Background: Generalizability of AI colonoscopy algorithms is important for wider adoption in clinical practice. However, current techniques for evaluating performance on unseen data require expensive and time-intensive labels. Methods: We use a "Masked Siamese Network" (MSN) to identify novel phenomena in unseen data and predict polyp detector performance. MSN is trained to predict masked out regions of polyp images, without any labels. We test MSN's ability to be trained on data only from Israel and detect unseen techniques, narrow-band imaging (NBI) and chromendoscoy (CE), on colonoscopes from Japan (354 videos, 128 hours). We also test MSN's ability to predict performance of Computer Aided Detection (CADe) of polyps on colonoscopies from both countries, even though MSN is not trained on data from Japan. Results: MSN correctly identifies NBI and CE as less similar to Israel whitelight than Japan whitelight (bootstrapped z-test, |z| > 496, p < 10^-8 for both) using the label-free Frechet distance. MSN detects NBI with 99 predicts CE better than our heuristic (90 trained only on whitelight, and is the only method that is robust to noisy labels. MSN predicts CADe polyp detector performance on in-domain Israel and out-of-domain Japan colonoscopies (r=0.79, 0.37 respectively). With few examples of Japan detector performance to train on, MSN prediction of Japan performance improves (r=0.56). Conclusion: Our technique can identify distribution shifts in clinical data and can predict CADe detector performance on unseen data, without labels. Our self-supervised approach can aid in detecting when data in practice is different from training, such as between hospitals or data has meaningfully shifted from training. MSN has potential for application to medical image domains beyond colonoscopy.

Abstract Centenarians exhibit remarkable longevity, and exploring the genetic determinants of that longevity is crucial for understanding the mechanisms of human ageing. Although APOE4 is the most common implicated negative factor in longevity, other genetic factors and their associated phenotypes are not fully understood. We conducted a genome-wide association study (GWAS) of 964 Japanese centenarians (including 173 supercentenarians) and 7,306 controls to identify the genetic components of longevity and the correlated phenotypes. GWAS summary statistics revealed that the genetic components of longevity were negatively associated with the risk of multiple age-related diseases and biometrics. Survival analysis indicated that a polygenic score derived from these summary statistics, called CentPGS, was correlated with healthspan in a cohort of healthy older people. This association was independent of APOE4 genotype and sex, suggesting that CentPGS is a promising genetic indicator of healthspan and may be used in future investigations into healthy longevity.

Abstract Generalizability of AI colonoscopy algorithms is important for wider adoption in clinical practice. However, current techniques for evaluating performance on unseen data require expensive and time-intensive labels. We show that a "Masked Siamese Network" (MSN), trained to predict masked out regions of polyp images without labels, can predict the performance of Computer Aided Detection (CADe) of polyps on colonoscopies, without labels. This holds on Japanese colonoscopies even when MSN is only trained on Israeli colonoscopies, which differ in scoping hardware, endoscope software, screening guidelines, bowel preparation, patient demographics, and the use of techniques such as narrow-band imaging (NBI) and chromoendoscopy (CE). Since our technique uses neither colonoscopy-specific information nor labels, it has the potential to apply to more medical imaging domains.

Purpose: To evaluate the impact of an artificial intelligence (AI) assistant for lung cancer screening on multinational clinical workflows. Materials and Methods: An AI assistant for lung cancer screening was evaluated on two retrospective randomized multireader multicase studies where 627 (141 cancer-positive cases) low-dose chest CT cases were each read twice (with and without AI assistance) by experienced thoracic radiologists (six U.S.-based or six Japan-based radiologists), resulting in a total of 7524 interpretations. Positive cases were defined as those within 2 years before a pathology-confirmed lung cancer diagnosis. Negative cases were defined as those without any subsequent cancer diagnosis for at least 2 years and were enriched for a spectrum of diverse nodules. The studies measured the readers' level of suspicion (on a 0-100 scale), country-specific screening system scoring categories, and management recommendations. Evaluation metrics included the area under the receiver operating characteristic curve (AUC) for level of suspicion and sensitivity and specificity of recall recommendations. Results: With AI assistance, the radiologists' AUC increased by 0.023 (0.70 to 0.72; P . .02) for the U.S. study and by 0.023 (0.93 to 0.96; P . .18) for the Japan study. Scoring system specificity for actionable findings increased 5.5% (57% to 63%; P < .001) for the U.S. study and 6.7% (23% to 30%; P < .001) for the Japan study. There was no evidence of a difference in corresponding sensitivity between unassisted and AI-assisted reads for the U.S. (67.3% to 67.5%; P . .88) and Japan (98% to 100%; P > .99) studies. Corresponding stand-alone AI AUC system performance was 0.75 (95% CI: 0.70, 0.81) and 0.88 (95% CI: 0.78, 0.97) for the U.S.- and Japan-based datasets, respectively. Conclusion : The concurrent AI interface improved lung cancer screening specificity in both U.S.- and Japan-based reader studies, meriting further study in additional international screening environments.

