-
Resuscitation Jan 2024The primary aim of this systematic review was to investigate the most common electroencephalogram (EEG)-based machine learning (ML) model with the highest Area Under... (Review)
Review
AIM OF THE REVIEW
The primary aim of this systematic review was to investigate the most common electroencephalogram (EEG)-based machine learning (ML) model with the highest Area Under Receiver Operating Characteristic Curve (AUC) in two ML categories, conventional ML and Deep Neural Network (DNN), to predict the neurologic outcomes after cardiac arrest; the secondary aim was to investigate common EEG features applied to ML models.
METHODS
Systematic search of medical literature from PubMed and engineering literature from Compendex up to June 2, 2023. One reviewer screened studies that used EEG-based ML models to predict the neurologic outcomes after cardiac arrest. Four reviewers validated that the studies met selection criteria. Nine variables were manually extracted. The top-five common EEG features were calculated. We evaluated each study's risk of bias using the Quality in Prognosis Studies guideline.
RESULTS
Out of 351 identified studies, 17 studies met the inclusion criteria. Random Forest (RF) (n = 7) was the most common ML model in the conventional ML category (n = 11), followed by Convolutional Neural Network (CNN) (n = 4) in the DNN category (n = 6). The AUCs for RF ranged between 0.8 and 0.97, while CNN had AUCs between 0.7 and 0.92. The top-three commonly used EEG features were band power (n = 12), Shannon's Entropy (n = 11), burst-suppression ratio (n = 9).
CONCLUSIONS
RF and CNN were the two most common ML models with the highest AUCs for predicting the neurologic outcomes after cardiac arrest. Using a multimodal model that combines EEG features and electronic health record data may further improve prognostic performance.
Topics: Humans; Heart Arrest; Machine Learning; Prognosis; Electroencephalography; ROC Curve
PubMed: 37972682
DOI: 10.1016/j.resuscitation.2023.110049 -
Psychiatry Research Aug 2023We developed and tested a Bayesian network(BN) model to predict ECT remission for depression, with non-response as a secondary outcome.
INTRODUCTION
We developed and tested a Bayesian network(BN) model to predict ECT remission for depression, with non-response as a secondary outcome.
METHODS
We performed a systematic literature search on clinically available predictors. We combined these predictors with variables from a dataset of clinical ECT trajectories (performed in the University Medical Center Utrecht) to create priors and train the BN. Temporal validation was performed in an independent sample.
RESULTS
The systematic literature search yielded three meta-analyses, which provided prior knowledge on outcome predictors. The clinical dataset consisted of 248 treatment trajectories in the training set and 44 trajectories in the test set at the same medical center. The AUC for the primary outcome remission estimated on an independent validation set was 0.686 (95%CI 0.513-0.859) (AUC values of 0.505 - 0.763 observed in 5-fold cross validation of the model within the train set). Accuracy 0.73 (balanced accuracy 0.67), sensitivity 0.55, specificity 0.79, after temporal validation in the independent sample. Prior literature information marginally reduced CI width.
DISCUSSION
A BN model comprised of prior knowledge and clinical data can predict remission of depression after ECT with reasonable performance. This approach can be used to make outcome predictions in psychiatry, and offers a methodological framework to weigh additional information, such as patient characteristics, symptoms and biomarkers. In time, it may be used to improve shared decision-making in clinical practice.
Topics: Humans; Electroconvulsive Therapy; Depression; Bayes Theorem; Prognosis; Biomarkers; Treatment Outcome
PubMed: 37429173
DOI: 10.1016/j.psychres.2023.115328 -
JMIR Mental Health Jun 2024Text-based digital media platforms have revolutionized communication and information sharing, providing valuable access to knowledge and understanding in the fields of... (Review)
Review
BACKGROUND
Text-based digital media platforms have revolutionized communication and information sharing, providing valuable access to knowledge and understanding in the fields of mental health and suicide prevention.
OBJECTIVE
This systematic review aimed to determine how machine learning and data analysis can be applied to text-based digital media data to understand mental health and aid suicide prevention.
METHODS
A systematic review of research papers from the following major electronic databases was conducted: Web of Science, MEDLINE, Embase (via MEDLINE), and PsycINFO (via MEDLINE). The database search was supplemented by a hand search using Google Scholar.
RESULTS
Overall, 19 studies were included, with five major themes as to how data analysis and machine learning techniques could be applied: (1) as predictors of personal mental health, (2) to understand how personal mental health and suicidal behavior are communicated, (3) to detect mental disorders and suicidal risk, (4) to identify help seeking for mental health difficulties, and (5) to determine the efficacy of interventions to support mental well-being.
