-
Journal of Clinical Medicine May 2024Large language models (LLMs) represent a recent advancement in artificial intelligence with medical applications across various healthcare domains. The objective of... (Review)
Review
Large language models (LLMs) represent a recent advancement in artificial intelligence with medical applications across various healthcare domains. The objective of this review is to highlight how LLMs can be utilized by clinicians and surgeons in their everyday practice. A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Six databases were searched to identify relevant articles. Eligibility criteria emphasized articles focused primarily on clinical and surgical applications of LLMs. The literature search yielded 333 results, with 34 meeting eligibility criteria. All articles were from 2023. There were 14 original research articles, four letters, one interview, and 15 review articles. These articles covered a wide variety of medical specialties, including various surgical subspecialties. : LLMs have the potential to enhance healthcare delivery. In clinical settings, LLMs can assist in diagnosis, treatment guidance, patient triage, physician knowledge augmentation, and administrative tasks. In surgical settings, LLMs can assist surgeons with documentation, surgical planning, and intraoperative guidance. However, addressing their limitations and concerns, particularly those related to accuracy and biases, is crucial. LLMs should be viewed as tools to complement, not replace, the expertise of healthcare professionals.
PubMed: 38892752
DOI: 10.3390/jcm13113041 -
Frontiers in Cardiovascular Medicine 2024In recent years, the use of artificial intelligence (AI) models to generate individualised risk assessments and predict patient outcomes post-Transcatheter Aortic Valve...
OBJECTIVES
In recent years, the use of artificial intelligence (AI) models to generate individualised risk assessments and predict patient outcomes post-Transcatheter Aortic Valve Implantation (TAVI) has been a topic of increasing relevance in literature. This study aims to evaluate the predictive accuracy of AI algorithms in forecasting post-TAVI mortality as compared to traditional risk scores.
METHODS
Following the Preferred Reporting Items for Systematic Reviews and Meta-analyses for Systematic Reviews (PRISMA) standard, a systematic review was carried out. We searched four databases in total-PubMed, Medline, Embase, and Cochrane-from 19 June 2023-24 June, 2023.
RESULTS
From 2,239 identified records, 1,504 duplicates were removed, 735 manuscripts were screened, and 10 studies were included in our review. Our pooled analysis of 5 studies and 9,398 patients revealed a significantly higher mean area under curve (AUC) associated with AI mortality predictions than traditional score predictions (MD: -0.16, CI: -0.22 to -0.10, < 0.00001). Subgroup analyses of 30-day mortality (MD: -0.08, CI: -0.13 to -0.03, = 0.001) and 1-year mortality (MD: -0.18, CI: -0.27 to -0.10, < 0.0001) also showed significantly higher mean AUC with AI predictions than traditional score predictions. Pooled mean AUC of all 10 studies and 22,933 patients was 0.79 [0.73, 0.85].
CONCLUSION
AI models have a higher predictive accuracy as compared to traditional risk scores in predicting post-TAVI mortality. Overall, this review demonstrates the potential of AI in achieving personalised risk assessment in TAVI patients.
REGISTRATION AND PROTOCOL
This systematic review and meta-analysis was registered under the International Prospective Register of Systematic Reviews (PROSPERO), under the registration name "All-Cause Mortality in Transcatheter Aortic Valve Replacement Assessed by Artificial Intelligence" and registration number CRD42023437705. A review protocol was not prepared. There were no amendments to the information provided at registration.
SYSTEMATIC REVIEW REGISTRATION
https://www.crd.york.ac.uk/, PROSPERO (CRD42023437705).
PubMed: 38883982
DOI: 10.3389/fcvm.2024.1343210 -
JMIR AI Dec 2023An early warning tool to predict attacks could enhance asthma management and reduce the likelihood of serious consequences. Electronic health records (EHRs) providing... (Review)
Review
BACKGROUND
An early warning tool to predict attacks could enhance asthma management and reduce the likelihood of serious consequences. Electronic health records (EHRs) providing access to historical data about patients with asthma coupled with machine learning (ML) provide an opportunity to develop such a tool. Several studies have developed ML-based tools to predict asthma attacks.
