-
Arthroscopy : the Journal of... Feb 2024To determine the model performance of artificial intelligence (AI) in detecting rotator cuff pathology using different imaging modalities and to compare capability with... (Review)
Review
PURPOSE
To determine the model performance of artificial intelligence (AI) in detecting rotator cuff pathology using different imaging modalities and to compare capability with physicians in clinical scenarios.
METHODS
The review followed the PRISMA guidelines and was registered on PROSPERO. The criteria were as follows: 1) studies on the application of AI in detecting rotator cuff pathology using medical images, and 2) studies on smart devices for assisting in diagnosis were excluded. The following data were extracted and recorded: statistical characteristics, input features, AI algorithms used, sample sizes of training and testing sets, and model performance. The data extracted from the included studies were narratively reviewed.
RESULTS
A total of 14 articles, comprising 23,119 patients, met the inclusion and exclusion criteria. The pooled mean age of the patients was 56.7 years, and the female rate was 56.1%. The area under the curve (AUC) of the algorithmic model to detect rotator cuff pathology from ultrasound images, MRI images, and radiographic series ranged from 0.789 to 0.950, 0.844 to 0.943, and 0.820 to 0.830, respectively. Notably, 1 of the studies reported that AI models based on ultrasound images demonstrated a diagnostic performance similar to that of radiologists. Another comparative study demonstrated that AI models using MRI images exhibited greater accuracy and specificity compared to orthopedic surgeons in the diagnosis of rotator cuff pathology, albeit not in sensitivity.
CONCLUSIONS
The detection of rotator cuff pathology has been significantly aided by the exceptional performance of AI models. In particular, these models are equally adept as musculoskeletal radiologists in using ultrasound to diagnose rotator cuff pathology. Furthermore, AI models exhibit statistically superior levels of accuracy and specificity when using MRI to diagnose rotator cuff pathology, albeit with no marked difference in sensitivity, in comparison to orthopaedic surgeons.
LEVEL OF EVIDENCE
Level III, systematic review of Level III studies.
Topics: Humans; Female; Middle Aged; Rotator Cuff; Rotator Cuff Injuries; Artificial Intelligence; Magnetic Resonance Imaging; Algorithms
PubMed: 37355191
DOI: 10.1016/j.arthro.2023.06.018 -
Computer Methods and Programs in... Feb 2024Non-alcoholic fatty liver disease (NAFLD) is a common liver disease with a rapidly growing incidence worldwide. For prognostication and therapeutic decisions, it is... (Review)
Review
BACKGROUND AND OBJECTIVES
Non-alcoholic fatty liver disease (NAFLD) is a common liver disease with a rapidly growing incidence worldwide. For prognostication and therapeutic decisions, it is important to distinguish the pathological stages of NAFLD: steatosis, steatohepatitis, and liver fibrosis, which are definitively diagnosed on invasive biopsy. Non-invasive ultrasound (US) imaging, including US elastography technique, and clinical parameters can be used to diagnose and grade NAFLD and its complications. Artificial intelligence (AI) is increasingly being harnessed for developing NAFLD diagnostic models based on clinical, biomarker, or imaging data. In this work, we systemically reviewed the literature for AI-enabled NAFLD diagnostic models based on US (including elastography) and clinical (including serological) data.
METHODS
We performed a comprehensive search on Google Scholar, Scopus, and PubMed search engines for articles published between January 2005 and June 2023 related to AI models for NAFLD diagnosis based on US and/or clinical parameters using the following search terms: "non-alcoholic fatty liver disease", "non-alcoholic steatohepatitis", "deep learning", "machine learning", "artificial intelligence", "ultrasound imaging", "sonography", "clinical information".
RESULTS
We reviewed 64 published models that used either US (including elastography) or clinical data input to detect the presence of NAFLD, non-alcoholic steatohepatitis, and/or fibrosis, and in some cases, the severity of steatosis, inflammation, and/or fibrosis as well. The performances of the published models were summarized, and stratified by data input and algorithms used, which could be broadly divided into machine and deep learning approaches.