CONCLUSIONS
Our findings show that data analysis and machine learning can be used to gain valuable insights, such as the following: web-based conversations relating to depression vary among different ethnic groups, teenagers engage in a web-based conversation about suicide more often than adults, and people seeking support in web-based mental health communities feel better after receiving online support. Digital tools and mental health apps are being used successfully to manage mental health, particularly through the COVID-19 epidemic, during which analysis has revealed that there was increased anxiety and depression, and web-based communities played a part in reducing isolation during the pandemic. Predictive analytics were also shown to have potential, and virtual reality shows promising results in the delivery of preventive or curative care. Future research efforts could center on optimizing algorithms to enhance the potential of text-based digital media analysis in mental health and suicide prevention. In addressing depression, a crucial step involves identifying the factors that contribute to happiness and using machine learning to forecast these sources of happiness. This could extend to understanding how various activities result in improved happiness across different socioeconomic groups. Using insights gathered from such data analysis and machine learning, there is an opportunity to craft digital interventions, such as chatbots, designed to provide support and address mental health challenges and suicide prevention.
Topics: Humans; Machine Learning; Suicide Prevention; Mental Health; Social Media; Data Analysis
PubMed: 38935419
DOI: 10.2196/55747 -
Frontiers in Immunology 2023The surge in the number of publications on psoriasis has posed significant challenges for researchers in effectively managing the vast amount of information. However,...
BACKGROUND
The surge in the number of publications on psoriasis has posed significant challenges for researchers in effectively managing the vast amount of information. However, due to the lack of tools to process metadata, no comprehensive bibliometric analysis has been conducted.
OBJECTIVES
This study is to evaluate the trends and current hotspots of psoriatic research from a macroscopic perspective through a bibliometric analysis assisted by machine learning based semantic analysis.
METHODS
Publications indexed under the Medical Subject Headings (MeSH) term "Psoriasis" from 2003 to 2022 were extracted from PubMed. The generative statistical algorithm latent Dirichlet allocation (LDA) was applied to identify specific topics and trends based on abstracts. The unsupervised Louvain algorithm was used to establish a network identifying relationships between topics.
RESULTS
A total of 28,178 publications were identified. The publications were derived from 176 countries, with United States, China, and Italy being the top three countries. For the term "psoriasis", 9,183 MeSH terms appeared 337,545 times. Among them, MeSH term "Severity of illness index", "Treatment outcome", "Dermatologic agents" occur most frequently. A total of 21,928 publications were included in LDA algorithm, which identified three main areas and 50 branched topics, with "Molecular pathogenesis", "Clinical trials", and "Skin inflammation" being the most increased topics. LDA networks identified "Skin inflammation" was tightly associated with "Molecular pathogenesis" and "Biological agents". "Nail psoriasis" and "Epidemiological study" have presented as new research hotspots, and attention on topics of comorbidities, including "Cardiovascular comorbidities", "Psoriatic arthritis", "Obesity" and "Psychological disorders" have increased gradually.
CONCLUSIONS
Research on psoriasis is flourishing, with molecular pathogenesis, skin inflammation, and clinical trials being the current hotspots. The strong association between skin inflammation and biologic agents indicated the effective translation between basic research and clinical application in psoriasis. Besides, nail psoriasis, epidemiological study and comorbidities of psoriasis also draw increased attention.
Topics: Humans; United States; Psoriasis; Arthritis, Psoriatic; Bibliometrics; Dermatitis; Machine Learning; Inflammation
PubMed: 37954610
DOI: 10.3389/fimmu.2023.1272080 -
Journal of Advanced Research Sep 2023The rapid and reliable detection of pathogenic bacteria at an early stage is a highly significant research field for public health. However, most traditional approaches... (Review)
Review
BACKGROUND
The rapid and reliable detection of pathogenic bacteria at an early stage is a highly significant research field for public health. However, most traditional approaches for pathogen identification are time-consuming and labour-intensive, which may cause physicians making inappropriate treatment decisions based on an incomplete diagnosis of patients with unknown infections, leading to increased morbidity and mortality. Therefore, novel methods are constantly required to face the emerging challenges of bacterial detection and identification. In particular, Raman spectroscopy (RS) is becoming an attractive method for rapid and accurate detection of bacterial pathogens in recent years, among which the newly developed surface-enhanced Raman spectroscopy (SERS) shows the most promising potential.
AIM OF REVIEW
Recent advances in pathogen detection and diagnosis of bacterial infections were discussed with focuses on the development of the SERS approaches and its applications in complex clinical settings.
