-
La Radiologia Medica Feb 2023This study aimed to systematically summarize the performance of the machine learning-based radiomics models in the prediction of microsatellite instability (MSI) in... (Review)
Review
This study aimed to systematically summarize the performance of the machine learning-based radiomics models in the prediction of microsatellite instability (MSI) in patients with colorectal cancer (CRC). It was conducted according to the preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA) guideline and was registered at the PROSPERO website with an identifier CRD42022295787. Systematic literature searching was conducted in databases of PubMed, Embase, Web of Science, and Cochrane Library up to November 10, 2022. Research which applied radiomics analysis on preoperative CT/MRI/PET-CT images for predicting the MSI status in CRC patients with no history of anti-tumor therapies was eligible. The radiomics quality score (RQS) and Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) were applied to evaluate the research quality (full score 100%). Twelve studies with 4,320 patients were included. All studies were retrospective, and only four had an external validation cohort. The median incidence of MSI was 19% (range 8-34%). The area under the receiver operator curve of the models ranged from 0.78 to 0.96 (median 0.83) in the external validation cohort. The median sensitivity was 0.76 (range 0.32-1.00), and the median specificity was 0.87 (range 0.69-1.00). The median RQS score was 38% (range 14-50%), and half of the studies showed high risk in patient selection as evaluated by QUADAS-2. In conclusion, while radiomics based on pretreatment imaging modalities had a high performance in the prediction of MSI status in CRC, so far it does not appear to be ready for clinical use due to insufficient methodological quality.
Topics: Humans; Colorectal Neoplasms; Machine Learning; Microsatellite Instability; Positron Emission Tomography Computed Tomography; Retrospective Studies
PubMed: 36648615
DOI: 10.1007/s11547-023-01593-x -
Biomedical Engineering Online Jun 2021The use of machine learning (ML) techniques in healthcare encompasses an emerging concept that envisages vast contributions to the tackling of rare diseases. In this... (Review)
Review
INTRODUCTION
The use of machine learning (ML) techniques in healthcare encompasses an emerging concept that envisages vast contributions to the tackling of rare diseases. In this scenario, amyotrophic lateral sclerosis (ALS) involves complexities that are yet not demystified. In ALS, the biomedical signals present themselves as potential biomarkers that, when used in tandem with smart algorithms, can be useful to applications within the context of the disease.
METHODS
This Systematic Literature Review (SLR) consists of searching for and investigating primary studies that use ML techniques and biomedical signals related to ALS. Following the definition and execution of the SLR protocol, 18 articles met the inclusion, exclusion, and quality assessment criteria, and answered the SLR research questions.
DISCUSSIONS
Based on the results, we identified three classes of ML applications combined with biomedical signals in the context of ALS: diagnosis (72.22%), communication (22.22%), and survival prediction (5.56%).
CONCLUSIONS
Distinct algorithmic models and biomedical signals have been reported and present promising approaches, regardless of their classes. In summary, this SLR provides an overview of the primary studies analyzed as well as directions for the construction and evolution of technology-based research within the scope of ALS.
Topics: Amyotrophic Lateral Sclerosis; Biomarkers; Disease Progression; Humans; Machine Learning
PubMed: 34130692
DOI: 10.1186/s12938-021-00896-2 -
Artificial Intelligence in Medicine Sep 2023DNA methylation biomarkers have great potential in improving prognostic classification systems for patients with cancer. Machine learning (ML)-based analytic techniques... (Review)
Review
BACKGROUND
DNA methylation biomarkers have great potential in improving prognostic classification systems for patients with cancer. Machine learning (ML)-based analytic techniques might help overcome the challenges of analyzing high-dimensional data in relatively small sample sizes. This systematic review summarizes the current use of ML-based methods in epigenome-wide studies for the identification of DNA methylation signatures associated with cancer prognosis.
METHODS
We searched three electronic databases including PubMed, EMBASE, and Web of Science for articles published until 2 January 2023. ML-based methods and workflows used to identify DNA methylation signatures associated with cancer prognosis were extracted and summarized. Two authors independently assessed the methodological quality of included studies by a seven-item checklist adapted from 'A Tool to Assess Risk of Bias and Applicability of Prediction Model Studies (PROBAST)' and from the 'Reporting Recommendations for Tumor Marker Prognostic Studies (REMARK). Different ML methods and workflows used in included studies were summarized and visualized by a sunburst chart, a bubble chart, and Sankey diagrams, respectively.
RESULTS
Eighty-three studies were included in this review. Three major types of ML-based workflows were identified. 1) unsupervised clustering, 2) supervised feature selection, and 3) deep learning-based feature transformation. For the three workflows, the most frequently used ML techniques were consensus clustering, least absolute shrinkage and selection operator (LASSO), and autoencoder, respectively. The systematic review revealed that the performance of these approaches has not been adequately evaluated yet and that methodological and reporting flaws were common in the identified studies using ML techniques.
