Personalised nutrition (PN) has emerged as an approach to optimise individual health outcomes through more targeted and tailored dietary recommendations based on unique genetic, phenotypic, medical, lifestyle and contextual factors. The application of artificial intelligence (AI) presents an opportunity to achieve personalised nutrition advice at a scale that has population impact. This review introduces a nutrition audience to different AI applications and offers insights into the concepts of AI that might be relevant to the field of nutrition research. The current and future uses of AI in PN are discussed, as well as the potential benefits and challenges to their application. AI-driven solutions have the potential to improve health and reduce the risk of disease because they can consider more information about an individual in making recommendations. However, challenges such as data interoperability, ethical considerations, and model interpretability remain an issue limiting widespread use at this point. This review will provide a foundational understanding of the application of AI within PN and help to identify opportunities to leverage the potential of AI in transforming dietary guidance and enhancing health outcomes through innovative solutions.

The rapid growth of clinical explainable AI (XAI) models raised concerns over unclear purposes and false hope regarding explanations. Currently, no standardised metrics exist for XAI evaluation. We developed a clinician-informed, 14-item checklist including clinical, machine and decision attributes. This is the first step toward XAI standardisation and transparent reporting XAI methods to enhance trust, reduce risks, foster AI adoption, and improve decisions to determine the true clinical potential of applied XAI.

Hepatic steatosis, a key factor in chronic liver diseases, is difficult to diagnose early. This study introduces a classifier for hepatic steatosis using microwave technology, validated through clinical trials. Our method uses microwave signals and deep learning to improve detection to reliable results. It includes a pipeline with simulation data, a new deep-learning model called HepNet, and transfer learning. The simulation data, created with 3D electromagnetic tools, is used for training and evaluating the model. HepNet uses skip connections in convolutional layers and two fully connected layers for better feature extraction and generalization. Calibration and uncertainty assessments ensure the model's robustness. Our simulation achieved an F1-score of 0.91 and a confidence level of 0.97 for classifications with entropy ≤0.1, outperforming traditional models like LeNet (0.81) and ResNet (0.87). We also use transfer learning to adapt HepNet to clinical data with limited patient samples. Using 1H-MRS as the standard for two microwave liver scanners, HepNet achieved high F1-scores of 0.95 and 0.88 for 94 and 158 patient samples, respectively, showing its clinical potential.

Objective This study aimed to assess the practicality and trustworthiness of explainable artificial intelligence (XAI) methods used for explaining clinical predictive models. Methods Two popular XAIs used for explaining clinical predictive models were evaluated based on their ability to generate domain-appropriate representations, impact clinical workflow, and consistency. Explanations were benchmarked against true clinical deterioration triggers recorded in the data system and agreement was quantified. The evaluation was conducted using two Electronic Medical Records datasets from major hospitals in Australia. Results were examined and commented on by a senior clinician. Results Findings demonstrate a violation of consistency criteria and moderate concordance (0.47-0.8) with true triggers, undermining reliability and actionability, criteria for clinicians’ trust in XAI. Conclusion Explanations are not trustworthy to guide clinical interventions, though they may offer useful insights and help model troubleshooting. Clinician-informed XAI development and presentation, clear disclaimers on limitations, and critical clinical judgment can promote informed decisions and prevent over-reliance.

Bradycardia is a commonly occurring condition in premature infants, often causing serious consequences and cardiovascular complications. Reliable and accurate detection of bradycardia events is pivotal for timely intervention and effective treatment. Excessive false alarms pose a critical problem in bradycardia event detection, eroding trust in machine learning (ML)-based clinical decision support tools designed for such detection. This could result in disregarding the algorithm's accurate recommendations and disrupting workflows, potentially compromising the quality of patient care. This article introduces an ML-based approach incorporating an output correction element, designed to minimise false alarms. The approach has been applied to bradycardia detection in preterm infants. We applied five ML-based autoencoder techniques, using recurrent neural network (RNN), long-short-term memory (LSTM), gated recurrent unit (GRU), 1D convolutional neural network (1D CNN), and a combination of 1D CNN and LSTM. The analysis is performed on ∼440 hours of real-time preterm infant data. The proposed approach achieved 0.978, 0.73, 0.992, 0.671 and 0.007 in AUC-ROC, AUC-PRC, recall, F1 score, and false positive rate (FPR) respectively and a false alarms reduction of 36% when compared with methods without the correction approach. This study underscores the imperative of cultivating solutions that alleviate alarm fatigue and encourage active engagement among healthcare professionals.

