Medical artificial intelligent research: translating artificial intelligence into clinical practice.
Ontology highlight
ABSTRACT:
SUBMITTER: Lin H
PROVIDER: S-EPMC7327358 | biostudies-literature | 2020 Jun
REPOSITORIES: biostudies-literature
Publications
Medical artificial intelligent research: translating artificial intelligence into clinical practice.
Annals of translational medicine 20200601 11
Similar Datasets
Project description: Not available
| S-EPMC7327360 | biostudies-literature
Project description:Artificial intelligence (AI), including machine learning (ML), has transformed numerous industries through newfound efficiencies and supportive decision-making. With the exponential growth of computing power and large datasets, AI has transitioned from theory to reality in teaching machines to automate tasks without human supervision. AI-based computational algorithms analyze "training sets" using pattern recognition and learning from inputted data to classify and predict outputs that otherwise could not be effectively analyzed with human processing or standard statistical methods. Though widespread understanding of the fundamental principles and adoption of applications have yet to be achieved, recent applications and research efforts implementing AI have demonstrated great promise in predicting future injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting telehealth. With appreciation, caution, and experience applying AI, the potential to automate tasks and improve data-driven insights may be realized to fundamentally improve patient care. The purpose of this review is to discuss the pearls, pitfalls, and applications associated with AI.
| S-EPMC7441013 | biostudies-literature
Project description:Pharmacogenetic/pharmacogenomic (PGx) approaches to psychopharmacology aim to identify clinically meaningful predictors of drug efficacy and/or side-effect burden. To date, however, PGx studies in psychiatry have not yielded compelling results, and clinical utilization of PGx testing in psychiatry is extremely limited. In this review, the authors provide a brief overview on the status of PGx studies in psychiatry, review the commercialization process for PGx tests and then discuss methodological considerations that may enhance the potential for clinically applicable PGx tests in psychiatry. The authors focus on design considerations that include increased ascertainment of subjects in the earliest phases of illness, discuss the advantages of drug-induced adverse events as phenotypes for examination and emphasize the importance of maximizing adherence to treatment in pharmacogenetic studies. Finally, the authors discuss unique aspects of pharmacogenetic studies that may distinguish them from studies of other complex traits. Taken together, these data provide insights into the design and methodological considerations that may enhance the potential for clinical utility of PGx studies.
| S-EPMC3928114 | biostudies-literature
Project description:Several factors, including advances in computational algorithms, the availability of high-performance computing hardware, and the assembly of large community-based databases, have led to the extensive application of Artificial Intelligence (AI) in the biomedical domain for nearly 20 years. AI algorithms have attained expert-level performance in cancer research. However, only a few AI-based applications have been approved for use in the real world. Whether AI will eventually be capable of replacing medical experts has been a hot topic. In this article, we first summarize the cancer research status using AI in the past two decades, including the consensus on the procedure of AI based on an ideal paradigm and current efforts of the expertise and domain knowledge. Next, the available data of AI process in the biomedical domain are surveyed. Then, we review the methods and applications of AI in cancer clinical research categorized by the data types including radiographic imaging, cancer genome, medical records, drug information and biomedical literatures. At last, we discuss challenges in moving AI from theoretical research to real-world cancer research applications and the perspectives toward the future realization of AI participating cancer treatment.
| S-EPMC8769909 | biostudies-literature
Project description:Background/Objectives: Orthopaedic trauma management in polytrauma patients presents challenges, particularly in selecting between damage control orthopaedics (DCO) and early appropriate care (EAC). This systematic review evaluates these approaches and explores the role of biomarkers in optimising surgical timing. The primary objective of this review was to evaluate the potential clinical utility of biomarkers in guiding surgical timing and predicting perioperative complications. The secondary objective was to compare the effectiveness of DCO and EAC approaches, focusing on their impact on patient outcomes when controlled for Injury Severity Scores (ISSs). Methods: A systematic search of PubMed, MEDLINE, and Google Scholar identified studies focusing on fracture management (DCO versus EAC), timing protocols, and biomarkers in polytrauma patients. Twenty-seven studies met inclusion criteria. Results: Among the 27 studies, 12 evaluated biomarkers and 15 compared DCO and EAC. Point-of-care (POC) biomarkers, including lactate (p < 0.001; OR 1.305), monocyte L-selectin (p = 0.001; OR 1.5), and neutrophil L-selectin (p = 0.005; OR 1.56), demonstrated predictive value for sepsis, infection, and morbidity. CD16bright/CD62Ldim neutrophils were significant predictors of infection (p = 0.002). Advanced biomarkers, such as IL-6, IL-10, RNA IL-7R, HMGB1, and leptin offered prognostic insights but required longer processing times. No clear superiority was identified between DCO and EAC, with comparable outcomes when injury severity scores (ISS) were controlled. Conclusions: This systematic review highlights the challenge of translating biomarker research into clinical practice, identifying several point-of-care and advanced laboratory biomarkers with significant potential to predict complications like sepsis, infection, and MODS. Future efforts should focus on refining biomarker thresholds, advancing point-of-care technologies, and validating their role in improving surgical timing and trauma care outcomes.