CONCLUSION
AI models based on US imaging and clinical data can reliably detect NAFLD and its complications, thereby reducing diagnostic costs and the need for invasive liver biopsy. The models offer advantages of efficiency, accuracy, and accessibility, and serve as virtual assistants for specialists to accelerate disease diagnosis and reduce treatment costs for patients and healthcare systems.
Topics: Humans; Artificial Intelligence; Biomarkers; Biopsy; Liver; Liver Cirrhosis; Non-alcoholic Fatty Liver Disease; Ultrasonography
PubMed: 38008040
DOI: 10.1016/j.cmpb.2023.107932 -
Critical Reviews in Food Science and... 2024Neural network (i.e. deep learning, NN)-based data analysis techniques have been listed as a pivotal opportunity to protect the integrity and safety of the global food... (Review)
Review
Neural network (i.e. deep learning, NN)-based data analysis techniques have been listed as a pivotal opportunity to protect the integrity and safety of the global food supply chain and forecast $11.2 billion in agriculture markets. As a general-purpose data analytic tool, NN has been applied in several areas of food science, such as food recognition, food supply chain security and omics analysis, and so on. Therefore, given the rapid emergence of NN applications in food safety, this review aims to provide a comprehensive overview of the NN application in food analysis for the first time, focusing on domain-specific applications in food analysis by introducing fundamental methodology, reviewing recent and notable progress, and discussing challenges and potential pitfalls. NN demonstrated that it has a bright future through effective collaboration between food specialist and the broader community in the food field, for example, superiority in food recognition, sensory evaluation, pattern recognition of spectroscopy and chromatography. However, major challenges impeded NN extension including void in the food scientist-friendly interface software package, incomprehensible model behavior, multi-source heterogeneous data, and so on. The breakthrough from other fields proved NN has the potential to offer a revolution in the immediate future.
Topics: Neural Networks, Computer; Humans; Food Analysis; Food Safety; Food Technology; Food Supply; Deep Learning
PubMed: 36322538
DOI: 10.1080/10408398.2022.2139217 -
Seminars in Nuclear Medicine Nov 2023Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are... (Review)
Review
Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting. V/Q studies have witnessed a long fluctuation in adoption rates in parallel to continuous advances in image processing and computer vision techniques. This review provides an overview on the status of artificial intelligence (AI) in V/Q scintigraphy. To clearly assess the past, current, and future role of AI in V/Q scans, we conducted a systematic Ovid MEDLINE(R) literature search from 1946 to August 5, 2022 in addition to a manual search. The literature was reviewed and summarized in terms of methodologies and results for the various applications of AI to V/Q scans. The PRISMA guidelines were followed. Thirty-one publications fulfilled our search criteria and were grouped into two distinct categories: (1) disease diagnosis/detection (N = 22, 71.0%) and (2) cross-modality image translation into V/Q images (N = 9, 29.0%). Studies on disease diagnosis and detection relied heavily on shallow artificial neural networks for acute pulmonary embolism (PE) diagnosis and were primarily published between the mid-1990s and early 2000s. Recent applications almost exclusively regard image translation tasks from CT to ventilation or perfusion images with modern algorithms, such as convolutional neural networks, and were published between 2019 and 2022. AI research in V/Q scintigraphy for acute PE diagnosis in the mid-90s to early 2000s yielded promising results but has since been largely neglected and thus have yet to benefit from today's state-of-the art machine-learning techniques, such as deep neural networks. Recently, the main application of AI for V/Q has shifted towards generating synthetic ventilation and perfusion images from CT. There is therefore considerable potential to expand and modernize the use of real V/Q studies with state-of-the-art deep learning approaches, especially for workflow optimization and PE detection at both acute and chronic stages. We discuss future challenges and potential directions to compensate for the lag in this domain and enhance the value of this traditional nuclear medicine scan.
Topics: Humans; Artificial Intelligence; Pulmonary Embolism; Lung; Radionuclide Imaging; Perfusion Imaging; Tomography, Emission-Computed, Single-Photon
PubMed: 37080822
DOI: 10.1053/j.semnuclmed.2023.03.002 -
Journal of the American College of... Feb 2024To summarize the literature regarding the performance of mammography-image based artificial intelligence (AI) algorithms, with and without additional clinical data, for...