KEY SCIENTIFIC CONCEPTS OF REVIEW
The current review describes bacterial classification using surface enhanced Raman spectroscopy (SERS) for developing a rapid and more accurate method for the identification of bacterial pathogens in clinical diagnosis. The initial part of this review gives a brief overview of the mechanism of SERS technology and development of the SERS approach to detect bacterial pathogens in complex samples. The development of the label-based and label-free SERS strategies and several novel SERS-compatible technologies in clinical applications, as well as the analytical procedures and examples of chemometric methods for SERS, are introduced. The computational challenges of pre-processing spectra and the highlights of the limitations and perspectives of the SERS technique are also discussed.Taken together, this systematic review provides an overall summary of the SERS technique and its application potential for direct bacterial diagnosis in clinical samples such as blood, urine and sputum, etc.
Topics: Humans; Spectrum Analysis, Raman; Bacteria; Bacterial Infections
PubMed: 36549439
DOI: 10.1016/j.jare.2022.11.010 -
Cureus Oct 2023Artificial intelligence (AI) is expected to improve healthcare outcomes by facilitating early diagnosis, reducing the medical administrative burden, aiding drug... (Review)
Review
Artificial intelligence (AI) is expected to improve healthcare outcomes by facilitating early diagnosis, reducing the medical administrative burden, aiding drug development, personalising medical and oncological management, monitoring healthcare parameters on an individual basis, and allowing clinicians to spend more time with their patients. In the post-pandemic world where there is a drive for efficient delivery of healthcare and manage long waiting times for patients to access care, AI has an important role in supporting clinicians and healthcare systems to streamline the care pathways and provide timely and high-quality care for the patients. Despite AI technologies being used in healthcare for some decades, and all the theoretical potential of AI, the uptake in healthcare has been uneven and slower than anticipated and there remain a number of barriers, both overt and covert, which have limited its incorporation. This literature review highlighted barriers in six key areas: ethical, technological, liability and regulatory, workforce, social, and patient safety barriers. Defining and understanding the barriers preventing the acceptance and implementation of AI in the setting of healthcare will enable clinical staff and healthcare leaders to overcome the identified hurdles and incorporate AI technologies for the benefit of patients and clinical staff.
PubMed: 37927664
DOI: 10.7759/cureus.46454 -
Brain Research Bulletin Oct 2023Gait analysis could be used in animal models as an indicator of sensory ataxia due to chemotherapy-induced peripheral neurotoxicity (CIPN). Over the years, gait analysis... (Review)
Review
Gait analysis could be used in animal models as an indicator of sensory ataxia due to chemotherapy-induced peripheral neurotoxicity (CIPN). Over the years, gait analysis in in vivo studies has evolved from simple observations carried out by a trained operator to computerised systems with machine learning that allow the quantification of any variable of interest and the establishment of algorithms for behavioural classification. However, there is not a consensus on gait analysis use in CIPN animal models; therefore, we carried out a systematic review. Of 987 potentially relevant studies, 14 were included, in which different methods were analysed (observation, footprint and CatWalk™). We presented the state-of-the-art of possible approaches to analyse sensory ataxia in rodent models, addressing advantages and disadvantages of different methods available. Semi-automated methods may be of interest when preventive or therapeutic strategies are evaluated, also considering their methodological simplicity and automaticity; up to now, only CatWalk™ analysis has been tested. Future studies should expect that CIPN-affected animals tend to reduce hind paw support due to pain, allodynia or loss of sensation, and an increase in swing phase could or should be observed. Few available studies documented these impairments at the last time point, and only appeared later on respect to other earlier signs of CIPN (such as altered neurophysiological findings). For that reason, gait impairment could be interpreted as late repercussions of loss of sensory.
Topics: Animals; Peripheral Nervous System Diseases; Gait Analysis; Rodentia; Neurotoxicity Syndromes; Antineoplastic Agents; Ataxia
PubMed: 37748696
DOI: 10.1016/j.brainresbull.2023.110769 -
Journal of Medical Internet Research Oct 2023Machine learning is a potentially effective method for identifying and predicting the time of the onset of stroke. However, the value of applying machine learning in... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Machine learning is a potentially effective method for identifying and predicting the time of the onset of stroke. However, the value of applying machine learning in this field remains controversial and debatable.
OBJECTIVE
We aimed to assess the value of applying machine learning in predicting the time of stroke onset.
METHODS
PubMed, Web of Science, Embase, and Cochrane were comprehensively searched. The C index and sensitivity with 95% CI were used as effect sizes. The risk of bias was evaluated using PROBAST (Prediction Model Risk of Bias Assessment Tool), and meta-analysis was conducted using R (version 4.2.0; R Core Team).
