Explore the vast range of titles available.

[...]even in cases of overwhelming public good such as in vaccination programs, lack of full disclosure and inadequate attention to patient education and autonomy can have dramatic negative consequences for the diffusion of helpful technologies.10 The relevance here is that the Frame Problem and related issues will inevitably cause medical errors that will draw the attention of both the public and, at least in the USA, lawsuits against parties using, deploying or developing medical AI applications. [...]optimised machine learning models in healthcare can be confounded by their training data where the reimbursement strategies driving diagnostic coding are implicit and may not reflect a more objective clinical assessment. Ongoing data-driven controversies regarding the causes of poor health outcomes among disadvantaged populations (ie, differential access vs differential biological health risks)13 illustrate just how difficult it is to avoid confounding in the analysis of observational health data. A recent study showed that over-reliance on decision support systems resulted in increased false negative rate in radiology diagnoses, compared with the study scenario where the computer-aided diagnostic system was unavailable to the same group of radiologists.14 Additionally, excessive warning information will result in alert fatigue,15 and inexperienced practitioners may over-react to the warning messages.

Artificial intelligence (AI) is gradually changing medical practice. With recent progress in digitized data acquisition, machine learning and computing infrastructure, AI applications are expanding into areas that were previously thought to be only the province of human experts. In this Review Article, we outline recent breakthroughs in AI technologies and their biomedical applications, identify the challenges for further progress in medical AI systems, and summarize the economic, legal and social implications of AI in healthcare. This Review summarizes the medical applications of artificial intelligence, and its economic, legal and social implications for healthcare.

Key PointsMedical Artificial Intelligence and Human ValuesAs large language models and other artificial intelligence models are used more in medicine, ethical dilemmas can arise depending on how the model was trained. A user must understand how human decisions and values can shape model outputs. Medical decision analysis offers lessons on measuring human values.A large language model will respond differently depending on the exact way a query is worded and how the model was directed by its makers and users. Caution is advised when considering the use of model output in decision making.

Lung cancer is the most prevalent cancer worldwide, and histopathological assessment is indispensable for its diagnosis. However, human evaluation of pathology slides cannot accurately predict patients’ prognoses. In this study, we obtain 2,186 haematoxylin and eosin stained histopathology whole-slide images of lung adenocarcinoma and squamous cell carcinoma patients from The Cancer Genome Atlas (TCGA), and 294 additional images from Stanford Tissue Microarray (TMA) Database. We extract 9,879 quantitative image features and use regularized machine-learning methods to select the top features and to distinguish shorter-term survivors from longer-term survivors with stage I adenocarcinoma ( P <0.003) or squamous cell carcinoma ( P =0.023) in the TCGA data set. We validate the survival prediction framework with the TMA cohort ( P <0.036 for both tumour types). Our results suggest that automatically derived image features can predict the prognosis of lung cancer patients and thereby contribute to precision oncology. Our methods are extensible to histopathology images of other organs. Diagnosis of lung cancer through manual histopathology evaluation is insufficient to predict patient survival. Here, the authors use computerized image processing to identify diagnostically relevant image features and use these features to distinguish lung cancer patients with different prognoses.

One of the primary tools that researchers use to predict risk is the case-control study. We identify a flaw, temporal bias, that is specific to and uniquely associated with these studies that occurs when the study period is not representative of the data that clinicians have during the diagnostic process. Temporal bias acts to undermine the validity of predictions by over-emphasizing features close to the outcome of interest. We examine the impact of temporal bias across the medical literature, and highlight examples of exaggerated effect sizes, false-negative predictions, and replication failure. Given the ubiquity and practical advantages of case-control studies, we discuss strategies for estimating the influence of and preventing temporal bias where it exists. One of the primary tools that researchers use to predict risk is the case-control study. Here, the authors identify a flaw, temporal bias, that is specific to and uniquely associated with these studies that occurs when the study period is not representative of the data that clinicians have during the diagnostic process, undermining the validity of predictions.

