☆ 4.7 Article

Implications of the Use of Artificial Intelligence Predictive Models in Health Care Settings A Simulation Study

ANNALS OF INTERNAL MEDICINE (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Medicine, General & Internal

There is no such thing as a validated prediction model

Ben Van Calster et al.

Summary: Clinical prediction models should be validated before implementation, as the performance of a model may vary across patient populations and measurement procedures. Validation studies should focus on understanding and quantifying heterogeneity and monitoring performance over time, to ensure that prediction models remain up-to-date and safe for clinical decision-making.

BMC MEDICINE (2023)

添加到收藏夹

Article Computer Science, Information Systems

Assessing the net benefit of machine learning models in the presence of resource constraints

Karandeep Singh et al.

Summary: The objective of this study is to provide a method to calculate model performance measures in the presence of resource constraints, with a focus on net benefit (NB). The Equator Network's TRIPOD guidelines recommend the calculation of the NB to quantify a model's clinical utility. This study demonstrates how resource constraints affect the realized net benefit (RNB) of a hypothetical ICU admission model and proposes solutions to overcome absolute constraints when possible.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2023)

添加到收藏夹

Review Biochemistry & Molecular Biology

AI in health and medicine

Pranav Rajpurkar et al.

Summary: This Review discusses the potential of AI to reshape medicine and make healthcare more accurate, efficient, and accessible. It covers recent progress in medical AI, including advances in medical image analysis, non-image data sources, and human-AI collaboration. The article also addresses technical and ethical challenges, such as data scarcity and racial bias.

NATURE MEDICINE (2022)

添加到收藏夹

Article Cardiac & Cardiovascular Systems

Using Deep-Learning Algorithms to Simultaneously Identify Right and Left Ventricular Dysfunction From the Electrocardiogram

Akhil Vaid et al.

Summary: This study developed deep learning models to comprehensively quantify left and right ventricular dysfunction from ECG data. The models can assist in the rapid evaluation of ventricular function, aid in diagnosis, and predict the risk of heart disease.

JACC-CARDIOVASCULAR IMAGING (2022)

添加到收藏夹

Article Health Care Sciences & Services

Performance of a Commonly Used Pressure Injury Risk Model Under Changing Incidence

Scott Lanyon Fleming et al.

Summary: This study evaluated the association between Braden QD scores and the incidence of Hospital-acquired pressure injuries (HAPIs). The results showed that higher Braden QD scores were associated with increased odds of developing HAPIs. The implementation of a HAPI-reduction initiative resulted in a decrease in HAPI incidence, but also led to a deterioration in threshold-dependent performance measures and improvements in threshold-independent performance measures.

JOINT COMMISSION JOURNAL ON QUALITY AND PATIENT SAFETY (2022)

添加到收藏夹

Review Health Care Sciences & Services

Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare

Jean Feng et al.

Summary: Machine learning and artificial intelligence algorithms can extract insights from clinical data and improve patient outcomes, but these complex systems are sensitive to environmental changes and prone to performance decay. Even after successful integration into clinical practice, continuous monitoring and updating are necessary to ensure long-term safety and effectiveness.

NPJ DIGITAL MEDICINE (2022)

添加到收藏夹

Article Biochemistry & Molecular Biology

Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis

Roy Adams et al.

Summary: This study examined the association between a deployed early warning system called TREWS and patient outcomes, and found that interaction of health-care providers with the system was associated with better patient outcomes, including reduced in-hospital mortality.

NATURE MEDICINE (2022)

添加到收藏夹

Article Biochemistry & Molecular Biology

Factors driving provider adoption of the TREWS machine learning-based early warning system and its effects on sepsis treatment timing

Katharine E. Henry et al.

Summary: A prospective evaluation of a machine learning-based early warning system for sepsis showed that healthcare providers interacted with the system at a high rate, resulting in faster antibiotic ordering. The early detection tool achieved high sensitivity and adoption rates, with confirmed alerts leading to a reduction in median time to antibiotic order. Emergency department providers and those with previous interactions with the alert were more likely to interact and confirm alerts.

