Erroneous data: The Achilles' heel of AI and personalized medicine

LASIK Versus PRK Based on Increased Risk of Corneal Haze: Assessing Current Decision-Making Capabilities of Six Artificial Intelligence Models in Refractive Surgery

PURPOSE

To investigate the current decision-making capabilities of 6 different artificial intelligence (AI) models by assessing their refractive surgery recommendations (laser in-situ keratomileusis [LASIK] or photorefractive keratectomy [PRK]) for a theoretical patient with a history of keloid formation.

METHODS

Claude-2 (Anthropic, 2023), GPT-4 (OpenAI, 2023), GPT-3.5 (OpenAI, 2022), Gemini 1.0 (Google DeepMind, 2023), Microsoft Copilot (Microsoft AI, 2023), and Google-PaLM (Google AI, 2022) underwent three systematic queries to determine the most appropriate surgical plan (LASIK or PRK) for a theoretical patient with an increasing manifest refraction of -3.50, -5.00, and -7.00 diopters (D) in both eyes, an uncomplicated ocular examination, and history of keloid formation. They were then tasked with providing published scientific references to support their responses. The AI models' recommendations were compared to those of a group of 6 experienced ophthalmologists, serving as a benchmark.

RESULTS

The group of ophthalmologists unanimously recommended LASIK (6/6 ophthalmologists), in contrast to the unanimous initial recommendation for PRK from the AI models (6/6 models). Of the 42 references provided by the AI models, 55% were fictitious and 45% were authentic. Only 1 of the 6 models altered its initial recommendation to LASIK when presented with the same patient with a history of keloid formation but with increasing severity of myopia (-3.50 to 5.00 to 7.00 D).

DISCUSSION

It is evident that current AI models lack the critical-thinking abilities required to accurately analyze and assess apparent risk factors in clinical scenarios, such as the risk of corneal haze after PRK at higher levels of myopia, particularly in cases with a history of keloid formation. [J Refract Surg. 2024;40(8):e533-e538.].

Diagnostic Modalities in Heart Failure: A Narrative Review

Heart failure (HF) can present acutely or progress over time. It can lead to morbidity and mortality affecting 6.5 million Americans over the age of 20. The HF type is described according to the ejection fraction classification, defined as the percentage of blood volume that exits the left ventricle after myocardial contraction, undergoing ejection into the circulation, also called stroke volume, and is proportional to the ejection fraction. Cardiac catheterization is an invasive procedure to evaluate coronary artery disease leading to HF. Several biomarkers are being studied that could lead to early detection of HF and better symptom management. Testing for various biomarkers in the patient's blood is instrumental in confirming the diagnosis and elucidating the etiology of HF. There are various biomarkers elevated in response to increased myocardial stress and volume overload, including B-type natriuretic peptide (BNP) and its N-terminal prohormone BNP. We explored online libraries such as PubMed, Google Scholar, and Cochrane to find relevant articles. Our narrative review aims to extensively shed light on diagnostic modalities and novel techniques for diagnosing HF.

An ethical assessment of professional opinions on concerns, chances, and limitations of the implementation of an artificial intelligence-based technology into the geriatric patient treatment and continuity of care

With the introduction of an artificial intelligence-based dashboard into the clinic, the project SURGE-Ahead responds to the importance of improving perioperative geriatric patient treatment and continuity of care. The use of artificial intelligence to process and analyze data automatically, aims at an evidence-based evaluation of the patient's health condition and recommending treatment options. However, its development and introduction raise ethical questions. To ascertain professional perspectives on the clinical use of the dashboard, we have conducted 19 semi-structured qualitative interviews with head physicians, computer scientists, jurists, and ethicists. The application of a qualitative content analysis and thematic analysis enabled the detection of main ethical concerns, chances, and limitations. These ethical considerations were categorized: changes of the patient-physician relationship and the current social reality are expected, causing de-skilling and an active participation of the artificial intelligence. The interviewees anticipated a redistribution of human resources, time, knowledge, and experiences as well as expenses and financing. Concerns of privacy, accuracy, transparency, and explainability were stated, and an insufficient data basis, an intensifying of existing inequalities and systematic discrimination considering a fair access emphasized. Concluding, the patient-physician relationship, social reality, redistribution of resources, fair access, as well as data-related aspects of the artificial intelligence-based system could conflict with the ethical principles of autonomy, non-maleficence, beneficence, and social justice. To respond to these ethical concerns, a responsible use of the dashboard and a critical verification of therapy suggestions is mandatory, and the application limited by questions at the end of life and taking life-changing decisions.