CONCLUSIONS
There is great heterogeneity in ML-based methodological strategies used by epigenome-wide studies to identify DNA methylation markers associated with cancer prognosis. In theory, most existing workflows could not handle the high multi-collinearity and potentially non-linearity interactions in epigenome-wide DNA methylation data. Benchmarking studies are needed to compare the relative performance of various approaches for specific cancer types. Adherence to relevant methodological and reporting guidelines are urgently needed.
Topics: Humans; DNA Methylation; Epigenome; Prognosis; Neoplasms; Machine Learning
PubMed: 37673571
DOI: 10.1016/j.artmed.2023.102589 -
Frontiers in Endocrinology 2023This study aimed to systematically review research on cinacalcet and secondary hyperparathyroidism (SHPT) using machine learning-based statistical analyses. (Meta-Analysis)
Meta-Analysis
INTRODUCTION
This study aimed to systematically review research on cinacalcet and secondary hyperparathyroidism (SHPT) using machine learning-based statistical analyses.
METHODS
Publications indexed in the Web of Science Core Collection database on Cinacalcet and SHPT published between 2000 and 2022 were retrieved. The R package "Bibliometrix," VOSviewer, CiteSpace, meta, and latent Dirichlet allocation (LDA) in Python were used to generate bibliometric and meta-analytical results.
RESULTS
A total of 959 articles were included in our bibliometric analysis. In total, 3753 scholars from 54 countries contributed to this field of research. The United States, Japan, and China were found to be among the three most productive countries worldwide. Three Japanese institutions (Showa University, Tokai University, and Kobe University) published the most articles on Cinacalcet and SHPT. Fukagawa, M.; Chertow, G.M.; Goodman W.G. were the three authors who published the most articles in this field. Most articles were published in , , and . Research on Cinacalcet and SHPT has mainly included three topics: 1) comparative effects of various treatments, 2) the safety and efficacy of cinacalcet, and 3) fibroblast growth factor-23 (FGF-23). Integrated treatments, cinacalcet use in pediatric chronic kidney disease, and new therapeutic targets are emerging research hotspots. Through a meta-analysis, we confirmed the effects of Cinacalcet on reducing serum PTH ( = -0.56, 95% = -0.76 to -0.37, = 0.001) and calcium ( = -0.93, 95% = -1.21to -0.64, = 0.001) and improving phosphate ( = 0.17, 95% = -0.33 to -0.01, = 0.033) and calcium-phosphate product levels ( = -0.49, 95% = -0.71 to -0.28, = 0.001); we found no difference in all-cause mortality ( = 0.97, 95% = 0.90 to 1.05, = 0.47), cardiovascular mortality ( = 0.69, 95% = 0.36 to 1.31, = 0.25), and parathyroidectomy ( = 0.36, 95% = 0.09 to 1.35, = 0.13) between the Cinacalcet and non-Cinacalcet users. Moreover, Cinacalcet was associated with an increased risk of nausea ( = 2.29, 95% = 1.73 to 3.05, = 0.001), hypocalcemia ( = 4.05, 95% = 2.33 to 7.04, = 0.001), and vomiting ( = 1.90, 95% = 1.70 to 2.11, = 0.001).
DISCUSSION
The number of publications indexed to Cinacalcet and SHPT has increased rapidly over the past 22 years. Literature distribution, research topics, and emerging trends in publications on Cinacalcet and SHPT were analyzed using a machine learning-based bibliometric review. The findings of this meta-analysis provide valuable insights into the efficacy and safety of cinacalcet for the treatment of SHPT, which will be of interest to both clinical and researchers.
Topics: Child; Humans; Calcimimetic Agents; Calcium; Cinacalcet; Hyperparathyroidism, Secondary; Phosphates; United States; Machine Learning
PubMed: 37538795
DOI: 10.3389/fendo.2023.1146955 -
Brain Informatics Oct 2022This systematic review offers a world-first critical analysis of machine learning methods and systems, along with future directions for the study of cybersickness... (Review)
Review
This systematic review offers a world-first critical analysis of machine learning methods and systems, along with future directions for the study of cybersickness induced by virtual reality (VR). VR is becoming increasingly popular and is an important part of current advances in human training, therapies, entertainment, and access to the metaverse. Usage of this technology is limited by cybersickness, a common debilitating condition experienced upon VR immersion. Cybersickness is accompanied by a mix of symptoms including nausea, dizziness, fatigue and oculomotor disturbances. Machine learning can be used to identify cybersickness and is a step towards overcoming these physiological limitations. Practical implementation of this is possible with optimised data collection from wearable devices and appropriate algorithms that incorporate advanced machine learning approaches. The present systematic review focuses on 26 selected studies. These concern machine learning of biometric and neuro-physiological signals obtained from wearable devices for the automatic identification of cybersickness. The methods, data processing and machine learning architecture, as well as suggestions for future exploration on detection and prediction of cybersickness are explored. A wide range of immersion environments, participant activity, features and machine learning architectures were identified. Although models for cybersickness detection have been developed, literature still lacks a model for the prediction of first-instance events. Future research is pointed towards goal-oriented data selection and labelling, as well as the use of brain-inspired spiking neural network models to achieve better accuracy and understanding of complex spatio-temporal brain processes related to cybersickness.