OBJECTIVE
This study aims to critically evaluate ML-based models derived using EHRs for the prediction of asthma attacks.
METHODS
We systematically searched PubMed and Scopus (the search period was between January 1, 2012, and January 31, 2023) for papers meeting the following inclusion criteria: (1) used EHR data as the main data source, (2) used asthma attack as the outcome, and (3) compared ML-based prediction models' performance. We excluded non-English papers and nonresearch papers, such as commentary and systematic review papers. In addition, we also excluded papers that did not provide any details about the respective ML approach and its result, including protocol papers. The selected studies were then summarized across multiple dimensions including data preprocessing methods, ML algorithms, model validation, model explainability, and model implementation.
RESULTS
Overall, 17 papers were included at the end of the selection process. There was considerable heterogeneity in how asthma attacks were defined. Of the 17 studies, 8 (47%) studies used routinely collected data both from primary care and secondary care practices together. Extreme imbalanced data was a notable issue in most studies (13/17, 76%), but only 38% (5/13) of them explicitly dealt with it in their data preprocessing pipeline. The gradient boosting-based method was the best ML method in 59% (10/17) of the studies. Of the 17 studies, 14 (82%) studies used a model explanation method to identify the most important predictors. None of the studies followed the standard reporting guidelines, and none were prospectively validated.
CONCLUSIONS
Our review indicates that this research field is still underdeveloped, given the limited body of evidence, heterogeneity of methods, lack of external validation, and suboptimally reported models. We highlighted several technical challenges (class imbalance, external validation, model explanation, and adherence to reporting guidelines to aid reproducibility) that need to be addressed to make progress toward clinical adoption.
PubMed: 38875586
DOI: 10.2196/46717 -
JMIR AI Nov 2023There is a dearth of knowledge on reliable adherence prediction measures in behavior change support systems (BCSSs). Existing reviews have predominately focused on... (Review)
Review
BACKGROUND
There is a dearth of knowledge on reliable adherence prediction measures in behavior change support systems (BCSSs). Existing reviews have predominately focused on self-reporting measures of adherence. These measures are susceptible to overestimation or underestimation of adherence behavior.
OBJECTIVE
This systematic review seeks to identify and summarize trends in the use of machine learning approaches to predict adherence to BCSSs.
METHODS
Systematic literature searches were conducted in the Scopus and PubMed electronic databases between January 2011 and August 2022. The initial search retrieved 2182 journal papers, but only 11 of these papers were eligible for this review.
RESULTS
A total of 4 categories of adherence problems in BCSSs were identified: adherence to digital cognitive and behavioral interventions, medication adherence, physical activity adherence, and diet adherence. The use of machine learning techniques for real-time adherence prediction in BCSSs is gaining research attention. A total of 13 unique supervised learning techniques were identified and the majority of them were traditional machine learning techniques (eg, support vector machine). Long short-term memory, multilayer perception, and ensemble learning are currently the only advanced learning techniques. Despite the heterogeneity in the feature selection approaches, most prediction models achieved good classification accuracies. This indicates that the features or predictors used were a good representation of the adherence problem.
CONCLUSIONS
Using machine learning algorithms to predict the adherence behavior of a BCSS user can facilitate the reinforcement of adherence behavior. This can be achieved by developing intelligent BCSSs that can provide users with more personalized, tailored, and timely suggestions.
PubMed: 38875538
DOI: 10.2196/46779 -
Journal of the American Heart... Jun 2024Enhanced detection of large vessel occlusion (LVO) through machine learning (ML) for acute ischemic stroke appears promising. This systematic review explored the... (Meta-Analysis)
Meta-Analysis
Systematic Review and Meta-Analysis of Prehospital Machine Learning Scores as Screening Tools for Early Detection of Large Vessel Occlusion in Patients With Suspected Stroke.
BACKGROUND
Enhanced detection of large vessel occlusion (LVO) through machine learning (ML) for acute ischemic stroke appears promising. This systematic review explored the capabilities of ML models compared with prehospital stroke scales for LVO prediction.
