Artificial Intelligence in Medicine

The integration of morphological attributes extracted from histopathological images and genomic data holds significant importance in advancing tumor diagnosis, prognosis, and grading. Histopathological images are acquired through microscopic ...

• Developed a multi-modal, multi-task framework for glioma diagnosis.
• Integrated Swin-Transformer v2 with contrastive learning to enhance image features.
• Implemented a novel gene selection method to reduce data redundancy.
• ...

Medical Concept Normalization (MCN) is a crucial process for deep information extraction and natural language processing tasks, which plays a vital role in biomedical research. Although MCN in English has achieved significant research ...

• Neural network architectural model we proposed significantly outperforms other previous methods.
• The framework of multi-task learning combine dynamic and static vectors.
• Explore the impact of knowledge-enhanced on the experiments.

Antimicrobial resistance (AMR) is a major threat to public health worldwide. It is a promising way to improve appropriate prescription by the review and stewardship of antimicrobials, and Post-Prescription Review (PPR) is currently the main tool ...

• A novel Multi-label Antimicrobial Post-Prescription Review System (MAPRS) to improve the post-prescription review capability
• Achieved fine-grained review of antimicrobial prescriptions, which are highly consistent with the guidelines

Dynamic functional connections (dFCs), can reveal neural activities, which provides an insightful way of mining the temporal patterns within the human brain and further detecting brain disorders. However, most existing studies focus on the dFCs ...

• Introducing a novel method to explore temporal patterns in dFCs.
• Combining Fourier transform with a non-stationary kernel to mine higher-order temporal patterns.
• Mining long-range relationships and complex temporal patterns in ...

To build datasets containing useful information from drug databases and recommend a list of drugs to physicians and patients with high accuracy by considering a wide range of features of people, diseases, and chemicals.

A ...

• Sentiment analysis was employed by NLP approaches in pre-processing.
• Neural network-based methods and RS algorithms were employed for modelling the system.
• We used knowledge from drug information and combined the model’s outcome ...

Accurate prediction of drug–target binding affinity (DTA) is essential in the field of drug discovery. Recently, scientists have been attempting to utilize artificial intelligence prediction to screen out a significant number of ineffective ...

• We propose a new DTA prediction model that facilitates drug discovery research.
• We resolve issues from incomplete substructure learning and overlooked atoms.
• We solve insufficient sequence info and errors in predicted spatial ...

Parkinson’s disease (PD) is the second most prevalent neurodegenerative disorder, and it remains incurable. Currently there is no definitive biomarker for detecting PD, measuring its severity, or monitoring of treatments. Recently, oculomotor ...

• A self-supervised geometrical representation that reconstruct SPD matrices.
• A geometrical ocular fixation descriptor able to classify Parkinson patterns.
• A potential digital Parkinson Biomarker designed without expert-label ...

Structural and functional brain networks are generated from two scan sequences of magnetic resonance imaging data, which can provide different perspectives for describing pathological changes caused by brain diseases. Recent studies found that ...

• We design a general end-to-end neural network framework for fusing structural and functional brain networks to identify brain diseases.
• We consider multi-granularity properties during the process of multi-modal brain network fusion for ...

The integration of different imaging modalities, such as structural, diffusion tensor, and functional magnetic resonance imaging, with deep learning models has yielded promising outcomes in discerning phenotypic characteristics and enhancing ...

• Deep learning and multimodal data to predict neurological deficits.
• Self-supervised contrastive learning to fuse heterogeneous multimodal features.
• Supervised contrastive learning to capture shared information among similar ...

Electrocardiogram (ECG) delineation is essential to the identification of abnormal cardiac status, especially when ECG signals are remotely monitored with wearable devices. The complexity and diversity of cardiac conditions generate numerous ...

• An abnormal recognition-assisted network links ECG delineation and disease diagnosis.
• Our onset-offset aware loss improves waveform boundary detection, reducing misdiagnosis.
• Our method shows favorable results on both wearable and ...

Mental health disorders pose an increasing public health challenge worsened by the COVID-19 pandemic. The pandemic highlighted gaps in preparedness, emphasizing the need for early identification of at-risk groups and ...

• The COVID-19 pandemic and lockdown worsened mental health, revealing a lack of preparedness to address this growing crisis.
• Interpretable machine learning predicts depression, anxiety, and stress, highlighting factors like poor health ...

Developing technology to assist medical experts in their everyday decision-making is currently a hot topic in the field of Artificial Intelligence (AI). This is specially true within the framework of Evidence-Based Medicine (EBM), where the aim ...

• A novel extractive task to identify the explanations of the correct answer in commented medical exams.
• The first dataset for Medical QA in a language other than English.
• Promising results in identifying relevant evidence-based ...

Clinical diagnoses are typically made by following a series of steps recommended by guidelines that are authored by colleges of experts. Accordingly, guidelines play a crucial role in rationalizing clinical decisions. However, they ...

• We adapt the reinforcement learning framework to diagnosis decision support.
• Our approach progressively constructs optimal sequences of actions to reach a diagnosis, which we refer to as diagnostic decision pathways.
• We perform an ...

Mental fatigue is defined as a decline in the ability and efficiency of mental activities. A lot of research suggests that the transition from alertness to fatigue is accompanied by alterations in correlation patterns among various brain regions. ...

• Mental fatigue status features vary with channels, thus requiring model adaptation.
• Spectral and temporal connections reflect the EEG properties within individuals.
• Graph convolutional network with dual transformation learns ...

Physics-based computer models based on numerical solutions of the governing equations generally cannot make rapid predictions, which in turn limits their applications in the clinic. To address this issue, we developed a physics-informed neural ...

