When performance is not enough-A multidisciplinary view on clinical decision support

Article Immunology

Dynamic risk prediction of BK polyomavirus reactivation after renal transplantation

Yiling Fang et al.

Summary: Dynamic Cox regression based on the landmarking method is effective in assessing the risk of BKV reactivation in the early period after renal transplantation and serves as a guide for clinical intervention.

FRONTIERS IN IMMUNOLOGY (2022)

添加到收藏夹

Article Immunology

Development and validation of multivariable prediction models of serological response to SARS-CoV-2 vaccination in kidney transplant recipients

Bilgin Osmanodja et al.

Summary: This study developed and validated prediction models for serological response to third and fourth doses of SARS-CoV-2 vaccine in kidney transplant recipients, showing good overall accuracy in guiding immunosuppressive therapy decisions.

FRONTIERS IN IMMUNOLOGY (2022)

添加到收藏夹

Review Genetics & Heredity

Donor-derived cell-free DNA as a diagnostic tool in transplantation

Michael Oellerich et al.

Summary: There is a growing need to improve personalized immunosuppression in organ transplantation, and the use of dd-cfDNA testing can provide more accurate results to monitor rejection and graft injury. It has positive implications for the patient's transplant progress and treatment plans.

FRONTIERS IN GENETICS (2022)

添加到收藏夹

Article Public, Environmental & Occupational Health

Evaluation of a clinical decision support system for detection of patients at risk after kidney transplantation

Roland Roller et al.

Summary: This study developed a clinical decision support system (CDSS) for detecting rejection and graft failure risks in kidney transplant patients. The CDSS was found to detect different at-risk patients compared to physicians, and while physicians' predictions were influenced by the CDSS, performance did not significantly improve.

FRONTIERS IN PUBLIC HEALTH (2022)

添加到收藏夹

Article Medicine, Research & Experimental

Comparison of artificial intelligence and human-based prediction and stratification of the risk of long-term kidney allograft failure

Gillian Divard et al.

Summary: This study evaluates the ability of transplant physicians to predict the risk of long-term allograft failure and compares them to a validated artificial intelligence (AI) prediction algorithm. The study finds that the overall performance of physicians in predicting individual long-term outcomes is limited compared to the AI system, and there is wide variability in physicians' predictions.

COMMUNICATIONS MEDICINE (2022)

添加到收藏夹

Article Ethics

Primer on an ethics of AI-based decision support systems in the clinic

Matthias Braun et al.

Summary: This article examines the challenges faced by clinical decision-making processes due to the emergence of artificial intelligence-driven decision support systems (AI-DSS), analyzing the impact on interactions between agents in the clinic and discussing implications for trustworthiness, transparency, normative concepts of agency, and responsibility ascriptions. Starting points for ensuring 'meaningful human control' over clinical AI-DSS are also discussed.

JOURNAL OF MEDICAL ETHICS (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies

Aniek F. Markus et al.

Summary: This paper discusses the issue of explainable AI in the healthcare domain, proposes a framework for choosing explainable AI methods, and highlights the lack of evaluation metrics in some aspects.

JOURNAL OF BIOMEDICAL INFORMATICS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Trust and medical AI: the challenges we face and the expertise needed to overcome them

Thomas P. Quinn et al.

Summary: The article highlights the potential serious consequences of failures in medical AI on clinical outcomes and patient experience, which could erode public trust in AI. To maintain trust in healthcare institutions, the proposed solution involves educating and accrediting new expert groups specializing in medical AI technologies.

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION (2021)

添加到收藏夹

Article Ethics

A Leap of Faith: Is There a Formula for Trustworthy AI?

Matthias Braun et al.

Summary: Trust is a key term in debates about the shaping of society, democracy, and emerging technologies. Trust in AI is not just an accelerator for societal acceptance of technology, but is granted through leaps of faith. Distrust plays an important role in societal deliberation, enabling individuals to forgo technology, constrain its power, and exercise meaningful human control.

HASTINGS CENTER REPORT (2021)

添加到收藏夹

Article Urology & Nephrology

Exploring the Complexity of Death-Censored Kidney Allograft Failure

Manuel Mayrdorfer et al.

Summary: The study found that kidney graft loss is often caused by multiple factors and more complex than previously thought, including intercurrent medical events, T cell-mediated rejection, and antibody-mediated rejection; the primary cause is often antibody-mediated rejection.

JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY (2021)

添加到收藏夹

Article Medicine, General & Internal

Forecasting of Patient-Specific Kidney Transplant Function With a Sequence-to-Sequence Deep Learning Model

Elisabet Van Loon et al.

Summary: A deep learning model was developed and validated to predict the patient-specific expected reference range of eGFR after kidney transplant, showing promising results in accurately forecasting individual trajectories within the first 3 months post-transplant.

JAMA NETWORK OPEN (2021)

添加到收藏夹

Article Public, Environmental & Occupational Health

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

Akshaya Karthikeyan et al.

Summary: This study introduces machine learning methods based on blood test data for predicting COVID-19 mortality risk, achieving high accuracy. By analyzing key biomarkers, it provides decision-making solutions for healthcare systems to expedite the decision-making process.

FRONTIERS IN PUBLIC HEALTH (2021)

添加到收藏夹

Article Medical Informatics

Dynamic prediction of renal survival among deeply phenotyped kidney transplant recipients using artificial intelligence: an observational, international, multicohort study

Marc Raynaud et al.

Summary: This study developed a dynamic artificial intelligence approach to enhance risk stratification for kidney transplant recipients by continuously updating predictions of survival. Using Bayesian joint models-an artificial intelligence approach, the predictive model demonstrated accurate calibration and high discrimination in both the development and external validation cohorts.

LANCET DIGITAL HEALTH (2021)

添加到收藏夹

Article Urology & Nephrology