PURPOSE
To summarize the literature regarding the performance of mammography-image based artificial intelligence (AI) algorithms, with and without additional clinical data, for future breast cancer risk prediction.
MATERIALS AND METHODS
A systematic literature review was performed using six databases (medRixiv, bioRxiv, Embase, Engineer Village, IEEE Xplore, and PubMed) from 2012 through September 30, 2022. Studies were included if they used real-world screening mammography examinations to validate AI algorithms for future risk prediction based on images alone or in combination with clinical risk factors. The quality of studies was assessed, and predictive accuracy was recorded as the area under the receiver operating characteristic curve (AUC).
RESULTS
Sixteen studies met inclusion and exclusion criteria, of which 14 studies provided AUC values. The median AUC performance of AI image-only models was 0.72 (range 0.62-0.90) compared with 0.61 for breast density or clinical risk factor-based tools (range 0.54-0.69). Of the seven studies that compared AI image-only performance directly to combined image + clinical risk factor performance, six demonstrated no significant improvement, and one study demonstrated increased improvement.
CONCLUSIONS
Early efforts for predicting future breast cancer risk based on mammography images alone demonstrate comparable or better accuracy to traditional risk tools with little or no improvement when adding clinical risk factor data. Transitioning from clinical risk factor-based to AI image-based risk models may lead to more accurate, personalized risk-based screening approaches.
Topics: Humans; Female; Breast Neoplasms; Mammography; Artificial Intelligence; Early Detection of Cancer; Breast; Retrospective Studies
PubMed: 37949155
DOI: 10.1016/j.jacr.2023.10.018 -
Journal of the American Medical... Nov 2023To describe and appraise the use of artificial intelligence (AI) techniques that can cope with longitudinal data from electronic health records (EHRs) to predict...
OBJECTIVE
To describe and appraise the use of artificial intelligence (AI) techniques that can cope with longitudinal data from electronic health records (EHRs) to predict health-related outcomes.
METHODS
This review included studies in any language that: EHR was at least one of the data sources, collected longitudinal data, used an AI technique capable of handling longitudinal data, and predicted any health-related outcomes. We searched MEDLINE, Scopus, Web of Science, and IEEE Xplorer from inception to January 3, 2022. Information on the dataset, prediction task, data preprocessing, feature selection, method, validation, performance, and implementation was extracted and summarized using descriptive statistics. Risk of bias and completeness of reporting were assessed using a short form of PROBAST and TRIPOD, respectively.
RESULTS
Eighty-one studies were included. Follow-up time and number of registers per patient varied greatly, and most predicted disease development or next event based on diagnoses and drug treatments. Architectures generally were based on Recurrent Neural Networks-like layers, though in recent years combining different layers or transformers has become more popular. About half of the included studies performed hyperparameter tuning and used attention mechanisms. Most performed a single train-test partition and could not correctly assess the variability of the model's performance. Reporting quality was poor, and a third of the studies were at high risk of bias.
CONCLUSIONS
AI models are increasingly using longitudinal data. However, the heterogeneity in reporting methodology and results, and the lack of public EHR datasets and code sharing, complicate the possibility of replication.
REGISTRATION
PROSPERO database (CRD42022331388).
Topics: Humans; Artificial Intelligence; Electronic Health Records
PubMed: 37659105
DOI: 10.1093/jamia/ocad168 -
Annals of Medicine Dec 2024Utilizing artificial intelligence (AI) in chatbots, especially for chronic diseases, has become increasingly prevalent. These AI-powered chatbots serve as crucial tools...
BACKGROUND
Utilizing artificial intelligence (AI) in chatbots, especially for chronic diseases, has become increasingly prevalent. These AI-powered chatbots serve as crucial tools for enhancing patient communication, addressing the rising prevalence of chronic conditions, and meeting the growing demand for supportive healthcare applications. However, there is a notable gap in comprehensive reviews evaluating the impact of AI-powered chatbot interventions in healthcare within academic literature. This study aimed to assess user satisfaction, intervention efficacy, and the specific characteristics and AI architectures of chatbot systems designed for chronic diseases.
