Evaluation of crowdsourced mortality prediction models as a framework for assessing artificial intelligence in medicine.

OBJECTIVE: Applications of machine learning in healthcare are of high interest and have the potential to improve patient care. Yet, the real-world accuracy of these models in clinical practice and on different patient subpopulations remains unclear. To address these important questions, we hosted a community challenge to evaluate methods that predict healthcare outcomes. We focused on the prediction of all-cause mortality as the community challenge question. MATERIALS AND METHODS: Using a Model-to-Data framework, 345 registered participants, coalescing into 25 independent teams, spread over 3 continents and 10 countries, generated 25 accurate models all trained on a dataset of over 1.1 million patients and evaluated on patients prospectively collected over a 1-year observation of a large health system. RESULTS: The top performing team achieved a final area under the receiver operator curve of 0.947 (95% CI, 0.942-0.951) and an area under the precision-recall curve of 0.487 (95% CI, 0.458-0.499) on a prospectively collected patient cohort. DISCUSSION: Post hoc analysis after the challenge revealed that models differ in accuracy on subpopulations, delineated by race or gender, even when they are trained on the same data. CONCLUSION: This is the largest community challenge focused on the evaluation of state-of-the-art machine learning methods in a healthcare system performed to date, revealing both opportunities and pitfalls of clinical AI.

ArkDTA: attention regularization guided by non-covalent interactions for explainable drug-target binding affinity prediction.

MOTIVATION: Protein-ligand binding affinity prediction is a central task in drug design and development. Cross-modal attention mechanism has recently become a core component of many deep learning models due to its potential to improve model explainability. Non-covalent interactions (NCIs), one of the most critical domain knowledge in binding affinity prediction task, should be incorporated into protein-ligand attention mechanism for more explainable deep drug-target interaction models. We propose ArkDTA, a novel deep neural architecture for explainable binding affinity prediction guided by NCIs. RESULTS: Experimental results show that ArkDTA achieves predictive performance comparable to current state-of-the-art models while significantly improving model explainability. Qualitative investigation into our novel attention mechanism reveals that ArkDTA can identify potential regions for NCIs between candidate drug compounds and target proteins, as well as guiding internal operations of the model in a more interpretable and domain-aware manner. AVAILABILITY: ArkDTA is available at https://github.com/dmis-lab/ArkDTA. CONTACT: kangj@korea.ac.kr.

Thorium and uranium trace ICP-MS analysis for AMoRE project.

AMoRE (Advanced Mo-based Rare process Experiment) is an international collaboration searching for the neutrinoless double-beta decay of the 100Mo isotope with cryogenic detectors using molybdate (100MoO4)-based scintillation crystals. The process requires that the detector apparatus and its components, including bolometric crystals and thus initial materials used for the crystal growth, be extremely low in radioactive isotopes having decays that may generate background noise signals in the region of interest. The present study summarizes an ICP-MS assay program conducted for the AMoRE experiment. Firstly, the 100MoO3 powder, the main component of the crystals, was studied in the analysis. Before crystal synthesis, enriched 100MoO3 powder was purified at the Center for Underground Physics (CUP). To ensure its radio purity, a sample preparation technique with a UTEVA® resin was developed for Th and U analysis with ICP-MS. The recovery yield was over 90% for the extraction procedure, and the detection limits for Th and U were 2.3 and 1.0 ppt, respectively. To determine the most appropriate material for the detector frame and shielding, several types of high-purity Cu were measured: Cu-OFE (Aurubis and Mitsubishi Materials) and Cu-NOSV (Aurubis). Similarly, a solid-phase extraction was applied for Th and U analysis, and detection limits were calculated at 0.1 and 0.2 ppt, respectively. The 3M Vikuiti™ ESR film, the closest part to the crystal in the detector assembly, was used as a light reflector. Two types of Vikuiti film, a roll and a sheet, were checked for radiopurity via full decomposition using a microwave ashing system. The procedural Detection Limits were achieved at a level of about 1 ppt.

Improved survival analysis by learning shared genomic information from pan-cancer data.

MOTIVATION: Recent advances in deep learning have offered solutions to many biomedical tasks. However, there remains a challenge in applying deep learning to survival analysis using human cancer transcriptome data. As the number of genes, the input variables of survival model, is larger than the amount of available cancer patient samples, deep-learning models are prone to overfitting. To address the issue, we introduce a new deep-learning architecture called VAECox. VAECox uses transfer learning and fine tuning. RESULTS: We pre-trained a variational autoencoder on all RNA-seq data in 20 TCGA datasets and transferred the trained weights to our survival prediction model. Then we fine-tuned the transferred weights during training the survival model on each dataset. Results show that our model outperformed other previous models such as Cox Proportional Hazard with LASSO and ridge penalty and Cox-nnet on the 7 of 10 TCGA datasets in terms of C-index. The results signify that the transferred information obtained from entire cancer transcriptome data helped our survival prediction model reduce overfitting and show robust performance in unseen cancer patient samples. AVAILABILITY AND IMPLEMENTATION: Our implementation of VAECox is available at https://github.com/dmis-lab/VAECox. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Fabrication of a nanosize-Pt-embedded membrane electrode assembly to enhance the utilization of Pt in proton exchange membrane fuel cells.

A procedure to locate the Pt nanostructure inside the hydrophilic channel of a Nafion membrane was developed in order to enhance Pt utilization in PEMFCs. Nanosize Pt-embedded MEA was constructed by Cu electroless plating and subsequent Pt electrodeposition inside the hydrophilic channels of the Nafion membrane. The metallic Pt nanostructure fabricated inside the membrane was employed as an oxygen reduction catalyst for a PEMFC and facilitated effective use of the hydrophilic channels inside the membrane. Compared to the conventional MEA, a Pt-embedded MEA with only 68% Pt loading showed better PEMFC performance.