Abstract Background Artificial intelligence (AI) has shown promise in mammography interpretation, and its use as a second reader in breast cancer screening may reduce the burden on health care systems. Purpose To evaluate the performance differences between routine double read and an AI as a second reader workflow (AISR), where the second reader is replaced with AI. Materials and Methods A cohort of patients undergoing routine breast cancer screening at a single center with mammography was retrospectively collected between 2005 and 2021. A model developed on US and UK data was fine-tuned on Japanese data. We subsequently performed a reader study with 10 qualified readers with varied experience (5 reader pairs), comparing routine double read to an AISR workflow. Results A “test set” of 4,059 women (mean age, 56 ± 14 years; 157 positive, 3,902 negative) was collected, with 278 (mean age 55 ± 13 years; 90 positive, 188 negative) evaluated for the reader study. We demonstrate an area under the curve =.84 (95% confidence interval [CI], 0.805-0.881) on the test set, with no significant difference to decisions made in clinical practice (P = .32). Compared with routine double reading, in the AISR arm, sensitivity improved by 7.6% (95% CI, 3.80-11.4; P = .00004) and specificity decreased 3.4% (1.42-5.43; P = .0016), with 71% (212/298) of scans no longer requiring input from a second reader. Variation in recall decision between reader pairs improved from a Cohen kappa of κ = .65 (96% CI, 0.61-0.68) to κ = .74 (96% CI, 0.71-0.77) in the AISR arm. Conclusion AISR improves sensitivity, reduces variability and decreases workload compared to routine dual screening.

Antibodies have become an important class of therapeutic agents to treat human diseases. To accelerate therapeutic antibody discovery, computational methods, especially machine learning, have attracted considerable interest for predicting specific interactions between antibody candidates and target antigens such as viruses and bacteria. However, the publicly available datasets in existing works have notable limitations, such as small sizes and the lack of non-binding samples and exact amino acid sequences. To overcome these limitations, we have developed AVIDa-hIL6, a large-scale dataset for predicting antigen-antibody interactions in the variable domain of heavy chain of heavy chain antibodies (VHHs), produced from an alpaca immunized with the human interleukin-6 (IL-6) protein, as antigens. By leveraging the simple structure of VHHs, which facilitates identification of full-length amino acid sequences by DNA sequencing technology, AVIDa-hIL6 contains 573,891 antigen-VHH pairs with amino acid sequences. All the antigen-VHH pairs have reliable labels for binding or non-binding, as generated by a novel labeling method. Furthermore, via introduction of artificial mutations, AVIDa-hIL6 contains 30 different mutants in addition to wild-type IL-6 protein. This characteristic provides opportunities to develop machine learning models for predicting changes in antibody binding by antigen mutations. We report experimental benchmark results on AVIDa-hIL6 by using machine learning models. The results indicate that the existing models have potential, but further research is needed to generalize them to predict effective antibodies against unknown mutants. The dataset is available at https://avida-hil6.cognanous.com.

