Using Machine Learning to Predict Antimicrobial Resistance―A Literature Review DOI Creative Commons
Aikaterini Sakagianni, Christina Koufopoulou, Georgios Feretzakis

et al.

Antibiotics, Journal Year: 2023, Volume and Issue: 12(3), P. 452 - 452

Published: Feb. 24, 2023

Machine learning (ML) algorithms are increasingly applied in medical research and healthcare, gradually improving clinical practice. Among various applications of these novel methods, their usage the combat against antimicrobial resistance (AMR) is one most crucial areas interest, as increasing to antibiotics management difficult-to-treat multidrug-resistant infections significant challenges for countries worldwide, with life-threatening consequences. As antibiotic efficacy treatment options decrease, need implementation multimodal stewardship programs utmost importance order restrict misuse prevent further aggravation AMR problem. Both supervised unsupervised machine tools have been successfully used predict early resistance, thus support clinicians selecting appropriate therapy. In this paper, we reviewed existing literature on artificial intelligence (AI) general conjunction prediction. This a narrative review, where discuss ML methods field value complementary tool practice, mainly from clinician’s point view.

Language: Английский

Human–AI collaboration enables more empathic conversations in text-based peer-to-peer mental health support DOI
Ashish Sharma, Inna Wanyin Lin, Adam S. Miner

et al.

Nature Machine Intelligence, Journal Year: 2023, Volume and Issue: 5(1), P. 46 - 57

Published: Jan. 23, 2023

Language: Английский

Citations

187
The shaky foundations of large language models and foundation models for electronic health records DOI Creative Commons
Michael Wornow, Yizhe Xu, Rahul Thapa

et al.

npj Digital Medicine, Journal Year: 2023, Volume and Issue: 6(1)

Published: July 29, 2023

The success of foundation models such as ChatGPT and AlphaFold has spurred significant interest in building similar for electronic medical records (EMRs) to improve patient care hospital operations. However, recent hype obscured critical gaps our understanding these models' capabilities. In this narrative review, we examine 84 trained on non-imaging EMR data (i.e., clinical text and/or structured data) create a taxonomy delineating their architectures, training data, potential use cases. We find that most are small, narrowly-scoped datasets (e.g., MIMIC-III) or broad, public biomedical corpora PubMed) evaluated tasks do not provide meaningful insights usefulness health systems. Considering findings, propose an improved evaluation framework measuring the benefits is more closely grounded metrics matter healthcare.

Language: Английский

Citations

150
Using machine learning for healthcare challenges and opportunities DOI Creative Commons
Abdullah Alanazi

Informatics in Medicine Unlocked, Journal Year: 2022, Volume and Issue: 30, P. 100924 - 100924

Published: Jan. 1, 2022

Machine learning (ML) and its applications in healthcare have gained a lot of attention. When enhanced computational power is combined with big data, there an opportunity to use ML algorithms improve health care. Supervised the type that can be implemented predict labeled data based on such as linear or logistic regression, support vector machine, decision tree, LASSO K Nearest Neighbor, Naive Bayes classifier. Unsupervised models identify patterns datasets do not contain information about outcome. Such used for fraud anomaly detection. Examples clinical include formulation various systems. An important public application identification prediction populations at high risk developing certain adverse outcomes development interventions targeted these populations. Various concepts related need integrated into medical curriculum so professionals effectively guide interpret research this area.

Language: Английский

Citations

140
A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics DOI Open Access
Hong-Yu Zhou,

Yizhou Yu,

Chengdi Wang

et al.

Nature Biomedical Engineering, Journal Year: 2023, Volume and Issue: 7(6), P. 743 - 755

Published: June 12, 2023

Language: Английский

Citations

133
Artificial Intelligence Applications in Health Care Practice: Scoping Review DOI Creative Commons
Malvika Sharma, Carl Savage, Monika Nair

et al.

Journal of Medical Internet Research, Journal Year: 2022, Volume and Issue: 24(10), P. e40238 - e40238

Published: Aug. 30, 2022

Artificial intelligence (AI) is often heralded as a potential disruptor that will transform the practice of medicine. The amount data collected and available in health care, coupled with advances computational power, has contributed to AI an exponential growth publications. However, development applications does not guarantee their adoption into routine practice. There risk despite resources invested, benefits for patients, staff, society be realized if implementation better understood.The aim this study was explore how care been described researched literature by answering 3 questions: What are characteristics research on practice? types systems described? process discernible?A scoping review conducted MEDLINE (PubMed), Scopus, Web Science, CINAHL, PsycINFO databases identify empirical studies since 2011, addition snowball sampling selected reference lists. Using Rayyan software, we screened titles abstracts full-text articles. Data from included articles were charted summarized.Of 9218 records retrieved, 45 (0.49%) included. cover diverse clinical settings disciplines; most (32/45, 71%) published recently, high-income countries (33/45, 73%), intended providers (25/45, 56%). predominantly particularly pertaining patient-provider encounters. More than half (24/45, 53%) possess no action autonomy but rather support human decision-making. focus establishing effectiveness interventions (16/45, 35%) or related technical aspects (11/45, 24%). Focus specifics processes yet seem priority research, use frameworks guide rare.Our current knowledge derives implementations low approaches common other information systems. To develop specific empirically based framework, further needed more disruptive being implemented unique such building trust, addressing transparency issues, developing explainable interpretable solutions, ethical concerns around privacy protection.