METHOD
A thorough exploration of the existing literature was undertaken by employing diverse databases such as PubMed MEDLINE, CINAHL, EMBASE, PsycINFO, ACM Digital Library and Scopus. The studies incorporated in this analysis encompassed primary research that employed chatbots or other forms of AI architecture in the context of preventing, treating or rehabilitating chronic diseases. The assessment of bias risk was conducted using Risk of 2.0 Tools.
RESULTS
Seven hundred and eighty-four results were obtained, and subsequently, eight studies were found to align with the inclusion criteria. The intervention methods encompassed health education ( = 3), behaviour change theory ( = 1), stress and coping ( = 1), cognitive behavioural therapy ( = 2) and self-care behaviour ( = 1). The research provided valuable insights into the effectiveness and user-friendliness of AI-powered chatbots in handling various chronic conditions. Overall, users showed favourable acceptance of these chatbots for self-managing chronic illnesses.
CONCLUSIONS
The reviewed studies suggest promising acceptance of AI-powered chatbots for self-managing chronic conditions. However, limited evidence on their efficacy due to insufficient technical documentation calls for future studies to provide detailed descriptions and prioritize patient safety. These chatbots employ natural language processing and multimodal interaction. Subsequent research should focus on evidence-based evaluations, facilitating comparisons across diverse chronic health conditions.
Topics: Humans; Artificial Intelligence; Chronic Disease; Coping Skills; Databases, Factual
PubMed: 38466897
DOI: 10.1080/07853890.2024.2302980 -
Frontiers in Public Health 2023To systematically compare and rank the accuracy of AI-based intraocular lens (IOL) power calculation formulas and traditional IOL formulas in highly myopic eyes. (Meta-Analysis)
Meta-Analysis
OBJECTIVE
To systematically compare and rank the accuracy of AI-based intraocular lens (IOL) power calculation formulas and traditional IOL formulas in highly myopic eyes.
METHODS
We screened PubMed, Web of Science, Embase, and Cochrane Library databases for studies published from inception to April 2023. The following outcome data were collected: mean absolute error (MAE), percentage of eyes with a refractive prediction error (PE) within ±0.25, ±0.50, and ±1.00 diopters (D), and median absolute error (MedAE). The network meta-analysis was conducted by R 4.3.0 and STATA 17.0.
RESULTS
Twelve studies involving 2,430 adult myopic eyes (with axial lengths >26.0 mm) that underwent uncomplicated cataract surgery with mono-focal IOL implantation were included. The network meta-analysis of 21 formulas showed that the top three AI-based formulas, as per the surface under the cumulative ranking curve (SUCRA) values, were XGBoost, Hill-RBF, and Kane. The three formulas had the lowest MedAE and were more accurate than traditional vergence formulas, such as SRK/T, Holladay 1, Holladay 2, Haigis, and Hoffer Q regarding MAE, percentage of eyes with PE within ±0.25, ±0.50, and ±1.00 D.
CONCLUSIONS
The top AI-based formulas for calculating IOL power in highly myopic eyes were XGBoost, Hill-RBF, and Kane. They were significantly more accurate than traditional vergence formulas and ranked better than formulas with Wang-Koch AL modifications or newer generations of formulas such as Barrett and Olsen.
SYSTEMATIC REVIEW REGISTRATION
https://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42022335969.
Topics: Adult; Humans; Refraction, Ocular; Lenses, Intraocular; Artificial Intelligence; Network Meta-Analysis; Retrospective Studies; Myopia; Refractive Errors
PubMed: 38026369
DOI: 10.3389/fpubh.2023.1279718 -
Indian Pediatrics Jul 2023The emergence of artificial intelligence (AI) tools such as ChatGPT and Bard is disrupting a broad swathe of fields, including medicine. In pediatric medicine, AI is...