• Physics-informed neural network (PINN) model for rapid prediction of cardiovascular hemodynamics.
• PINN model achieved a maximum error of less than 5%.
• Inverse PINN modeling approach for rapid estimation of cardiac contractility (in ...

Multi-site MRI imaging poses a significant challenge due to the potential variations in images across different scanners at different sites. This variability can introduce ambiguity in further image analysis. Consequently, the image analysis ...

• We develop a deep learning model that learns features from multi-site datasets.
• Proposed model uses signal and FC matrices for enhanced ASD classification.
• The model consists of two sub-modules: MHACSM and RMCN.
• MHACSM extracts ...

Patients who are undergoing physical rehabilitation, benefit from feedback that follows from reliable assessment of their cumulative performance attained at a given time. In this paper, we provide a method for the learning of the recovery ...

• Random graph learnt using time series data generated on patient playing an exergame.
• New distance computed between probabilities of graphs learnt at successive playing.
• Computed inter-graph distance provides recovery score at one ...

Effective drug delivery is the cornerstone of modern healthcare, ensuring therapeutic compounds reach their intended targets efficiently. This paper explores the potential of personalized and holistic healthcare, driven by the synergy between ...

• Extensively reviews in-silico methods for DTI analysis in both allopathy and siddha.
• Elucidates methodologies, datasets, challenges, future trends to advance DTI research.
• Comparative analysis of DTI studies in allopathy and ...

COVID-19 vaccine research has played a vital role in successfully controlling the pandemic, and the research surrounding the coronavirus vaccine is ever-evolving and accruing. These enormous efforts in knowledge production necessitate a ...

• From 2020 to April 2022 more than 4803 research about COVID-19 Vaccine were published.
• COVID-19 Vaccine Research are clustered in the "Reporting," "Acceptance," "Reaction," "Surveyed Opinions," "Pregnancy," "Titer of Variants," "...

Systematic Review (SR) are foundational to influencing policies and decision-making in healthcare and beyond. SRs thoroughly synthesise primary research on a specific topic while maintaining reproducibility and transparency. However, the rigorous ...

• This study explores optimal Active Learning (AL) combinations for systematic reviews (SRs).
• Smaller initial training samples improve performance metrics in datasets.
• TF-IDF consistently outperformed Doc2Vec and S-BERT.
• ...

Nowadays, the most adopted technique to address infertility problems is in vitro fertilisation (IVF). However, its success rate is limited, and the associated procedures, known as assisted reproduction technology (ART), suffer from a lack of ...

• AI can improve the outcomes of reproductive technologies, especially IVF.
• Many AI applications in IVF focus on embryo selection to optimize transfer.
• AI solutions for oocyte quality assessment can cut costs and boost IVF success ...

The latest evolution of the healthcare industry from Industry 1.0 to 5.0, incorporating smart wearable devices and digital technologies, has revolutionized healthcare delivery and improved patient treatment. Integrating smart wearables such as ...

• A taxonomy is proposed to classify literature on smart wearable devices for healthcare Industry 5.0.
• An ML-based novel model is proposed for healthcare analytics for personalized healthcare using smart wearable devices.
• A case ...

In recent years, we have witnessed both artificial intelligence obtaining remarkable results in clinical decision support systems (CDSSs) and explainable artificial intelligence (XAI) improving the interpretability of these models. In turn, this ...

• Limited availability of data limits small hospitals in generating high- quality counterfactual explanations.
• Integrating federated learning mitigates this limitation and maintains data privacy.
• Benefit of using federated learning ...

Contemporary large language models (LLMs) may have utility for processing unstructured, narrative free-text clinical data contained in electronic health records (EHRs) — a particularly important use-case for mental health where a majority of ...

• Mental health EHR data presents unique challenges for LLMs.
• Variable length clinical data can be ingested by existing LLM architectures.
• Bespoke LLMs perform well for specific clinical tasks such as triaging patients.

Recent advances in large language models (LLM) offer opportunities to automate health coaching. With zero-shot learning ability, LLMs could revolutionize health coaching by providing better accessibility, scalability, and customization. ...

• LLaMA responses were preferred over health coach responses in about 60 % of cases.
• LLaMA had comparable performance with health coaches across five quality dimensions.
• LLM (GPT-4)-based evaluation was consistent with experts in ...

Vision computer-aided diagnostic methods have been used in early ophthalmic disease screening and diagnosis. However, the limited output formats of these methods lead to poor human–computer interaction and low clinical applicability value. Thus, ...

• Ophthalmology large language-and-vision assistant based on LLMs and pre-training visual diagnostic models.
• A new Chinese ophthalmic fine-tuning dataset including the fundus instruction and conversation sets.
• Possessing abundant ...

In this study, we delve into the adaptation and effectiveness of Transformer-based, pre-trained Large Language Models (LLMs) within the biomedical domain, a field that poses unique challenges due to its complexity and the specialized nature of ...

• Comparison between encoder/decoder LLMs and their domain-adapted versions.
• Assessment of the impact of different data volumes on Fine-Tuning.
• Probing and analysis of LLMs’ internal representations and attention mechanisms.
• ...

The entry of large language models (LLMs) into research and commercial spaces has led to a trend of ever-larger models, with initial promises of generalisability. This was followed by a widespread desire to downsize and create specialised models ...

• State of the art performance in Clinical NLP using efficient fine-tuning methods.
• 25 million parameter LLMs benefit from LoRA fine-tuning.
• Classification performance matched with 98% fewer trained parameters.
• Trade-off in ...