Understanding co-occurrence patterns and prognostic implications of immune-related adverse events is crucial for immunotherapy management. However, previous studies have been limited by sample size and generalisability. In this study, we leveraged a multi-institutional cohort and a population-level database to investigate co-occurrence patterns of and survival outcomes after multi-organ immune-related adverse events among recipients of immune checkpoint inhibitors. In this retrospective study, we identified individuals who received immune checkpoint inhibitors between May 31, 2015, and June 29, 2022, from the Massachusetts General Hospital, Brigham and Women's Hospital, and Dana-Farber Cancer Institute (Boston, MA, USA; MGBD cohort), and between April 30, 2010, and Oct 11, 2021, from the independent US population-based TriNetX network. We identified recipients from all datasets using medication codes and names of seven common immune checkpoint inhibitors, and patients were excluded from our analysis if they had incomplete information (eg, diagnosis and medication records) or if they initiated immune checkpoint inhibitor therapy after Oct 11, 2021. Eligible patients from the MGBD cohort were then propensity score matched with recipients of immune checkpoint inhibitors from the TriNetX database (1:2) based on demographic, cancer, and immune checkpoint inhibitor characteristics to facilitate cohort comparability. We applied immune-related adverse event identification rules to identify patients who did and did not have immune-related adverse events in the matched cohorts. To reduce the likelihood of false positives, patients diagnosed with suspected immune-related adverse events within 3 months after chemotherapy were excluded. We performed pairwise correlation analyses, non-negative matrix factorisation, and hierarchical clustering to identify co-occurrence patterns in the MGBD cohort. We conducted landmark overall survival analyses for patient clusters based on predominant immune-related adverse event factors and calculated accompanying hazard ratios (HRs) and 95% CIs, focusing on the 6-month landmark time for primary analyses. We validated our findings using the TriNetX cohort. We identified 15 246 recipients of immune checkpoint inhibitors from MGBD and 50 503 from TriNetX, of whom 13 086 from MGBD and 26 172 from TriNetX were included in our propensity score-matched cohort. Median follow-up durations were 317 days (IQR 113–712) in patients from MGBD and 249 days (91–616) in patients from TriNetX. After applying immune-related adverse event identification rules, 8704 recipients of immune checkpoint inhibitors were retained from MGBD, of whom 3284 (37·7%) had and 5420 (62·3%) did not have immune-related adverse events, and 18 162 recipients were retained from TriNetX, of whom 5538 (30·5%) had and 12 624 (69·5%) did not have immune-related adverse events. In both cohorts, positive pairwise correlations of immune-related adverse events were commonly observed. Co-occurring immune-related adverse events were decomposed into seven factors across organs, revealing seven distinct patient clusters (endocrine, cutaneous, respiratory, gastrointestinal, hepatic, musculoskeletal, and neurological). In the MGBD cohort, the patient clusters that predominantly had endocrine (HR 0·53 [95% CI 0·40–0·70], p<0·0001) and cutaneous (0·61 [0·46–0·81], p=0·0007) immune-related adverse events had favourable overall survival outcomes at the 6-month landmark timepoint, while the other clusters either had unfavourable (respiratory: 1·60 [1·25–2·03], p=0·0001) or neutral survival outcomes (gastrointestinal: 0·86 [0·67–1·10], p=0·23; musculoskeletal: 0·97 [0·78–1·21], p=0·78; hepatic: 1·20 [0·91–1·59], p=0·19; and neurological: 1·30 [0·97–1·74], p=0·074). Similar results were found in the TriNetX cohort (endocrine: HR 0·75 [95% CI 0·60–0·93], p=0·0078; cutaneous: 0·62 [0·48–0·82], p=0·0007; respiratory: 1·21 [1·00–1·46], p=0·044), except for the neurological cluster having unfavourable (rather than neutral) survival outcomes (1·30 [1·06–1·59], p=0·013). Reliably identifying the immune-related adverse event cluster to which a patient belongs can provide valuable clinical information for prognosticating outcomes of immunotherapy. These insights can be leveraged to counsel patients on the clinical impact of their individual constellation of immune-related adverse events and ultimately develop more personalised surveillance and mitigation strategies. US National Institutes of Health.