METHODS AND RESULTS
Six bibliographic databases were searched from inception until October 10, 2023. Meta-analyses pooled the model performance using area under the curve (AUC), sensitivity, specificity, and summary receiver operating characteristic curve. Of 1544 studies screened, 8 retrospective studies were eligible, including 32 prehospital stroke scales and 21 ML models. Of the 9 prehospital scales meta-analyzed, the Rapid Arterial Occlusion Evaluation had the highest pooled AUC (0.82 [95% CI, 0.79-0.84]). Support Vector Machine achieved the highest AUC of 9 ML models included (pooled AUC, 0.89 [95% CI, 0.88-0.89]). Six prehospital stroke scales and 10 ML models were eligible for summary receiver operating characteristic analysis. Pooled sensitivity and specificity for any prehospital stroke scale were 0.72 (95% CI, 0.68-0.75) and 0.77 (95% CI, 0.72-0.81), respectively; summary receiver operating characteristic curve AUC was 0.80 (95% CI, 0.76-0.83). Pooled sensitivity for any ML model for LVO was 0.73 (95% CI, 0.64-0.79), specificity was 0.85 (95% CI, 0.80-0.89), and summary receiver operating characteristic curve AUC was 0.87 (95% CI, 0.83-0.89).
CONCLUSIONS
Both prehospital stroke scales and ML models demonstrated varying accuracies in predicting LVO. Despite ML potential for improved LVO detection in the prehospital setting, application remains limited by the absence of prospective external validation, limited sample sizes, and lack of real-world performance data in a prehospital setting.
Topics: Humans; Machine Learning; Emergency Medical Services; Early Diagnosis; Stroke; Ischemic Stroke; Predictive Value of Tests
PubMed: 38874054
DOI: 10.1161/JAHA.123.033298 -
BMC Medical Imaging Jun 2024Esophageal cancer, a global health concern, impacts predominantly men, particularly in Eastern Asia. Lymph node metastasis (LNM) significantly influences prognosis, and... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Esophageal cancer, a global health concern, impacts predominantly men, particularly in Eastern Asia. Lymph node metastasis (LNM) significantly influences prognosis, and current imaging methods exhibit limitations in accurate detection. The integration of radiomics, an artificial intelligence (AI) driven approach in medical imaging, offers a transformative potential. This meta-analysis evaluates existing evidence on the accuracy of radiomics models for predicting LNM in esophageal cancer.
METHODS
We conducted a systematic review following PRISMA 2020 guidelines, searching Embase, PubMed, and Web of Science for English-language studies up to November 16, 2023. Inclusion criteria focused on preoperatively diagnosed esophageal cancer patients with radiomics predicting LNM before treatment. Exclusion criteria were applied, including non-English studies and those lacking sufficient data or separate validation cohorts. Data extraction encompassed study characteristics and radiomics technical details. Quality assessment employed modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and Radiomics Quality Score (RQS) tools. Statistical analysis involved random-effects models for pooled sensitivity, specificity, diagnostic odds ratio (DOR), and area under the curve (AUC). Heterogeneity and publication bias were assessed using Deek's test and funnel plots. Analysis was performed using Stata version 17.0 and meta-DiSc.
RESULTS
Out of 426 initially identified citations, nine studies met inclusion criteria, encompassing 719 patients. These retrospective studies utilized CT, PET, and MRI imaging modalities, predominantly conducted in China. Two studies employed deep learning-based radiomics. Quality assessment revealed acceptable QUADAS-2 scores. RQS scores ranged from 9 to 14, averaging 12.78. The diagnostic meta-analysis yielded a pooled sensitivity, specificity, and AUC of 0.72, 0.76, and 0.74, respectively, representing fair diagnostic performance. Meta-regression identified the use of combined models as a significant contributor to heterogeneity (p-value = 0.05). Other factors, such as sample size (> 75) and least absolute shrinkage and selection operator (LASSO) usage for feature extraction, showed potential influence but lacked statistical significance (0.05 < p-value < 0.10). Publication bias was not statistically significant.