Early prediction of patient outcomes is important for targeting preventive care. This protocol describes a practical workflow for developing deep-learning risk models that can predict various clinical and operational outcomes from structured electronic health record (EHR) data. The protocol comprises five main stages: formal problem definition, data pre-processing, architecture selection, calibration and uncertainty, and generalizability evaluation. We have applied the workflow to four endpoints (acute kidney injury, mortality, length of stay and 30-day hospital readmission). The workflow can enable continuous (e.g., triggered every 6 h) and static (e.g., triggered at 24 h after admission) predictions. We also provide an open-source codebase that illustrates some key principles in EHR modeling. This protocol can be used by interdisciplinary teams with programming and clinical expertise to build deep-learning prediction models with alternate data sources and prediction tasks. We present a practical workflow describing how to use deep learning to develop continuous-risk models that can predict various adverse outcomes from structured electronic health records.

The COVID-19 pandemic has highlighted the global need for reliable models of disease spread. We propose an AI-augmented forecast modeling framework that provides daily predictions of the expected number of confirmed COVID-19 deaths, cases, and hospitalizations during the following 4 weeks. We present an international, prospective evaluation of our models' performance across all states and counties in the USA and prefectures in Japan. Nationally, incident mean absolute percentage error (MAPE) for predicting COVID-19 associated deaths during prospective deployment remained consistently <8% (US) and <29% (Japan), while cumulative MAPE remained <2% (US) and <10% (Japan). We show that our models perform well even during periods of considerable change in population behavior, and are robust to demographic differences across different geographic locations. We further demonstrate that our framework provides meaningful explanatory insights with the models accurately adapting to local and national policy interventions. Our framework enables counterfactual simulations, which indicate continuing Non-Pharmaceutical Interventions alongside vaccinations is essential for faster recovery from the pandemic, delaying the application of interventions has a detrimental effect, and allow exploration of the consequences of different vaccination strategies. The COVID-19 pandemic remains a global emergency. In the face of substantial challenges ahead, the approach presented here has the potential to inform critical decisions.

Background Over half a million individuals are diagnosed with head and neck cancer each year globally. Radiotherapy is an important curative treatment for this disease, but it requires manual time to delineate radiosensitive organs at risk. This planning process can delay treatment while also introducing interoperator variability, resulting in downstream radiation dose differences. Although auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying, and achieving expert performance remain. Objective Adopting a deep learning approach, we aim to demonstrate a 3D U-Net architecture that achieves expert-level performance in delineating 21 distinct head and neck organs at risk commonly segmented in clinical practice. Methods The model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practice and segmentations created by experienced radiographers as part of this research, all in accordance with consensus organ at risk definitions. Results We demonstrated the model’s clinical applicability by assessing its performance on a test set of 21 computed tomography scans from clinical practice, each with 21 organs at risk segmented by 2 independent experts. We also introduced surface Dice similarity coefficient, a new metric for the comparison of organ delineation, to quantify the deviation between organ at risk surface contours rather than volumes, better reflecting the clinical task of correcting errors in automated organ segmentations. The model’s generalizability was then demonstrated on 2 distinct open-source data sets, reflecting different centers and countries to model training. Conclusions Deep learning is an effective and clinically applicable technique for the segmentation of the head and neck anatomy for radiotherapy. With appropriate validation studies and regulatory approvals, this system could improve the efficiency, consistency, and safety of radiotherapy pathways.

How noncoding DNA determines gene expression in different cell types is a major unsolved problem, and critical downstream applications in human genetics depend on improved solutions. Here, we report substantially improved gene expression prediction accuracy from DNA sequences through the use of a deep learning architecture, called Enformer, that is able to integrate information from long-range interactions (up to 100 kb away) in the genome. This improvement yielded more accurate variant effect predictions on gene expression for both natural genetic variants and saturation mutagenesis measured by massively parallel reporter assays. Furthermore, Enformer learned to predict enhancer–promoter interactions directly from the DNA sequence competitively with methods that take direct experimental data as input. We expect that these advances will enable more effective fine-mapping of human disease associations and provide a framework to interpret cis -regulatory evolution.

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful 1 . Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives 2 . Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection performance. Unlike leading methods for OOD detection, our approach does not require access to examples labeled explicitly as OOD, which can be difficult to collect in practice. We show in extensive experiments that contrastive training significantly helps OOD detection performance on a number of common benchmarks. By introducing and employing the Confusion Log Probability (CLP) score, which quantifies the difficulty of the OOD detection task by capturing the similarity of inlier and outlier datasets, we show that our method especially improves performance in the `near OOD' classes -- a particularly challenging setting for previous methods.