Histopathologic assessment is indispensable for diagnosing colorectal cancer (CRC). However, manual evaluation of the diseased tissues under the microscope cannot reliably inform patient prognosis or genomic variations crucial for treatment selections. To address these challenges, we develop the Multi-omics Multi-cohort Assessment (MOMA) platform, an explainable machine learning approach, to systematically identify and interpret the relationship between patients’ histologic patterns, multi-omics, and clinical profiles in three large patient cohorts ( n  = 1888). MOMA successfully predicts the overall survival, disease-free survival (log-rank test P -value<0.05), and copy number alterations of CRC patients. In addition, our approaches identify interpretable pathology patterns predictive of gene expression profiles, microsatellite instability status, and clinically actionable genetic alterations. We show that MOMA models are generalizable to multiple patient populations with different demographic compositions and pathology images collected from distinctive digitization methods. Our machine learning approaches provide clinically actionable predictions that could inform treatments for colorectal cancer patients. Histopathological analysis is an essential tool in diagnosing colorectal cancer, but is limited in predicting prognosis and molecular profiles. Here, the authors designed a machine learning-based platform to predict multi-omics profiles and prognosis from pathology images.

A subset of primary central nervous system lymphomas (PCNSL) are difficult to distinguish from glioblastoma multiforme (GBM) on magnetic resonance imaging (MRI). We developed a convolutional neural network (CNN) to distinguish these tumors on contrast-enhanced T 1 -weighted images. Preoperative brain tumor MRIs were retrospectively collected among 320 patients with either GBM (n = 160) and PCNSL (n = 160) from two academic institutions. The individual images from these MRIs consisted of a training set (n = 1894 GBM and 1245 PCNSL), a validation set (n = 339 GBM; 202 PCNSL), and a testing set (99 GBM and 108 PCNSL). Three CNNs using the EfficientNetB4 architecture were evaluated. To increase the size of the training set and minimize overfitting, random flips and changes to color were performed on the training set. Our transfer learning approach (with image augmentation and 292 epochs) yielded an AUC of 0.94 (95% CI: 0.91–0.97) for GBM and an AUC of 0.95 (95% CI: 0.92–0.98) for PCNL. In the second case (not augmented and 137 epochs), the images were augmented prior to training. The area under the curve for GBM was 0.92 (95% CI: 0.88–0.96) for GBM and an AUC of 0.94 (95% CI: 0.91–0.97) for PCNSL. For the last case (augmented, Gaussian noise and 238 epochs) the AUC for GBM was 0.93 (95% CI: 0.89–0.96) and an AUC 0.93 (95% CI = 0.89–0.96) for PCNSL. Even with a relatively small dataset, our transfer learning approach demonstrated CNNs may provide accurate diagnostic information to assist radiologists in distinguishing PCNSL and GBM.

Correspondence to Mr Oren Miron, Ben-Gurion University of the Negev, Beer Sheva, Israel; orenmir@post.bgu.ac.il The USA closed most of its schools in March–April 2020, which was associated with reduced COVID-19 incidence.1 In August–September 2020, schools reopened, with many schools teaching remotely until they can safely teach physically.2 We analysed COVID-19 incidence from Florida since its database provides incidence at ages 6–13 years (elementary school) and 14–17 years (high school). [...]we tested if trends were different between counties teaching physically and remotely. Counties with remote reopening did not have increased incidence, which may also relate to their lower COVID-19 rates before the reopening, their public mask mandate and gathering limit or their socioeconomic difference, such as in Miami-Dade and Broward.3 A limitation of the study is that some parents opted not to send their children to physical learning.

Chest computed tomography (CT) is crucial for the detection of lung cancer, and many automated CT evaluation methods have been proposed. Due to the divergent software dependencies of the reported approaches, the developed methods are rarely compared or reproduced. The goal of the research was to generate reproducible machine learning modules for lung cancer detection and compare the approaches and performances of the award-winning algorithms developed in the Kaggle Data Science Bowl. We obtained the source codes of all award-winning solutions of the Kaggle Data Science Bowl Challenge, where participants developed automated CT evaluation methods to detect lung cancer (training set n=1397, public test set n=198, final test set n=506). The performance of the algorithms was evaluated by the log-loss function, and the Spearman correlation coefficient of the performance in the public and final test sets was computed. Most solutions implemented distinct image preprocessing, segmentation, and classification modules. Variants of U-Net, VGGNet, and residual net were commonly used in nodule segmentation, and transfer learning was used in most of the classification algorithms. Substantial performance variations in the public and final test sets were observed (Spearman correlation coefficient = .39 among the top 10 teams). To ensure the reproducibility of results, we generated a Docker container for each of the top solutions. We compared the award-winning algorithms for lung cancer detection and generated reproducible Docker images for the top solutions. Although convolutional neural networks achieved decent accuracy, there is plenty of room for improvement regarding model generalizability.