NATURE MEDICINE (2022)

添加到收藏夹

Letter Medicine, General & Internal

Quantification of Sepsis Model Alerts in 24 US Hospitals Before and During the COVID-19 Pandemic

Andrew Wong et al.

JAMA NETWORK OPEN (2021)

添加到收藏夹

Review Cardiac & Cardiovascular Systems

External Validations of Cardiovascular Clinical Prediction Models: A Large-Scale Review of the Literature

Benjamin S. Wessler et al.

Summary: The study found that many cardiovascular clinical prediction models have not been externally validated, and those that have often show overly optimistic performance during development. A single external validation appears insufficient to broadly understand the performance heterogeneity across different settings.

CIRCULATION-CARDIOVASCULAR QUALITY AND OUTCOMES (2021)

添加到收藏夹

Letter Medicine, General & Internal

The Clinician and Dataset Shift in Artificial Intelligence

Samuel G. Finlayson et al.

NEW ENGLAND JOURNAL OF MEDICINE (2021)

添加到收藏夹

Article Medicine, General & Internal

External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients

Andrew Wong et al.

Summary: The study evaluated the Epic Sepsis Model (ESM) in predicting sepsis and found that it had poor discrimination and calibration. The widespread use of ESM despite its poor performance raises concerns about sepsis management nationally.

JAMA INTERNAL MEDICINE (2021)

添加到收藏夹

Review Multidisciplinary Sciences

Array programming with NumPy

Charles R. Harris et al.

NATURE (2020)

添加到收藏夹

Article Medicine, General & Internal

Automated Identification of Adults at Risk for In-Hospital Clinical Deterioration

Gabriel J. Escobar et al.

NEW ENGLAND JOURNAL OF MEDICINE (2020)

添加到收藏夹

Review Psychology, Clinical

Machine learning in mental health: a scoping review of methods and applications

Adrian B. R. Shatte et al.

PSYCHOLOGICAL MEDICINE (2019)

添加到收藏夹

Review Health Care Sciences & Services

A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models

Evangelia Christodoulou et al.

JOURNAL OF CLINICAL EPIDEMIOLOGY (2019)

添加到收藏夹

Article Computer Science, Information Systems

Prognostic models will be victims of their own success, unless...

Matthew C. Lenert et al.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2019)

添加到收藏夹

Article Health Policy & Services

A framework for value-creating learning health systems

Matthew Menear et al.

HEALTH RESEARCH POLICY AND SYSTEMS (2019)

添加到收藏夹

Review Radiology, Nuclear Medicine & Medical Imaging

Current Applications and Future Impact of Machine Learning in Radiology

Garry Choy et al.

RADIOLOGY (2018)

添加到收藏夹

Letter Health Care Sciences & Services

Reporting accuracy of rare event classifiers

Edieal Pinker

NPJ DIGITAL MEDICINE (2018)

添加到收藏夹

Article Computer Science, Information Systems

Calibration drift in regression and machine learning models for acute kidney injury

Sharon E. Davis et al.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2017)

添加到收藏夹

Article Health Care Sciences & Services

Calibration of Risk Prediction Models: Impact on Decision-Analytic Performance

Ben Van Calster et al.

MEDICAL DECISION MAKING (2015)

添加到收藏夹

Article Multidisciplinary Sciences

The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets

Takaya Saito et al.

PLOS ONE (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A unifying view on dataset shift in classification

Jose G. Moreno-Torres et al.

PATTERN RECOGNITION (2012)

添加到收藏夹

Editorial Material Urology & Nephrology

Why Can't Nomograms Be More Like Netflix?

Andrew J. Vickers et al.

UROLOGY (2010)

添加到收藏夹

Article Health Care Sciences & Services

Decision curve analysis: A novel method for evaluating prediction models

Andrew J. Vickers et al.

MEDICAL DECISION MAKING (2006)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.