RESULTS
Thirteen eligible studies were included in the meta-analysis involving 55 machine learning models with 41 models in the training set and 14 in the validation set. The overall C index was 0.800 (95% CI 0.773-0.826) in the training set and 0.781 (95% CI 0.709-0.852) in the validation set. The sensitivity and specificity were 0.76 (95% CI 0.73-0.80) and 0.79 (95% CI 0.74-0.82) in the training set and 0.81 (95% CI 0.68-0.90) and 0.83 (95% CI 0.73-0.89) in the validation set, respectively. Subgroup analysis revealed that the accuracy of machine learning in predicting the time of stroke onset within 4.5 hours was optimal (training: 0.80, 95% CI 0.77-0.83; validation: 0.79, 95% CI 0.71-0.86).
CONCLUSIONS
Machine learning has ideal performance in identifying the time of stroke onset. More reasonable image segmentation and texture extraction methods in radiomics should be used to promote the value of applying machine learning in diverse ethnic backgrounds.
TRIAL REGISTRATION
PROSPERO CRD42022358898; https://www.crd.york.ac.uk/Prospero/display_record.php?RecordID=358898.
Topics: Humans; Ethnicity; Machine Learning; Patients; PubMed; Stroke
PubMed: 37824198
DOI: 10.2196/44895 -
International Journal of Computer... Aug 2023The implementation of artificial intelligence in hand surgery and rehabilitation is gaining popularity. The purpose of this scoping review was to give an overview of... (Review)
Review
PURPOSE
The implementation of artificial intelligence in hand surgery and rehabilitation is gaining popularity. The purpose of this scoping review was to give an overview of implementations of artificial intelligence in hand surgery and rehabilitation and their current significance in clinical practice.
METHODS
A systematic literature search of the MEDLINE/PubMed and Cochrane Collaboration libraries was conducted. The review was conducted according to the framework outlined by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews. A narrative summary of the papers is presented to give an orienting overview of this rapidly evolving topic.
RESULTS
Primary search yielded 435 articles. After application of the inclusion/exclusion criteria and addition of supplementary search, 235 articles were included in the final review. In order to facilitate navigation through this heterogenous field, the articles were clustered into four groups of thematically related publications. The most common applications of artificial intelligence in hand surgery and rehabilitation target automated image analysis of anatomic structures, fracture detection and localization and automated screening for other hand and wrist pathologies such as carpal tunnel syndrome, rheumatoid arthritis or osteoporosis. Compared to other medical subspecialties the number of applications in hand surgery is still small.
CONCLUSION
Although various promising applications of artificial intelligence in hand surgery and rehabilitation show strong performances, their implementation mostly takes place within the context of experimental studies. Therefore, their use in daily clinical routine is still limited.
Topics: Humans; Artificial Intelligence; Carpal Tunnel Syndrome; Fractures, Bone; Hand; Image Processing, Computer-Assisted
PubMed: 36633789
DOI: 10.1007/s11548-023-02831-3 -
Digital Health 2023Due to the large volume of online health information, while quality remains dubious, understanding the usage of artificial intelligence to evaluate health information... (Review)
Review
BACKGROUND
Due to the large volume of online health information, while quality remains dubious, understanding the usage of artificial intelligence to evaluate health information and surpass human-level performance is crucial. However, the existing studies still need a comprehensive review highlighting the vital machine, and Deep learning techniques for the automatic health information evaluation process.
OBJECTIVE
Therefore, this study outlines the most recent developments and the current state of the art regarding evaluating the quality of online health information on web pages and specifies the direction of future research.
METHODS
In this article, a systematic literature is conducted according to the PRISMA statement in eight online databases PubMed, Science Direct, Scopus, ACM, Springer Link, Wiley Online Library, Emerald Insight, and Web of Science to identify all empirical studies that use machine and deep learning models for evaluating the online health information quality. Furthermore, the selected techniques are compared based on their characteristics, such as health quality criteria, quality measurement tools, algorithm type, and achieved performance.
RESULTS
The included papers evaluate health information on web pages using over 100 quality criteria. The results show no universal quality dimensions used by health professionals and machine or deep learning practitioners while evaluating health information quality. In addition, the metrics used to assess the model performance are not the same as those used to evaluate human performance.
CONCLUSIONS
This systemic review offers a novel perspective in approaching the health information quality in web pages that can be used by machine and deep learning practitioners to tackle the problem more effectively.
PubMed: 38025112
DOI: 10.1177/20552076231212296