Stroke is a leading cause of death and disability worldwide, and early diagnosis and prompt medical intervention are thus crucial. Frequent monitoring of stroke patients is also essential to assess treatment efficacy and detect complications earlier. While computed tomography (CT) and magnetic resonance imaging (MRI) are commonly used for stroke diagnosis, they cannot be easily used onsite, nor for frequent monitoring purposes. To meet those requirements, an electromagnetic imaging (EMI) device, which is portable, non-invasive, and non-ionizing, has been developed. It uses a headset with an antenna array that irradiates the head with a safe low-frequency EM field and captures scattered fields to map the brain using a complementary set of physics-based and data-driven algorithms, enabling quasi-real-time detection, two-dimensional localization, and classification of strokes. This study reports clinical findings from the first time the device was used on stroke patients. The clinical results on 50 patients indicate achieving an overall accuracy of 98% in classification and 80% in two-dimensional quadrant localization. With its lightweight design and potential for use by a single para-medical staff at the point of care, the device can be used in intensive care units, emergency departments, and by paramedics for onsite diagnosis.

Accurate identification of the QRS complex is critical to analyse heart rate variability (HRV), which is linked to various adverse outcomes in premature infants. Reliable and accurate extraction of HRV characteristics at a large scale in the neonatal context remains a challenge. In this paper, we investigate the capabilities of 15 state-of-the-art QRS complex detection implementations using two real-world preterm neonatal datasets. As an attempt to improve the accuracy and reliability, we introduce a weighted ensemble-based method as an alternative. Obtained results indicate the superiority of the proposed method over the state of the art on both datasets with an F1-score of 0.966 (95% CI 0.962-0.97) and 0.893 (95% CI 0.892-0.894). This motivates the deployment of ensemble-based methods for any HRV-based analysis to ensure robust and accurate QRS complex detection.

The lack of transparency and explainability hinders the clinical adoption of Machine learning (ML) algorithms. While explainable artificial intelligence (XAI) methods have been proposed, little research has focused on the agreement between these methods and expert clinical knowledge. This study applies current state-of-the-art explainability methods to clinical decision support algorithms developed for Electronic Medical Records (EMR) data to analyse the concordance between these factors and discusses causes for identified discrepancies from a clinical and technical perspective. Important factors for achieving trustworthy XAI solutions for clinical decision support are also discussed.

Stroke is one of the leading causes of death and disability. To address this challenge, microwave imaging has been proposed as a portable medical imaging modality. However, accurate stroke classification using microwave signals is still an open challenge. In addition, identified features of microwave signals used for stroke classification need to be linked back to the original data. This work attempts to address these issues by proposing a wavelet convolutional neural network (CNN), which combines multiresolution analysis and CNN to learn distinctive patterns in the scalogram for accurate classification. A game theoretic approach is used to explain the model and indicate distinctive features for discriminating stroke types. The proposed algorithm is tested in simulation and experiments. Different types of noise and manufacturing tolerances are modeled using data collected from healthy human trials and added to the simulation data to bridge the gap between the simulation and real-life data. The achieved classification accuracy using the proposed method ranges from 81.7% for 3D simulations to 95.7% for lab experiments using simple head phantoms. Obtained explanations using the method indicate the relevance of wavelet coefficients on frequencies 0.95-1.45 GHz and the time slot of 1.3 to 1.7 ns for distinguishing ischemic from hemorrhagic strokes.