| S-EPMC11856232 | biostudies-literature
Project description:BackgroundThe number of artificial intelligence (AI) studies in medicine has exponentially increased recently. However, there is no clear quantification of the clinical benefits of implementing AI-assisted tools in patient care.ObjectiveThis study aims to systematically review all published randomized controlled trials (RCTs) of AI-assisted tools to characterize their performance in clinical practice.MethodsCINAHL, Cochrane Central, Embase, MEDLINE, and PubMed were searched to identify relevant RCTs published up to July 2021 and comparing the performance of AI-assisted tools with conventional clinical management without AI assistance. We evaluated the primary end points of each study to determine their clinical relevance. This systematic review was conducted following the updated PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines.ResultsAmong the 11,839 articles retrieved, only 39 (0.33%) RCTs were included. These RCTs were conducted in an approximately equal distribution from North America, Europe, and Asia. AI-assisted tools were implemented in 13 different clinical specialties. Most RCTs were published in the field of gastroenterology, with 15 studies on AI-assisted endoscopy. Most RCTs studied biosignal-based AI-assisted tools, and a minority of RCTs studied AI-assisted tools drawn from clinical data. In 77% (30/39) of the RCTs, AI-assisted interventions outperformed usual clinical care, and clinically relevant outcomes improved with AI-assisted intervention in 70% (21/30) of the studies. Small sample size and single-center design limited the generalizability of these studies.ConclusionsThere is growing evidence supporting the implementation of AI-assisted tools in daily clinical practice; however, the number of available RCTs is limited and heterogeneous. More RCTs of AI-assisted tools integrated into clinical practice are needed to advance the role of AI in medicine.Trial registrationPROSPERO CRD42021286539; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=286539.
| S-EPMC9459941 | biostudies-literature
Project description:ObjectiveMTX remains the cornerstone for therapy for RA, yet research shows that non-adherence is significant and correlates with response to therapy. This study aimed to halve self-reported non-adherence to MTX at the Kellgren Centre for Rheumatology.MethodsAn anonymous self-report adherence questionnaire was developed and data collected for 3 months prior to the introduction of interventions, and then regularly for the subsequent 2.5 years. A series of interventions were implemented, including motivational interviewing training, consistent information about MTX and development of a summary bookmark. Information on clinic times was collected for consultations with and without motivational interviewing. Surveys were conducted to ascertain consistency of messages about MTX. A biochemical assay was used to test MTX serum levels in patients at two time points: before and 2.8 years following introduction of the changes. Remission rates at 6 and 12 months post-MTX initiation were retrieved from patient notes and cost savings estimated by comparing actual numbers of new biologic starters compared with expected numbers based on the numbers of consultants employed at the two time points.ResultsBetween June and August 2016, self-reported non-adherence to MTX was 24.7%. Following introduction of the interventions, self-reported non-adherence rates reduced to an average of 7.4% between April 2018 and August 2019. Clinic times were not significantly increased when motivational interviewing was employed. Consistency of messages by staff across three key areas (benefits of MTX, alcohol guidance and importance of adherence) improved from 64% in September 2016 to 94% in January 2018. Biochemical non-adherence reduced from 56% (September 2016) to 17% (June 2019), whilst remission rates 6 months post-initiation of MTX improved from 13% in 2014/15 to 37% in 2017/18, resulting is estimated cost savings of £30 000 per year.ConclusionNon-adherence to MTX can be improved using simple measures including focussing on the adherence and the benefits of treatment, and providing consistent information across departments.