Use of artificial intelligence in obstetric and gynaecological diagnostics: a protocol for a systematic review and meta-analysis

INTRODUCTION

Emerging developments in applications of artificial intelligence (AI) in healthcare offer the opportunity to improve diagnostic capabilities in obstetrics and gynaecology (O&G), ensuring early detection of pathology, optimal management and improving survival. Consensus on a robust AI healthcare framework is crucial for standardising protocols that promote data privacy and transparency, minimise bias, and ensure patient safety. Here, we describe the study protocol for a systematic review and meta-analysis to evaluate current applications of AI in O&G diagnostics with consideration of reporting standards used and their ethical implications. This protocol is written following the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P) 2015 checklist.

METHODS AND ANALYSIS

The study objective is to explore the current application of AI in O&G diagnostics and assess the reporting standards used in these studies. Electronic bibliographic databases MEDLINE, EMBASE and Cochrane will be searched. Study selection, data extraction and subsequent narrative synthesis and meta-analyses will be carried out following the PRISMA-P guidelines. Included papers will be English-language full-text articles from May 2015 to March 2024, which provide original data, as AI has been redefined in recent literature. Papers must use AI as the predictive method, focusing on improving O&G diagnostic outcomes.We will evaluate the reporting standards including the risk of bias, lack of transparency and consider the ethical implications and potential harm to patients. Outcome measures will involve assessing the included studies against gold-standard criteria for robustness of model development (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis, model predictive performance, model risk of bias and applicability (Prediction model Risk Of Bias Assessment Tool and study reporting (Consolidated Standards of Reporting Trials-AI) guidance.

ETHICS AND DISSEMINATION

Ethical approval is not required for this systematic review. Findings will be shared through peer-reviewed publications. There will be no patient or public involvement in this study.

PROSPERO REGISTRATION NUMBER

CRD42022357024 .

Development and validation of prognostic machine learning models for short- and long-term mortality among acutely admitted patients based on blood tests

Several scores predicting mortality at the emergency department have been developed. However, all with shortcomings either simple and applicable in a clinical setting, with poor performance, or advanced, with high performance, but clinically difficult to implement. This study aimed to explore if machine learning algorithms could predict all-cause short- and long-term mortality based on the routine blood test collected at admission.

METHODS

We analyzed data from a retrospective cohort study, including patients > 18 years admitted to the Emergency Department (ED) of Copenhagen University Hospital Hvidovre, Denmark between November 2013 and March 2017. The primary outcomes were 3-, 10-, 30-, and 365-day mortality after admission. PyCaret, an automated machine learning library, was used to evaluate the predictive performance of fifteen machine learning algorithms using the area under the receiver operating characteristic curve (AUC).

RESULTS

Data from 48,841 admissions were analyzed, of these 34,190 (70%) were randomly divided into training data, and 14,651 (30%) were in test data. Eight machine learning algorithms achieved very good to excellent results of AUC on test data in a of range 0.85-0.93. In prediction of short-term mortality, lactate dehydrogenase (LDH), leukocyte counts and differentials, Blood urea nitrogen (BUN) and mean corpuscular hemoglobin concentration (MCHC) were the best predictors, whereas prediction of long-term mortality was favored by age, LDH, soluble urokinase plasminogen activator receptor (suPAR), albumin, and blood urea nitrogen (BUN).

CONCLUSION

The findings suggest that measures of biomarkers taken from one blood sample during admission to the ED can identify patients at high risk of short-and long-term mortality following emergency admissions.

Remote Monitoring and Artificial Intelligence: Outlook for 2050

Remote monitoring and artificial intelligence will become common and intertwined in anesthesiology by 2050. In the intraoperative period, technology will lead to the development of integrated monitoring systems that will integrate multiple data streams and allow anesthesiologists to track patients more effectively. This will free up anesthesiologists to focus on more complex tasks, such as managing risk and making value-based decisions. This will also enable the continued integration of remote monitoring and control towers having profound effects on coverage and practice models. In the PACU and ICU, the technology will lead to the development of early warning systems that can identify patients who are at risk of complications, enabling early interventions and more proactive care. The integration of augmented reality will allow for better integration of diverse types of data and better decision-making. Postoperatively, the proliferation of wearable devices that can monitor patient vital signs and track their progress will allow patients to be discharged from the hospital sooner and receive care at home. This will require increased use of telemedicine, which will allow patients to consult with doctors remotely. All of these advances will require changes to legal and regulatory frameworks that will enable new workflows that are different from those familiar to today's providers.