CONCLUSION
Radiomics shows potential for predicting LNM in esophageal cancer, with a moderate diagnostic performance. Standardized approaches, ongoing research, and prospective validation studies are crucial for realizing its clinical applicability.
Topics: Humans; Esophageal Neoplasms; Lymphatic Metastasis; Sensitivity and Specificity; Artificial Intelligence; Radiomics
PubMed: 38867143
DOI: 10.1186/s12880-024-01278-5 -
Biological Psychiatry Jun 2024Research in machine-learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to... (Review)
Review
Use of Machine-Learning Algorithms Based on Text, Audio and Video Data in the Prediction of Anxiety and Post-Traumatic Stress in General and Clinical Populations: A Systematic Review.
Research in machine-learning (ML) algorithms using natural behavior (i.e., text, audio, and video data) suggests that these techniques could contribute to personalization in psychology and psychiatry. However, a systematic review of the current state-of-the-art is missing. Moreover, individual studies often target ML experts, and may overlook potential clinical implications of their findings. In a narrative accessible to mental health professionals, we present a systematic review, conducted in 5 psychology and 2 computer-science databases. We included 128 studies assessing the predictive power of ML algorithms using text, audio, and/or video data in the prediction of anxiety and post-traumatic stress (PTSD). Most studies (n = 87) aimed at predicting anxiety, the remainder (n = 41) focused on PTSD. They were mostly published since 2019, in computer science journals, and tested algorithms using text (n = 72), as opposed to audio or video. They focused mainly on general populations (n = 92), less on laboratory experiments (n = 23) or clinical populations (n = 13). Methodological quality varied, as did reported metrics of the predictive power, hampering comparison across studies. Two thirds of studies, focusing on both disorders, reported acceptable to very good predictive power (including high-quality studies only). Results of 33 studies were uninterpretable, mainly due to missing information. Research into ML algorithms using natural behavior is in its infancy, but shows potential to contribute to diagnostics of mental disorders, such as anxiety and PTSD, in the future, if standardization of methods, reporting of results, and research in clinical populations are improved.
PubMed: 38866173
DOI: 10.1016/j.biopsych.2024.06.002 -
Cureus May 2024Chronic kidney disease (CKD) is a progressive condition characterized by gradual loss of kidney function, necessitating timely monitoring and interventions. This... (Review)
Review
Chronic kidney disease (CKD) is a progressive condition characterized by gradual loss of kidney function, necessitating timely monitoring and interventions. This systematic review comprehensively evaluates the application of artificial intelligence (AI) and machine learning (ML) techniques for predicting CKD progression. A rigorous literature search identified 13 relevant studies employing diverse AI/ML algorithms, including logistic regression, support vector machines, random forests, neural networks, and deep learning approaches. These studies primarily aimed to predict CKD progression to end-stage renal disease (ESRD) or the need for renal replacement therapy, with some focusing on diabetic kidney disease progression, proteinuria, or estimated glomerular filtration rate (GFR) decline. The findings highlight the promising predictive performance of AI/ML models, with several achieving high accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve scores. Key factors contributing to enhanced prediction included incorporating longitudinal data, baseline characteristics, and specific biomarkers such as estimated GFR, proteinuria, serum albumin, and hemoglobin levels. Integration of these predictive models with electronic health records and clinical decision support systems offers opportunities for timely risk identification, early interventions, and personalized management strategies. While challenges related to data quality, bias, and ethical considerations exist, the reviewed studies underscore the potential of AI/ML techniques to facilitate early detection, risk stratification, and targeted interventions for CKD patients. Ongoing research, external validation, and careful implementation are crucial to leveraging these advanced analytical approaches in clinical practice, ultimately improving outcomes and reducing the burden of CKD.
PubMed: 38864072
DOI: 10.7759/cureus.60145 -
Diabetology & Metabolic Syndrome Jun 2024Numerous studies have developed or validated prediction models aimed at estimating the likelihood of amputation in diabetic foot (DF) patients. However, the quality and... (Review)
Review
BACKGROUND
Numerous studies have developed or validated prediction models aimed at estimating the likelihood of amputation in diabetic foot (DF) patients. However, the quality and applicability of these models in clinical practice and future research remain uncertain. This study conducts a systematic review and assessment of the risk of bias and applicability of amputation prediction models among individuals with DF.