| S-EPMC7785311 | biostudies-literature
Project description:BackgroundArtificial intelligence (AI) application is increasingly used in all fields, especially, in medicine. However, for the successful incorporation of AI-driven tools into medicine, healthcare professional should be equipped with the necessary knowledge. From that, we aimed to assess the AI readiness among medical students in Jordan.MethodsA cross-sectional survey was conducted among medical students across 6 Jordanian universities. Prevalidated Medical Artificial Intelligence Readiness Scale for Medical Students questionnaire was used. The questionnaire was distributed through social media groups of students. SPSS v.27 was used for analysis.ResultsA total of 858 responses were collected. The mean AI readiness score was 64.2%. Students scored more in the ability domain with a mean of 22.57. We found that academic performance (Grade point average) positively associated with overall AI readiness (P = .023), and prior exposure to AI through formal education or experience significantly enhances readiness (P = .009). In contrast, AI readiness levels did not significantly vary across different medical schools in Jordan. Notably, most students (84%) did not receive a formal education about AI from their schools.ConclusionIncorporation of AI education in medical curricula is crucial to close knowledge gaps and ensure that students are prepared for the use of AI in their future career. Our findings highlight the importance of preparing students to engage with AI technologies, and to be equipped with the necessary knowledge about its aspect.
| S-EPMC11437586 | biostudies-literature
Project description:The primary source of energy losses in distribution networks (DNs) is rooted in line losses, which is crucial to conduct a thorough and reasonable examination of any unusual sources of line losses to guarantee the power supply in a timely and safe manner. In recent studies, identifying and analyzing abnormal line losses in DNs has been a widely and challenging research subject. This article investigates a key technology for the line loss analyses of DNs and intelligent diagnosis of abnormal causes by implementing artificial intelligence (AI), resulting in several prominent results. The proposed algorithm optimizes the parameters of the support vector machine (SVM) and suggests an intelligent diagnosis algorithm called the Improved Sparrow Search Algorithm and Support Vector Machine (ISSA-SVM). The ISSA-SVM algorithm is trained to calculate the data anomalies of line losses when changing loads and exhibiting exceptional performance to identify abnormal line losses. The accuracy of abnormality identification employing the ISSA-SVM algorithm reaches an impressive 98%, surpassing the performances of other available algorithms. Moreover, the practical performance of the proposed approach for analyzing large volumes of abnormal line loss data daily in DNs is also noteworthy. The ISSA-SVM accurately identifies the root causes of abnormal line losses and lowers the error in calculating abnormal line loss data. By combining different types of power operation data and creating a multidimensional feature traceability model, the study successfully determines the factors contributing to abnormal line losses. The relationship between transformers and voltage among various lines is determined by using the Pearson correlation, which provides valuable insights into the relationship between these variables and line losses. The algorithm's reliability and its potential to be applied to real-world scenarios bring an opportunity to improve the efficiency and safety of power supply systems. The ISSA that incorporates advanced techniques such as the Sobol sequence, golden sine algorithm, and Gaussian difference mutation appears to be a promising tool.
| S-EPMC10773768 | biostudies-literature
Project description:BackgroundPeople with atrial fibrillation (AF) have lower reported quality of life and increased risk of heart attack, death, and stroke. Lifestyle modifications can improve arrhythmia-free survival/symptom severity. Shared medical appointments (SMAs) have been effective at targeting lifestyle change in other chronic diseases and may be beneficial for patients with AF.ObjectiveTo determine if perceived self-management and satisfaction with provider communication differed between patients who participated in SMAs compared to patients in standard care. Secondary objectives were to examine differences between groups for knowledge about AF, symptom severity, and healthcare utilization.MethodsWe conducted a retrospective analysis of data collected where patients were assigned to either standard care (n = 62) or a SMA (n = 59). Surveys were administered at pre-procedure, 3, and 6 months.ResultsPerceived self-management was not significantly different at baseline (p = 0.95) or 6 months (p = 0.21). Patients in SMAs reported more knowledge gain at baseline (p = 0.01), and higher goal setting at 6 months (p = 0.0045). Symptom severity for both groups followed similar trends.ConclusionPatients with AF who participated in SMAs had similar perceived self-management, patient satisfaction with provider communication, symptom severity, and healthcare utilization with their counterparts, but had a statistically significant improvement in knowledge about their disease.
| S-EPMC7880477 | biostudies-literature