Artificial Intelligence in Heart Failure: Friend or Foe?

In recent times, there have been notable changes in cardiovascular medicine, propelled by the swift advancements in artificial intelligence (AI). The present work provides an overview of the current applications and challenges of AI in the field of heart failure. It emphasizes the "garbage in, garbage out" issue, where AI systems can produce inaccurate results with skewed data. The discussion covers issues in heart failure diagnostic algorithms, particularly discrepancies between existing models. Concerns about the reliance on the left ventricular ejection fraction (LVEF) for classification and treatment are highlighted, showcasing differences in current scientific perceptions. This review also delves into challenges in implementing AI, including variable considerations and biases in training data. It underscores the limitations of current AI models in real-world scenarios and the difficulty in interpreting their predictions, contributing to limited physician trust in AI-based models. The overarching suggestion is that AI can be a valuable tool in clinicians' hands for treating heart failure patients, as far as existing medical inaccuracies have been addressed before integrating AI into these frameworks.

The Reporting Quality of Machine Learning Studies on Pediatric Diabetes Mellitus: Systematic Review

BACKGROUND

Diabetes mellitus (DM) is a major health concern among children with the widespread adoption of advanced technologies. However, concerns are growing about the transparency, replicability, biasedness, and overall validity of artificial intelligence studies in medicine.

OBJECTIVE

We aimed to systematically review the reporting quality of machine learning (ML) studies of pediatric DM using the Minimum Information About Clinical Artificial Intelligence Modelling (MI-CLAIM) checklist, a general reporting guideline for medical artificial intelligence studies.

METHODS

We searched the PubMed and Web of Science databases from 2016 to 2020. Studies were included if the use of ML was reported in children with DM aged 2 to 18 years, including studies on complications, screening studies, and in silico samples. In studies following the ML workflow of training, validation, and testing of results, reporting quality was assessed via MI-CLAIM by consensus judgments of independent reviewer pairs. Positive answers to the 17 binary items regarding sufficient reporting were qualitatively summarized and counted as a proxy measure of reporting quality. The synthesis of results included testing the association of reporting quality with publication and data type, participants (human or in silico), research goals, level of code sharing, and the scientific field of publication (medical or engineering), as well as with expert judgments of clinical impact and reproducibility.

RESULTS

After screening 1043 records, 28 studies were included. The sample size of the training cohort ranged from 5 to 561. Six studies featured only in silico patients. The reporting quality was low, with great variation among the 21 studies assessed using MI-CLAIM. The number of items with sufficient reporting ranged from 4 to 12 (mean 7.43, SD 2.62). The items on research questions and data characterization were reported adequately most often, whereas items on patient characteristics and model examination were reported adequately least often. The representativeness of the training and test cohorts to real-world settings and the adequacy of model performance evaluation were the most difficult to judge. Reporting quality improved over time (r=0.50; P=.02); it was higher than average in prognostic biomarker and risk factor studies (P=.04) and lower in noninvasive hypoglycemia detection studies (P=.006), higher in studies published in medical versus engineering journals (P=.004), and higher in studies sharing any code of the ML pipeline versus not sharing (P=.003). The association between expert judgments and MI-CLAIM ratings was not significant.

CONCLUSIONS

The reporting quality of ML studies in the pediatric population with DM was generally low. Important details for clinicians, such as patient characteristics; comparison with the state-of-the-art solution; and model examination for valid, unbiased, and robust results, were often the weak points of reporting. To assess their clinical utility, the reporting standards of ML studies must evolve, and algorithms for this challenging population must become more transparent and replicable.

Transforming neonatal care with artificial intelligence: challenges, ethical consideration, and opportunities

Artificial intelligence (AI) offers tremendous potential to transform neonatology through improved diagnostics, personalized treatments, and earlier prevention of complications. However, there are many challenges to address before AI is ready for clinical practice. This review defines key AI concepts and discusses ethical considerations and implicit biases associated with AI. Next we will review literature examples of AI already being explored in neonatology research and we will suggest future potentials for AI work. Examples discussed in this article include predicting outcomes such as sepsis, optimizing oxygen therapy, and image analysis to detect brain injury and retinopathy of prematurity. Realizing AI's potential necessitates collaboration between diverse stakeholders across the entire process of incorporating AI tools in the NICU to address testability, usability, bias, and transparency. With multi-center and multi-disciplinary collaboration, AI holds tremendous potential to transform the future of neonatology.

The robot butler: How and why should we study predictive algorithms and artificial intelligence (AI) in healthcare?