METHODS
A comprehensive search was conducted across multiple databases, including PubMed, Web of Science, EBSCO CINAHL Plus, Embase, Cochrane Library, China National Knowledge Infrastructure (CNKI), Wanfang, Chinese Biomedical Literature Database (CBM), and Weipu (VIP) from their inception to December 24, 2023. Two investigators independently screened the literature and extracted data using the checklist for critical appraisal and data extraction for systematic reviews of prediction modeling studies. The Prediction Model Risk of Bias Assessment Tool (PROBAST) checklist was employed to evaluate both the risk of bias and applicability.
RESULTS
A total of 20 studies were included in this analysis, comprising 17 development studies and three validation studies, encompassing 20 prediction models and 11 classification systems. The incidence of amputation in patients with DF ranged from 5.9 to 58.5%. Machine learning-based methods were employed in more than half of the studies. The reported area under the curve (AUC) varied from 0.560 to 0.939. Independent predictors consistently identified by multivariate models included age, gender, HbA1c, hemoglobin, white blood cell count, low-density lipoprotein cholesterol, diabetes duration, and Wagner's Classification. All studies were found to exhibit a high risk of bias, primarily attributed to inadequate handling of outcome events and missing data, lack of model performance assessment, and overfitting.
CONCLUSIONS
The assessment using PROBAST revealed a notable risk of bias in the existing prediction models for amputation in patients with DF. It is imperative for future studies to concentrate on enhancing the robustness of current prediction models or constructing new models with stringent methodologies.
PubMed: 38858732
DOI: 10.1186/s13098-024-01360-6 -
PeerJ. Computer Science 2024Concrete, a fundamental construction material, stands as a significant consumer of virgin resources, including sand, gravel, crushed stone, and fresh water. It exerts an...
BACKGROUND
Concrete, a fundamental construction material, stands as a significant consumer of virgin resources, including sand, gravel, crushed stone, and fresh water. It exerts an immense demand, accounting for approximately 1.6 billion metric tons of Portland and modified Portland cement annually. Moreover, addressing extreme conditions with exceptionally nonlinear behavior necessitates a laborious calibration procedure in structural analysis and design methodologies. These methods are also difficult to execute in practice. To reduce time and effort, ML might be a viable option.
MATERIAL AND METHODS
A set of keywords are designed to perform the search PubMed search engine with filters to not search the studies below the year 2015. Furthermore, using PRISMA guidelines, studies were selected and after screening, a total of 42 studies were summarized. The PRISMA guidelines provide a structured framework to ensure transparency, accuracy, and completeness in reporting the methods and results of systematic reviews and meta-analyses. The ability to methodically and accurately connect disparate parts of the literature is often lacking in review research. Some of the trickiest parts of original research include knowledge mapping, co-citation, and co-occurrence. Using this data, we were able to determine which locations were most active in researching machine learning applications for concrete, where the most influential authors were in terms of both output and citations and which articles garnered the most citations overall.
CONCLUSION
ML has become a viable prediction method for a wide variety of structural industrial applications, and hence it may serve as a potential successor for routinely used empirical model in the design of concrete structures. The non-ML structural engineering community may use this overview of ML methods, fundamental principles, access codes, ML libraries, and gathered datasets to construct their own ML models for useful uses. Structural engineering practitioners and researchers may benefit from this article's incorporation of concrete ML studies as well as structural engineering datasets. The construction industry stands to benefit from the use of machine learning in terms of cost savings, time savings, and labor intensity. The statistical and graphical representation of contributing authors and participants in this work might facilitate future collaborations and the sharing of novel ideas and approaches among researchers and industry professionals. The limitation of this systematic review is that it is only PubMed based which means it includes studies included in the PubMed database.
PubMed: 38855208
DOI: 10.7717/peerj-cs.1853