Artificial Intelligence in Medicine

Since depression often results in suicidal thoughts and leaves a person severely disabled daily, there is an elevated risk of premature mortality due to mental problems caused by depression. Therefore, it's crucial to identify the patient's ...

• More than two-thirds of suicides each year are caused by depression, which is the most common mental illness.
• Social media posts can be a useful tool for tracking a variety of mental health conditions, including depression.
• The ...

Acute ischemic stroke is one of the leading causes of morbidity and disability worldwide, often followed by a long rehabilitation period. To improve and personalize stroke rehabilitation, it is essential to provide a reliable ...

• Using multimodal clinical and CT perfusion data improves CVA outcome.
• Sequential attention in deep learning on tabular data outperforms baselines.
• Implemented data fusion technique with affine transformation of feature maps.
• ...

Diagnostic errors have become the biggest threat to the safety of patients in primary health care. General practitioners, as the “gatekeepers” of primary health care, have a responsibility to accurately diagnose patients. However, many ...

• A few-shot disease diagnosis modelis proposed for improving the prediction performance in general practice.
• The proposed model referring to model-agnostic meta-learning can achieve fast adaption for new diseases using few examples.

Fetoscopic Laser Coagulation (FLC) for Twin to Twin Transfusion Syndrome is a challenging intervention due to the working conditions: low quality images acquired from a 3 mm fetoscope inside a turbid liquid environment, local view of the ...

Display Omitted

• Robotic platform for TTTS surgery to increase patient safety and surgery outcomes.
• Cognitive control based using hierarchical Finite State Machine architecture.
• Safe autonomous fetoscope navigation to pre-located Points of ...

Neonates are not able to verbally communicate pain, hindering the correct identification of this phenomenon. Several clinical scales have been proposed to assess pain, mainly using the facial features of the neonate, but a better comprehension of ...

• Understanding of human and machine facial feature extraction for clinical practice
• CNN models extracted clinical relevant facial regions to discriminate neonatal pain
• XAI methods yield distinct explanations to the same model, ...

The search for new antimalarial treatments is urgent due to growing resistance to existing therapies. The Open Source Malaria (OSM) project offers a promising starting point, having extensively screened various compounds for their ...

• Interpretability in machine learning for Quantitative Structure-Activity Relationship modelling in drug discovery is important.
• An optimisation-based method for piecewise linear regression, modSAR, applied on data from the Open Source ...

Automatic diagnosis systems capable of handling multiple pathologies are essential in clinical practice. This study focuses on enhancing precise lesion localization, classification and delineation in transurethral resection of bladder tumor (...

• Improved instance segmentation network for bladder cancer addressing multi-pathology classification and the critical aspect of bad cancer resection that leads to cancer recurrence.
• Data augmentation using an texture-constrained version ...

Multi-state processes (Webster, 2019) are commonly used to model the complex clinical evolution of diseases where patients progress through different states. In recent years, machine learning and deep learning algorithms have been proposed to ...

• Multi-state processes can model the complex evolution of diseases.
• Deep learning algorithms improve the accuracy of these models’ predictions.
• Acceptability for regulatory compliance requires interpretability of these algorithms.

Chest X-ray scans are frequently requested to detect the presence of abnormalities, due to their low-cost and non-invasive nature. The interpretation of these images can be automated to prioritize more urgent exams through deep learning models, ...

• The proposed spatial transformer allows the system to focus on the thoracic region.
• This built-in attention-driven model reduces the negative impact of image artifacts.
• A novel loss function and a finetuning stage improve the ...

Reinforcement Learning (RL) has recently found many applications in the healthcare domain thanks to its natural fit to clinical decision-making and ability to learn optimal decisions from observational data. A key challenge in adopting RL-based ...

• Reinforcement learning based on observational data and existing knowledge.
• Treatment advice and physiological knowledge in guidelines are injected into learner.
• Ventilation case study indicates adherence to guidelines, clinician ...

Traditional Chinese medicine (TCM) has been recognized worldwide as a valuable asset of human medicine. The procedure of TCM is to treatment based on syndrome differentiation. However, the effect of TCM syndrome differentiation relies heavily on ...

• Challenges to address the syndrome differentiation issue in TCM.
• The TCM diagnostic knowledge is represented by fist-order logic rules.
• A TCM dataset includes 40,000 clinical records and 500 labels.