Artificial intelligence (AI) and algorithms are heralded as significant solutions to the widening gap between the rising healthcare needs of ageing and multi-morbid populations and the scarcity of resources to provide such care.

Objective

This article investigates how the PMHnet algorithm - an AI prognostication tool developed in Denmark to predict the one-year all-cause mortality risk for patients hospitalized with ischemic heart disease - was presented to cardiologists working in the hospital setting, and how they responded to this novel decision-support tool.

Methods

Empirically, we draw upon ethnographic fieldwork in the Danish-led international research project, PM Heart, which since 2019 has developed the PMHnet algorithm and implemented the software into the electronic health record system in hospitals in Eastern Denmark (the Capital Region and Region Zealand).

Results

Paying careful attention to the hopes and concerns of cardiologists who will have to embrace and adapt to algorithmic tools in their everyday work of diagnosing and treating patients, we identify three analytical themes meriting attention when AI is implemented in healthcare: 1) the re-negotiation of agency and autonomy in human-algorithm relations, 2) accountability in algorithmic prognostication and 3) the complex relationship between association and causation actualized by predictive algorithms. From these analytical themes, we elicit methodological questions to guide future ethnographic explorations of how AI and advanced algorithms are put to use in the healthcare system, with what implications, and for whom.

Conclusion

We conclude that local, qualitative investigations of how algorithms are used, embraced and contested in everyday clinical practice are needed in order to understand their implications - good and bad, intended and unintended - for clinicians, patients and healthcare provision.

Evaluating the Efficacy of ChatGPT in Navigating the Spanish Medical Residency Entrance Examination (MIR): Promising Horizons for AI in Clinical Medicine

The rapid progress in artificial intelligence, machine learning, and natural language processing has led to increasingly sophisticated large language models (LLMs) for use in healthcare. This study assesses the performance of two LLMs, the GPT-3.5 and GPT-4 models, in passing the MIR medical examination for access to medical specialist training in Spain. Our objectives included gauging the model's overall performance, analyzing discrepancies across different medical specialties, discerning between theoretical and practical questions, estimating error proportions, and assessing the hypothetical severity of errors committed by a physician.

MATERIAL AND METHODS

We studied the 2022 Spanish MIR examination results after excluding those questions requiring image evaluations or having acknowledged errors. The remaining 182 questions were presented to the LLM GPT-4 and GPT-3.5 in Spanish and English. Logistic regression models analyzed the relationships between question length, sequence, and performance. We also analyzed the 23 questions with images, using GPT-4's new image analysis capability.

RESULTS

GPT-4 outperformed GPT-3.5, scoring 86.81% in Spanish (p < 0.001). English translations had a slightly enhanced performance. GPT-4 scored 26.1% of the questions with images in English. The results were worse when the questions were in Spanish, 13.0%, although the differences were not statistically significant (p = 0.250). Among medical specialties, GPT-4 achieved a 100% correct response rate in several areas, and the Pharmacology, Critical Care, and Infectious Diseases specialties showed lower performance. The error analysis revealed that while a 13.2% error rate existed, the gravest categories, such as "error requiring intervention to sustain life" and "error resulting in death", had a 0% rate.

CONCLUSIONS

GPT-4 performs robustly on the Spanish MIR examination, with varying capabilities to discriminate knowledge across specialties. While the model's high success rate is commendable, understanding the error severity is critical, especially when considering AI's potential role in real-world medical practice and its implications for patient safety.

Medical imaging and multimodal artificial intelligence models for streamlining and enhancing cancer care: opportunities and challenges

INTRODUCTION

Artificial intelligence (AI) has the potential to transform oncologic care. There have been significant developments in AI applications in medical imaging and increasing interest in multimodal models. These are likely to enable improved oncologic care through more precise diagnosis, increasingly in a more personalized and less invasive manner. In this review, we provide an overview of the current state and challenges that clinicians, administrative personnel and policy makers need to be aware of and mitigate for the technology to reach its full potential.

AREAS COVERED

The article provides a brief targeted overview of AI, a high-level review of the current state and future potential AI applications in diagnostic radiology and to a lesser extent digital pathology, focusing on oncologic applications. This is followed by a discussion of emerging approaches, including multimodal models. The article concludes with a discussion of technical, regulatory challenges and infrastructure needs for AI to realize its full potential.

EXPERT OPINION

There is a large volume of promising research, and steadily increasing commercially available tools using AI. For the most advanced and promising precision diagnostic applications of AI to be used clinically, robust and comprehensive quality monitoring systems and informatics platforms will likely be required.