Center-involved diabetic macular edema (ci-DME) is a major cause of vision loss. Although the gold standard for diagnosis involves 3D imaging, 2D imaging by fundus photography is usually used in screening settings, resulting in high false-positive and false-negative calls. To address this, we train a deep learning model to predict ci-DME from fundus photographs, with an ROC–AUC of 0.89 (95% CI: 0.87–0.91), corresponding to 85% sensitivity at 80% specificity. In comparison, retinal specialists have similar sensitivities (82–85%), but only half the specificity (45–50%, p < 0.001). Our model can also detect the presence of intraretinal fluid (AUC: 0.81; 95% CI: 0.81–0.86) and subretinal fluid (AUC 0.88; 95% CI: 0.85–0.91). Using deep learning to make predictions via simple 2D images without sophisticated 3D-imaging equipment and with better than specialist performance, has broad relevance to many other applications in medical imaging.

Background: Dynamic susceptibility contrast MR imaging (DSC-MRI) offers direct evaluation of neo-vascularity. Ferucarbotran does not accumulate in the interstitial space, instead remaining in the intravascular space during early phase imaging. We investigate tracer kinetic analysis with DSC-MRI with ferucarbotran and single level CT during hepatic arteriography (SL-CTHA) in assessment of hypervascular hepatocellular lesions and evaluate the usefulness of DSC-MRI with ferucarbotran. Methods: Six patients having hypervascular hepatocellular carcinoma (HCC) and 3 patients having focal nodular hyperplasia (FNH) were included in the study. SL-CTHA was performed with the infusion of 3 mL of contrast media at a rate of 1 mL/s and scanned at a rate of 0.8 second per rotation. DSC-MRI was acquired with the echo-planar method at 1.5T system. A total dose of 1.4 mL (0.5 mol Fe/L) of ferucarbotran was used. Ferucarbotran was injected at a rate of 2 mL/s with 40 mL of physiological saline. Imaging was obtained at a temporal resolution of 1.2 or 0.46 seconds in 5 and 4 patients, respectively. For both CT and MRI modalities, a model-free analysis method was used to derive region of interest-based perfusion parameters. Plasma flow, distribution volume (DV) of contrast agent and estimated mean transit time (EMTT) were estimated. Results: A strong correlation was obtained with plasma flow (r=0.8231, P=0.0064) between DSC-MRI and SL-CTHA. No significant correlation was obtained for DV and EMTT between DSC-MRI and SL-CTHA. All perfusion parameters showed no significant difference between SL-CTHA and DSC-MRI in FNH. On the other hand, in HCC, DV and EMTT showed significant differences (P=0.046 and 0.046), and plasma flow showed no significant difference between DSC-MRI and SL-CTHA. Conclusions: This pilot study demonstrates the possibility of quantitative analysis of liver tumor using superparamagnetic iron oxide (SPIO)-based agent and highlights the potential for SPIO-based agent in more precisely assessing the perfusion characteristic of hypervascular liver tumors than by using extracellular contrast media.

Progression to exudative 'wet' age-related macular degeneration (exAMD) is a major cause of visual deterioration. In patients diagnosed with exAMD in one eye, we introduce an artificial intelligence (AI) system to predict progression to exAMD in the second eye. By combining models based on three-dimensional (3D) optical coherence tomography images and corresponding automatic tissue maps, our system predicts conversion to exAMD within a clinically actionable 6-month time window, achieving a per-volumetric-scan sensitivity of 80% at 55% specificity, and 34% sensitivity at 90% specificity. This level of performance corresponds to true positives in 78% and 41% of individual eyes, and false positives in 56% and 17% of individual eyes at the high sensitivity and high specificity points, respectively. Moreover, we show that automatic tissue segmentation can identify anatomical changes before conversion and high-risk subgroups. This AI system overcomes substantial interobserver variability in expert predictions, performing better than five out of six experts, and demonstrates the potential of using AI to predict disease progression.