PubMed: 36209445
DOI: 10.1186/s40708-022-00172-6 -
Journal of Clinical Epidemiology Feb 2023We sought to summarize the study design, modelling strategies, and performance measures reported in studies on clinical prediction models developed using machine... (Review)
Review
BACKGROUND AND OBJECTIVES
We sought to summarize the study design, modelling strategies, and performance measures reported in studies on clinical prediction models developed using machine learning techniques.
METHODS
We search PubMed for articles published between 01/01/2018 and 31/12/2019, describing the development or the development with external validation of a multivariable prediction model using any supervised machine learning technique. No restrictions were made based on study design, data source, or predicted patient-related health outcomes.
RESULTS
We included 152 studies, 58 (38.2% [95% CI 30.8-46.1]) were diagnostic and 94 (61.8% [95% CI 53.9-69.2]) prognostic studies. Most studies reported only the development of prediction models (n = 133, 87.5% [95% CI 81.3-91.8]), focused on binary outcomes (n = 131, 86.2% [95% CI 79.8-90.8), and did not report a sample size calculation (n = 125, 82.2% [95% CI 75.4-87.5]). The most common algorithms used were support vector machine (n = 86/522, 16.5% [95% CI 13.5-19.9]) and random forest (n = 73/522, 14% [95% CI 11.3-17.2]). Values for area under the Receiver Operating Characteristic curve ranged from 0.45 to 1.00. Calibration metrics were often missed (n = 494/522, 94.6% [95% CI 92.4-96.3]).
CONCLUSION
Our review revealed that focus is required on handling of missing values, methods for internal validation, and reporting of calibration to improve the methodological conduct of studies on machine learning-based prediction models.
SYSTEMATIC REVIEW REGISTRATION
PROSPERO, CRD42019161764.
Topics: Humans; Algorithms; Machine Learning; Prognosis; ROC Curve; Supervised Machine Learning
PubMed: 36436815
DOI: 10.1016/j.jclinepi.2022.11.015 -
Frontiers in Bioengineering and... 2021Artificial intelligence is widely used in medical field, and machine learning has been increasingly used in health care, prediction, and diagnosis and as a method of... (Review)
Review
Artificial intelligence is widely used in medical field, and machine learning has been increasingly used in health care, prediction, and diagnosis and as a method of determining priority. Machine learning methods have been features of several tools in the fields of obstetrics and childcare. This present review aims to summarize the machine learning techniques to predict perinatal complications. To identify the applicability and performance of machine learning methods used to identify pregnancy complications. A total of 98 articles were obtained with the keywords "machine learning," "deep learning," "artificial intelligence," and accordingly as they related to perinatal complications ("complications in pregnancy," "pregnancy complications") from three scientific databases: PubMed, Scopus, and Web of Science. These were managed on the Mendeley platform and classified using the PRISMA method. A total of 31 articles were selected after elimination according to inclusion and exclusion criteria. The features used to predict perinatal complications were primarily electronic medical records (48%), medical images (29%), and biological markers (19%), while 4% were based on other types of features, such as sensors and fetal heart rate. The main perinatal complications considered in the application of machine learning thus far are pre-eclampsia and prematurity. In the 31 studies, a total of sixteen complications were predicted. The main precision metric used is the AUC. The machine learning methods with the best results were the prediction of prematurity from medical images using the support vector machine technique, with an accuracy of 95.7%, and the prediction of neonatal mortality with the XGBoost technique, with 99.7% accuracy. It is important to continue promoting this area of research and promote solutions with multicenter clinical applicability through machine learning to reduce perinatal complications. This systematic review contributes significantly to the specialized literature on artificial intelligence and women's health.