Heparin is a critical aspect of managing sepsis after abdominal surgery, which can improve microcirculation, protect organ function, and reduce mortality. However, there is no clinical evidence to support decision-making for heparin dosage. This ...

• This paper proposes a model called SOFA-MDP, which utilizes SOFA scores as states and the difference of SOFA scores of successive states as reward function, to investigate heparin treatment policy of patients with sepsis in ICU.
• ...

Designing appropriate clinical dental treatment plans is an urgent need because a growing number of dental patients are suffering from partial edentulism with the population getting older.

The aim of this study is to ...

• Predict sequential dental treatment plans from textual data through a newly designed deep learning model which integrates CNN and RNN.
• Demonstrate that our workflow achieves the best overall performance compared to a variety of machine ...

It is not uncommon for real-life data produced in healthcare to have a higher proportion of missing data than in other scopes. To take into account these missing data, imputation is not always desired by healthcare experts, and complete case ...

• CBSL algorithm is for BN structure learning on highly missing or non-imputable data.
• It shows a good trade-off between true and false positive arcs.
• The DAG learned by CBSL was preferred to others by senior radiotherapists.

Recently, computational fluid dynamics enables the non-invasive calculation of fractional flow reserve (FFR) based on 3D coronary model, but it is time-consuming. Currently, machine learning technique has emerged as an ...

• Reduced-order (0D) coronary model is used to replace the conventional 3D CFD model for simulating coronary flow.
• Reduced-order (0D) coronary model improves the computational efficiency.
• Machine learning model is embedded into the ...

Human accuracy in diagnosing psychiatric disorders is still low. Even though digitizing health care leads to more and more data, the successful adoption of AI-based digital decision support (DDSS) is rare. One reason is that AI algorithms are ...

Display Omitted

• We evaluate AI models for depression detection based on EHR data of 812,853 patients.
• We propose our Att-GRU-decay model, which outperforms the current state of the art.
• Att-GRU-decay yields a 0.974 AUPRC, 0.999 specificity and ...

Accurate prediction of gastric cancer patient survival time is essential for clinical decision-making. However, unified static models lack specificity and flexibility in predictions owing to the varying survival outcomes among gastric cancer ...

• Proposed a dynamic ensemble regression framework.
• Designed a weighted distance-based method.
• Designed a weighted K-means clustering method and a fuzzy K-means sampling method.
• Applied the proposed methods to the prognosis of ...

Deep Brain Stimulation (DBS) is an implantable medical device used for electrical stimulation to treat neurological disorders. Traditional DBS devices provide fixed frequency pulses, but personalized adjustment of stimulation parameters is ...

• Stabilize the synchronization and convergence points allowing for more accurate estimation.
• Avoid overestimated bias to generalize the model well.
• Adds noise to the target action to exploit the Q-function errors by smoothing out Q-...

Sepsis is a syndrome involving multi-organ dysfunction, and the mortality in sepsis patients correlates with the number of lesioned organs. Precise prognosis models play a pivotal role in enabling healthcare practitioners to administer ...

Display Omitted

• A prediction model integrating the spatiotemporal information in multi-organ systems was proposed for predicting sepsis patients’ in-hospital mortality.
• The model consisted of multiple gated recurrent units (mGRU), graph attention ...

Early assessment, with the help of machine learning methods, can aid clinicians in optimizing the diagnosis and treatment process, allowing patients to receive critical treatment time. Due to the advantages of effective information organization ...

• Multi-grained and temporal medical information is crucial to automatic diagnosis.
• A novel multi-grained evolutionary graph-based framework for disease diagnosis.
• Comprehensive experiments on two real-world datasets.

Artificial intelligence (AI) technology has the potential to transform medical practice within the medical imaging industry and materially improve productivity and patient outcomes. However, low acceptability of AI as a digital ...

• Poor acceptability of AI among healthcare professionals in medical imaging domains threatens to prevent its promising benefits from being realised
• This review summarises the key factors influencing AI acceptability that have been ...

Electroencephalogram (EEG)-based Brain–Computer Interfaces (BCIs) build a communication path between human brain and external devices. Among EEG-based BCI paradigms, the most commonly used one is motor imagery (MI). As a hot research topic, MI ...

• 67 relevant studies are identified and included primarily through a systematic meta-analysis procedure.
• A comprehensive review of Deep Learning-based Motor Imagery EEG classification from various perspectives.
• 13 typical models are ...