OOIR: Observatory of International Research

Papers

(The H4-Index of Nature Machine Intelligence is 68. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2020-03-01 to 2024-03-01.)

Article	Citations
An interpretable mortality prediction model for COVID-19 patients	655
Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans	585
Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators	569
Shortcut learning in deep neural networks	540
Secure, privacy-preserving and federated machine learning in medical imaging	470
Drug discovery with explainable artificial intelligence	406
Predicting the state of charge and health of batteries using data-driven machine learning	332
Deep learning for tomographic image reconstruction	230
AI for radiographic COVID-19 detection selects shortcuts over signal	226
Machine learning pipeline for battery state-of-health estimation	224
An open source machine learning framework for efficient and transparent systematic reviews	214
Molecular contrastive learning of representations via graph neural networks	180
Inverse design of nanoporous crystalline reticular materials with deep generative models	167
Finding key players in complex networks through deep reinforcement learning	164
Expanding functional protein sequence spaces using generative adversarial networks	161
End-to-end privacy preserving deep learning on multi-institutional medical imaging	155
Ensemble deep learning in bioinformatics	153
Geometry-enhanced molecular representation learning for property prediction	150
Causal inference and counterfactual prediction in machine learning for actionable healthcare	147
The carbon impact of artificial intelligence	144
Improved protein structure prediction by deep learning irrespective of co-evolution information	135
Concept whitening for interpretable image recognition	120
Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks	120
Enabling the future of colonoscopy with intelligent and autonomous magnetic manipulation	113
Mapping the space of chemical reactions using attention-based neural networks	112

Development of metaverse for intelligent healthcare	108
The rise of robots in surgical environments during COVID-19	106
Generative molecular design in low data regimes	105
Rapid online learning and robust recall in a neuromorphic olfactory circuit	105
Database-independent molecular formula annotation using Gibbs sampling through ZODIAC	100
Geometric deep learning on molecular representations	98
Deep learning-based prediction of the T cell receptor–antigen binding specificity	97
Bioinspired acousto-magnetic microswarm robots with upstream motility	97
Towards neural Earth system modelling by integrating artificial intelligence in Earth system science	95
A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing	95
Neural circuit policies enabling auditable autonomy	94
Generating three-dimensional structures from a two-dimensional slice with generative adversarial network-based dimensionality expansion	93
Predicting ultrafast nonlinear dynamics in fibre optics with a recurrent neural network	91
Advances, challenges and opportunities in creating data for trustworthy AI	90
A soft robot that adapts to environments through shape change	90
Estimation of continuous valence and arousal levels from faces in naturalistic conditions	89
Code-free deep learning for multi-modality medical image classification	89
Making deep neural networks right for the right scientific reasons by interacting with their explanations	89
Prediction of water stability of metal–organic frameworks using machine learning	89
Towards a new generation of artificial intelligence in China	88
High-accuracy prostate cancer pathology using deep learning	88
Origami-inspired miniature manipulator for teleoperated microsurgery	88
Exploring the limit of using a deep neural network on pileup data for germline variant calling	87
Machine learning and computation-enabled intelligent sensor design	86
scBERT as a large-scale pretrained deep language model for cell type annotation of single-cell RNA-seq data	85
Deep learning incorporating biologically inspired neural dynamics and in-memory computing	85
Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms	85
Automating turbulence modelling by multi-agent reinforcement learning	81
Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis	81
Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning	79
Dual use of artificial-intelligence-powered drug discovery	79
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors	79
Artificial intelligence cooperation to support the global response to COVID-19	76
Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks	74
Controllable protein design with language models	74
The transformational role of GPU computing and deep learning in drug discovery	72
Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning	72
Machine learning and algorithmic fairness in public and population health	72
A soft thumb-sized vision-based sensor with accurate all-round force perception	70
Using online verification to prevent autonomous vehicles from causing accidents	70
A definition, benchmark and database of AI for social good initiatives	70
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images	69
Morphological and molecular breast cancer profiling through explainable machine learning	69
Stable learning establishes some common ground between causal inference and machine learning	68