BACKGROUND
The emergence of artificial intelligence (AI) tools such as ChatGPT and Bard is disrupting a broad swathe of fields, including medicine. In pediatric medicine, AI is also increasingly being used across multiple subspecialties. However, the practical application of AI still faces a number of key challenges. Consequently, there is a requirement for a concise overview of the roles of AI across the multiple domains of pediatric medicine, which the current study seeks to address.
AIM
To systematically assess the challenges, opportunities, and explainability of AI in pediatric medicine.
METHODOLOGY
A systematic search was carried out on peer-reviewed databases, PubMed Central, Europe PubMed Central, and grey literature using search terms related to machine learning (ML) and AI for the years 2016 to 2022 in the English language. A total of 210 articles were retrieved that were screened with PRISMA for abstract, year, language, context, and proximal relevance to research aims. A thematic analysis was carried out to extract findings from the included studies.
RESULTS
Twenty articles were selected for data abstraction and analysis, with three consistent themes emerging from these articles. In particular, eleven articles address the current state-of-the-art application of AI in diagnosing and predicting health conditions such as behavioral and mental health, cancer, syndromic and metabolic diseases. Five articles highlight the specific challenges of AI deployment in pediatric medicines: data security, handling, authentication, and validation. Four articles set out future opportunities for AI to be adapted: the incorporation of Big Data, cloud computing, precision medicine, and clinical decision support systems. These studies collectively critically evaluate the potential of AI in overcoming current barriers to adoption.
CONCLUSION
AI is proving disruptive within pediatric medicine and is presently associated with challenges, opportunities, and the need for explainability. AI should be viewed as a tool to enhance and support clinical decision-making rather than a substitute for human judgement and expertise. Future research should consequently focus on obtaining comprehensive data to ensure the generalizability of research findings.
Topics: Artificial Intelligence; Pediatrics; Clinical Decision-Making; Humans; Child, Preschool; Child; Deep Learning
PubMed: 37424120
DOI: No ID Found -
European Review For Medical and... Oct 2023Acute kidney injury (AKI) increases mortality and costs in hospitalized patients. New methods for early AKI identification have been developed with targeted biomarkers...
OBJECTIVE
Acute kidney injury (AKI) increases mortality and costs in hospitalized patients. New methods for early AKI identification have been developed with targeted biomarkers and electronic health records data analysis. Machine learning (ML) use in diagnostics and health data analysis has recently increased. We performed a systematic review to analyze the use of ML for AKI prediction in hospitalized adults.
MATERIALS AND METHODS
Tubmed, EMBASE, Cochrane, and Web of Science databases were searched until 31st March of 2023. English-language studies using ML in adults for AKI prediction were included using predetermined eligibility search terms such as acute kidney injury, machine learning, and artificial intelligence. Two reviewers evaluated the publications' titles, abstracts, and full texts separately and obtained appropriate data. The main outcome was an area under the curve (AUC) result of at least 0.70.
RESULTS
Ten studies in 102 articles were included involving 242,251 patients. Deep learning (AUC 0.907 in critical care AKI; AUC 0.797 in hospitalized patients AKI) was similar to Logistic regression (AUC 0.877 in critical care AKI; AUC 0.789 in hospitalized patients). Decision tree constructions had similar AUC.
CONCLUSIONS
In this review, most ML models analyzed fulfilled the main outcome. AKI is multifactorial; however, ML performed well with different etiologies, such as cardiac-related AKI, drug-related AKI, and critical care patients. Overfitting data and constructing black box models are limitations that might jeopardize the generalization and comprehension of the results. Most studies were single-center, and three manuscripts used the same database with a predominantly Caucasian population, resulting in a lack of diversity and reducing external generalization. In conclusion, ML could effectively predict AKI in hospitalized adults. Future directions rely on including a more diverse population and completing prospective and controlled trials.
Topics: Adult; Humans; Artificial Intelligence; Prospective Studies; Biomarkers; Machine Learning; Acute Kidney Injury
PubMed: 37916354
DOI: 10.26355/eurrev_202310_34164