Language: Английский

Citations

117
Chatbots for future docs: exploring medical students’ attitudes and knowledge towards artificial intelligence and medical chatbots DOI Creative Commons
Julia-Astrid Moldt, Teresa Festl‐Wietek, Amir Madany Mamlouk

et al.

Medical Education Online, Journal Year: 2023, Volume and Issue: 28(1)

Published: Feb. 28, 2023

Artificial intelligence (AI) in medicine and digital assistance systems such as chatbots will play an increasingly important role future doctor - patient communication. To benefit from the potential of this technical innovation ensure optimal care, physicians should be equipped with appropriate skills. Accordingly, a suitable place for management adaptation must found medical education curriculum. determine existing levels knowledge students about AI particular healthcare setting, study surveyed University Luebeck Hospital Tuebingen. Using standardized quantitative questionnaires qualitative analysis group discussions, attitudes toward were investigated. From this, relevant requirements integration into curriculum could identified. The aim was to establish basic understanding opportunities, limitations, risks, well areas application technology. participants (N = 12) able develop how affect their daily work. Although use positive, also expressed concerns. There high agreement regarding administrative settings (83.3%) research health-related data (91.7%). However, concerns that protection may insufficiently guaranteed (33.3%) they might monitored at work (58.3%). evaluations indicated want engage more intensively medicine. In view developments, competencies taught structured way during integrated curricular teaching.

Language: Английский

Citations

110
FDA-Approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: An Updated Landscape DOI Open Access
Geeta Joshi, Aditi Jain,

Shalini Reddy Araveeti

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(3), P. 498 - 498

Published: Jan. 24, 2024

As artificial intelligence (AI) has been highly advancing in the last decade, machine learning (ML)-enabled medical devices are increasingly used healthcare. In this study, we collected publicly available information on AI/ML-enabled approved by FDA United States, as of latest update 19 October 2023. We performed comprehensive analysis a total 691 FDA-approved and (AI/ML)-enabled offer an in-depth clearance pathways, approval timeline, regulation type, specialty, decision recall history, etc. found significant surge approvals since 2018, with clear dominance radiology specialty application tools, attributed to abundant data from routine clinical data. The study also reveals reliance 510(k)-clearance pathway, emphasizing its basis substantial equivalence often bypassing need for new trials. Also, it notes underrepresentation pediatric-focused trials, suggesting opportunity expansion demographic. Moreover, geographical limitation primarily within points more globally inclusive trials encompass diverse patient demographics. This not only maps current landscape but pinpoints trends, potential gaps, areas future exploration, trial practices, regulatory approaches. conclusion, our sheds light state prevailing contributing wider comprehension.

Language: Английский

Citations

109
Using artificial intelligence to improve public health: a narrative review DOI Creative Commons
David B. Olawade,

Ojima J. Wada,

Aanuoluwapo Clement David-Olawade

et al.

Frontiers in Public Health, Journal Year: 2023, Volume and Issue: 11

Published: Oct. 26, 2023

Artificial intelligence (AI) is a rapidly evolving tool revolutionizing many aspects of healthcare. AI has been predominantly employed in medicine and healthcare administration. However, public health, the widespread employment only began recently, with advent COVID-19. This review examines advances health potential challenges that lie ahead. Some ways aided delivery are via spatial modeling, risk prediction, misinformation control, surveillance, disease forecasting, pandemic/epidemic diagnosis. implementation not universal due to factors including limited infrastructure, lack technical understanding, data paucity, ethical/privacy issues.

Language: Английский

Citations

106
Automated Interpretation of Clinical Electroencephalograms Using Artificial Intelligence DOI Creative Commons

Jesper Tveit,

Harald Aurlien,

Sergey M. Plis

et al.

JAMA Neurology, Journal Year: 2023, Volume and Issue: 80(8), P. 805 - 805

Published: June 20, 2023

Electroencephalograms (EEGs) are a fundamental evaluation in neurology but require special expertise unavailable many regions of the world. Artificial intelligence (AI) has potential for addressing these unmet needs. Previous AI models address only limited aspects EEG interpretation such as distinguishing abnormal from normal or identifying epileptiform activity. A comprehensive, fully automated routine based on suitable clinical practice is needed.

Language: Английский

Citations

100
Biomaterials as Implants in the Orthopedic Field for Regenerative Medicine: Metal versus Synthetic Polymers DOI Open Access

Faisal Dakhelallah Al-Shalawi,

Azmah Hanim Mohamed Ariff, Dong Won Jung

et al.

Polymers, Journal Year: 2023, Volume and Issue: 15(12), P. 2601 - 2601

Published: June 7, 2023

Patients suffering bone fractures in different parts of the body require implants that will enable similar function to natural they are replacing. Joint diseases (rheumatoid arthritis and osteoarthritis) also surgical intervention with such as hip knee joint replacement. Biomaterial utilized fix or replace body. For majority these implant cases, either metal polymer biomaterials chosen order have a functional capacity original material. The employed most often for fracture metals stainless steel titanium, polymers polyethene polyetheretherketone (PEEK). This review compared metallic synthetic can be secure load-bearing due their ability withstand mechanical stresses strains body, focus on classification, properties, application.

Language: Английский

Citations

98