive learning scheme to enhance the differences in feature patterns of sleep monitoring signals across various sleep stages. Finally, LIME is employed to improve the interpretability of MSF-SleepNet. Experimental results on ISRUC-S1 and ISRUC-S3 datasets show that MSF-SleepNet achieves competitive results and is superior to its state-of-the-art counterparts on most of performance metrics.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"164"},"PeriodicalIF":3.3,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11998347/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143974866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the efficacy of microwave ablation of benign thyroid nodules from ultrasound images using deep convolutional neural networks.","authors":"Enock Adjei Agyekum, Yu-Guo Wang, Eliasu Issaka, Yong-Zhen Ren, Gongxun Tan, Xiangjun Shen, Xiao-Qin Qian","doi":"10.1186/s12911-025-02989-7","DOIUrl":"https://doi.org/10.1186/s12911-025-02989-7","url":null,"abstract":"<p><strong>Background: </strong>Thyroid nodules are frequent in clinical settings, and their diagnosis in adults is growing, with some persons experiencing symptoms. Ultrasound-guided thermal ablation can shrink nodules and alleviate discomfort. Because the degree and rate of lesion absorption vary greatly between individuals, there is no reliable model for predicting the therapeutic efficacy of thermal ablation.</p><p><strong>Methods: </strong>Five convolutional neural network models including VGG19, Resnet 50, EfficientNetB1, EfficientNetB0, and InceptionV3, pre-trained with ImageNet, were compared for predicting the efficacy of ultrasound-guided microwave ablation (MWA) for benign thyroid nodules using ultrasound data. The patients were randomly assigned to one of two data sets: training (70%) or validation (30%). Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve (AUC) were all used to assess predictive performance.</p><p><strong>Results: </strong>In the validation set, fine-tuned EfficientNetB1 performed best, with an AUC of 0.85 and an ACC of 0.79.</p><p><strong>Conclusions: </strong>The study found that our deep learning model accurately predicts nodules with VRR < 50% after a single MWA session. Indeed, when thermal therapies compete with surgery, anticipating which nodules will be poor responders provides useful information that may assist physicians and patients determine whether thermal ablation or surgery is the preferable option. This was a preliminary study of deep learning, with a gap in actual clinical applications. As a result, more in-depth study should be undertaken to develop deep-learning models that can better help clinics. Prospective studies are expected to generate high-quality evidence and improve clinical performance in subsequent research.</p>","PeriodicalId":9340,"journal":{"name":"BMC Medical Informatics and Decision Making","volume":"25 1","pages":"161"},"PeriodicalIF":3.3,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11987319/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144062335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}