PubMed: 35127665
DOI: 10.3389/fbioe.2021.780389 -
Sensors (Basel, Switzerland) Jun 2022Wireless networks have drastically influenced our lifestyle, changing our workplaces and society. Among the variety of wireless technology, Wi-Fi surely plays a leading... (Review)
Review
Wireless networks have drastically influenced our lifestyle, changing our workplaces and society. Among the variety of wireless technology, Wi-Fi surely plays a leading role, especially in local area networks. The spread of mobiles and tablets, and more recently, the advent of Internet of Things, have resulted in a multitude of Wi-Fi-enabled devices continuously sending data to the Internet and between each other. At the same time, Machine Learning has proven to be one of the most effective and versatile tools for the analysis of fast streaming data. This systematic review aims at studying the interaction between these technologies and how it has developed throughout their lifetimes. We used Scopus, Web of Science, and IEEE Xplore databases to retrieve paper abstracts and leveraged a topic modeling technique, namely, BERTopic, to analyze the resulting document corpus. After these steps, we inspected the obtained clusters and computed statistics to characterize and interpret the topics they refer to. Our results include both the applications of Wi-Fi sensing and the variety of Machine Learning algorithms used to tackle them. We also report how the Wi-Fi advances have affected sensing applications and the choice of the most suitable Machine Learning models.
Topics: Algorithms; Databases, Factual; Local Area Networks; Machine Learning; Wireless Technology
PubMed: 35808430
DOI: 10.3390/s22134925 -
Diagnostics (Basel, Switzerland) Feb 2023Limitations of the chest X-ray (CXR) have resulted in attempts to create machine learning systems to assist clinicians and improve interpretation accuracy. An... (Review)
Review
Limitations of the chest X-ray (CXR) have resulted in attempts to create machine learning systems to assist clinicians and improve interpretation accuracy. An understanding of the capabilities and limitations of modern machine learning systems is necessary for clinicians as these tools begin to permeate practice. This systematic review aimed to provide an overview of machine learning applications designed to facilitate CXR interpretation. A systematic search strategy was executed to identify research into machine learning algorithms capable of detecting >2 radiographic findings on CXRs published between January 2020 and September 2022. Model details and study characteristics, including risk of bias and quality, were summarized. Initially, 2248 articles were retrieved, with 46 included in the final review. Published models demonstrated strong standalone performance and were typically as accurate, or more accurate, than radiologists or non-radiologist clinicians. Multiple studies demonstrated an improvement in the clinical finding classification performance of clinicians when models acted as a diagnostic assistance device. Device performance was compared with that of clinicians in 30% of studies, while effects on clinical perception and diagnosis were evaluated in 19%. Only one study was prospectively run. On average, 128,662 images were used to train and validate models. Most classified less than eight clinical findings, while the three most comprehensive models classified 54, 72, and 124 findings. This review suggests that machine learning devices designed to facilitate CXR interpretation perform strongly, improve the detection performance of clinicians, and improve the efficiency of radiology workflow. Several limitations were identified, and clinician involvement and expertise will be key to driving the safe implementation of quality CXR machine learning systems.
PubMed: 36832231
DOI: 10.3390/diagnostics13040743 -
BMC Pulmonary Medicine Jul 2023Asthma exacerbations reduce the patient's quality of life and are also responsible for significant disease burdens and economic costs. Machine learning (ML)-based... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Asthma exacerbations reduce the patient's quality of life and are also responsible for significant disease burdens and economic costs. Machine learning (ML)-based prediction models have been increasingly developed to predict asthma exacerbations in recent years. This systematic review and meta-analysis aimed to identify the prediction performance of ML-based prediction models for asthma exacerbations and address the uncertainty of whether modern ML methods could become an alternative option to predict asthma exacerbations.
METHODS
PubMed, Cochrane Library, EMBASE, and Web of Science were searched for studies published up to December 15, 2022. Studies that applied ML methods to develop prediction models for asthma exacerbations among asthmatic patients older than five years and were published in English were eligible. The prediction model risk of bias assessment tool (PROBAST) was utilized to estimate the risk of bias and the applicability of included studies. Stata software (version 15.0) was used for the random effects meta-analysis of performance measures. Subgroup analyses stratified by ML methods, sample size, age groups, and outcome definitions were conducted.
RESULTS
Eleven studies, including 23 prediction models, were identified. Most of the studies were published in recent three years. Logistic regression, boosting, and random forest were the most used ML methods. The most common important predictors were systemic steroid use, short-acting beta2-agonists, emergency department visit, age, and exacerbation history. The overall pooled area under the curve of the receiver operating characteristics (AUROC) of 11 studies (23 prediction models) was 0.80 (95% CI 0.77-0.83). Subgroup analysis based on different ML models showed that boosting method achieved the best performance, with an overall pooled AUROC of 0.84 (95% CI 0.81-0.87).
CONCLUSION
This study identified that ML was the potential tool to achieve great performance in predicting asthma exacerbations. However, the methodology within these models was heterogeneous. Future studies should focus on improving the generalization ability and practicability, thus driving the application of these models in clinical practice.
Topics: Humans; Quality of Life; Asthma; Steroids; Machine Learning; Cost of Illness
PubMed: 37507662
DOI: 10.1186/s12890-023-02570-w