Machine learning applications on neonatal sepsis treatment: a scoping review
Neonatal sepsis has non-specific signs, treatment is labour-intensive, and antimicrobial resistance complicates empiric antibiotic choice.
Papers
1,138 of 1,138 verified cases.
Quantum Error Correction with Quantum Autoencoders
Physics & Astronomy
Quantum Computing Algorithms and Architecture
ai assisted
importance 7/10
scale stated
Quantum processors require active error correction, and designing effective strategies for detecting and correcting varied errors (including correlated errors and qubit loss) is difficult.
Smart Platform for Data Blood Bank Management: Forecasting Demand in Blood Supply Chain Using Machine Learning
Blood supply chains suffer from uncertain demand, causing wastage and shortages when inventory is insufficient.
Application of Machine Learning in Material Synthesis and Property Prediction
Engineering & Materials
Machine Learning in Materials Science
ai assisted
importance 7/10
scale stated
Traditional experimental and simulation-based discovery of new materials is slow and resource-intensive, motivating faster computational approaches.
Application of Deep Learning in Histopathology Images of Breast Cancer: A Review
Detection, segmentation and classification of breast cancer in histopathology images is difficult; the study reviews deep learning approaches to it.
The Immune Subtypes and Landscape of Gastric Cancer and to Predict Based on the Whole-Slide Images Using Deep Learning
Gastric cancer responds heterogeneously to immunotherapy, and identifying immune subtypes could improve therapeutic strategies.
Malaria parasite detection in thick blood smear microscopic images using modified YOLOV3 and YOLOV4 models
Manual microscopic examination of blood smears, the gold standard for malaria diagnosis, depends on skilled microscopists who are scarce in remote developing regions.
Machine learning for predicting cardiac events: what does the future hold?
Medicine & Health
Artificial Intelligence in Healthcare
partially solved
importance 7/10
scale stated
Traditional statistical models cannot predict individual-level risk of cardiovascular events such as heart failure and arrhythmias.
An overview and metanalysis of machine and deep learning-based CRISPR gRNA design tools
Predicting the on-target activity and off-target specificity of CRISPR-Cas9 guide RNAs is difficult, yet decisive for safe and effective gene editing.
Air pollution particulate matter (PM2.5) prediction in South African cities using machine learning techniques
Climate & Environment
Air Quality Monitoring and Forecasting
ai assisted
importance 7/10
scale stated
Predicting PM2.5 particulate pollution in South African cities, where reliable air quality sensors are scarce.
The Application of Machine Learning on Antibody Discovery and Optimization
Biology & Life Sciences
Monoclonal and Polyclonal Antibodies Research
ai assisted
importance 7/10
scale stated
Traditional antibody discovery and optimization is time-consuming and resource-intensive, slowing development of antibody diagnostics and therapeutics.
A Survey on Deep-Learning-Based Diabetic Retinopathy Classification
Diabetic retinopathy damages the eyes of long-term diabetes patients, and early automatic detection is needed to avoid vision loss.
Retinal Disease Detection Using Deep Learning Techniques: A Comprehensive Review
Manual detection of retinal diseases such as glaucoma, diabetic retinopathy and AMD is time-consuming, tedious and lacks repeatability.
Advances in De Novo Drug Design: From Conventional to Machine Learning Methods
De novo drug design, generating novel molecular structures from atomic building blocks, is difficult and costly with conventional structure- or ligand-based methods.
Applications of artificial intelligence in clinical laboratory genomics
Medicine & Health
Artificial Intelligence in Healthcare and Education
ai assisted
importance 7/10
scale stated
Genomic data volumes are exceeding human capacity to rapidly and reproducibly analyze complex molecular data for timely diagnosis and management of genomic disorders.
Superhuman AI for multiplayer poker
AI had surpassed humans in two-player games, but six-player no-limit Texas hold'em poker remained a much harder, unsolved challenge.
An autonomous laboratory for the accelerated synthesis of inorganic materials
Synthesizing novel inorganic materials is slow and labor-intensive; the work aimed to autonomously accelerate solid-state synthesis of targeted compounds.
Identification of nanomolar adenosine A2A receptor ligands using reinforcement learning and structure-based drug design
Finding novel small-molecule ligands for the adenosine A2A receptor from protein structure alone, without prior knowledge of ligand chemistry.
Combinatorial Optimization-Enriched Machine Learning to Solve the Dynamic Vehicle Routing Problem with Time Windows
Logistics providers struggle to plan same-day deliveries: stochastic optimization is too slow online and reinforcement learning struggles with high-dimensional combinatorial problems.
Protein structure prediction with in-cell photo-crosslinking mass spectrometry and deep learning
Biology & Life Sciences
Protein Structure and Dynamics
partially solved
importance 6/10
scale stated
Predicting accurate structures for challenging proteins, such as those undergoing conformational changes or with few homologous sequences, where AlphaFold2 underperforms.
Incorporating the image formation process into deep learning improves network performance
Deconvolution of 3D fluorescence microscopy images is slow and artifact-prone with existing methods.
Deep learning-based enhancement of epigenomics data with AtacWorks
Low cell count, low-coverage or noisy ATAC-seq data limits detection of active regulatory regions in the genome.
MMSplice: modular modeling improves the predictions of genetic variant effects on splicing
Predicting how genetic variants affect splicing (exon skipping, splice site choice, pathogenicity) is difficult but highly relevant to human genetics.
SpCas9 activity prediction by DeepSpCas9, a deep learning–based model with high generalization performance
Predicting SpCas9 gene-editing activity at arbitrary target sequences was unreliable, limiting CRISPR-based editing.