Machine learning applications in preventive healthcare: A systematic literature review on predictive analytics of disease comorbidity from multiple perspectives

Artificial intelligence is constantly revolutionizing biomedical research and healthcare management. Disease comorbidity is a major threat to the quality of life for susceptible groups, especially middle-aged and elderly patients. The presence of multiple chronic diseases makes precision diagnosis challenging to realize and imposes a heavy burden on the healthcare system and economy. Given an enormous amount of accumulated health data, machine learning techniques show their capability in handling this puzzle. The present study conducts a review to uncover current research efforts in applying these methods to understanding comorbidity mechanisms and making clinical predictions considering these complex patterns. A descriptive metadata analysis of 791 unique publications aims to capture the overall research progression between January 2012 and June 2023. To delve into comorbidity-focused research, 61 of these scientific papers are systematically assessed. Four predictive analytics of tasks are detected: disease comorbidity data extraction, clustering, network, and risk prediction. It is observed that some machine learning-driven applications address inherent data deficiencies in healthcare datasets and provide a model interpretation that identifies significant risk factors of comorbidity development. Based on insights, both technical and practical, gained from relevant literature, this study intends to guide future interests in comorbidity research and draw conclusions about chronic disease prevention and diagnosis with managerial implications.

An XAI-enhanced efficientNetB0 framework for precision brain tumor detection in MRI imaging

BACKGROUND

Accurately diagnosing brain tumors from MRI scans is crucial for effective treatment planning. While traditional methods heavily rely on radiologist expertise, the integration of AI, particularly Convolutional Neural Networks (CNNs), has shown promise in improving accuracy. However, the lack of transparency in AI decision-making processes presents a challenge for clinical adoption.

METHODS

Recent advancements in deep learning, particularly the utilization of CNNs, have facilitated the development of models for medical image analysis. In this study, we employed the EfficientNetB0 architecture and integrated explainable AI techniques to enhance both accuracy and interpretability. Grad-CAM visualization was utilized to highlight significant areas in MRI scans influencing classification decisions.

RESULTS

Our model achieved a classification accuracy of 98.72 % across four categories of brain tumors (Glioma, Meningioma, No Tumor, Pituitary), with precision and recall exceeding 97 % for all categories. The incorporation of explainable AI techniques was validated through visual inspection of Grad-CAM heatmaps, which aligned well with established diagnostic markers in MRI scans.

CONCLUSION

The AI-enhanced EfficientNetB0 framework with explainable AI techniques significantly improves brain tumor classification accuracy to 98.72 %, offering clear visual insights into the decision-making process. This method enhances diagnostic reliability and trust, demonstrating substantial potential for clinical adoption in medical diagnostics.

Panpsychism and dualism in the science of consciousness

A resurgence of panpsychism and dualism is a matter of ongoing debate in modern neuroscience. Although metaphysically hostile, panpsychism and dualism both persist in the science of consciousness because the former is proposed as a straightforward answer to the problem of integrating consciousness into the fabric of physical reality, whereas the latter proposes a simple solution to the problem of free will by endowing consciousness with causal power as a prerequisite for moral responsibility. I take the Integrated Information Theory (IIT) as a paradigmatic exemplar of a theory of consciousness (ToC) that makes its commitments to panpsychism and dualism within a unified framework. These features are not, however, unique for IIT. Many ToCs are implicitly prone to some degree of panpsychism whenever they strive to propose a universal definition of consciousness, associated with one or another known phenomenon. Yet, those ToCs that can be characterized as strongly emergent are at risk of being dualist. A remedy against both covert dualism and uncomfortable corollaries of panpsychism can be found in the evolutionary theory of life, called here "bioprotopsychism" and generalized in terms of autopoiesis and the free energy principle. Bioprotopsychism provides a biologically inspired basis for a minimalist approach to consciousness via the triad "chemotaxis-efference copy mechanism-counterfactual active inference" by associating the stream of weakly emergent conscious states with an amount of information (best guesses) of the brain, engaged in unconscious predictive processing.

Artificial intelligence-based prediction of pathogen emergence and evolution in the world of synthetic biology

The emergence of new techniques in both microbial biotechnology and artificial intelligence (AI) is opening up a completely new field for monitoring and sometimes even controlling the evolution of pathogens. However, the now famous generative AI extracts and reorganizes prior knowledge from large datasets, making it poorly suited to making predictions in an unreliable future. In contrast, an unfamiliar perspective can help us identify key issues related to the emergence of new technologies, such as those arising from synthetic biology, whilst revisiting old views of AI or including generative AI as a generator of abduction as a resource. This could enable us to identify dangerous situations that are bound to emerge in the not-too-distant future, and prepare ourselves to anticipate when and where they will occur. Here, we emphasize the fact that amongst the many causes of pathogen outbreaks, often driven by the explosion of the human population, laboratory accidents are a major cause of epidemics. This review, limited to animal pathogens, concludes with a discussion of potential epidemic origins based on unusual organisms or associations of organisms that have rarely been highlighted or studied.

Longitudinal inference of multiscale markers in psychosis: from hippocampal centrality to functional outcome

Multiscale neuroscience conceptualizes mental illness as arising from aberrant interactions across and within multiple biopsychosocial scales. We leverage this framework to propose a multiscale disease progression model of psychosis, in which hippocampal-cortical dysconnectivity precedes impairments in episodic memory and social cognition, which lead to more severe negative symptoms and lower functional outcome. As psychosis represents a heterogeneous collection of biological and behavioral alterations that evolve over time, we further predict this disease progression for a subtype of the patient sample, with other patients showing normal-range performance on all variables. We sampled data from two cross-sectional datasets of first- and multi-episode psychosis, resulting in a sample of 163 patients and 119 non-clinical controls. To address our proposed disease progression model and evaluate potential heterogeneity, we applied a machine-learning algorithm, SuStaIn, to the patient data. SuStaIn uniquely integrates clustering and disease progression modeling and identified three patient subtypes. Subtype 0 showed normal-range performance on all variables. In comparison, Subtype 1 showed lower episodic memory, social cognition, functional outcome, and higher negative symptoms, while Subtype 2 showed lower hippocampal-cortical connectivity and episodic memory. Subtype 1 deteriorated from episodic memory to social cognition, negative symptoms, functional outcome to bilateral hippocampal-cortical dysconnectivity, while Subtype 2 deteriorated from bilateral hippocampal-cortical dysconnectivity to episodic memory and social cognition, functional outcome to negative symptoms. This first application of SuStaIn in a multiscale psychiatric model provides distinct disease trajectories of hippocampal-cortical connectivity, which might underlie the heterogeneous behavioral manifestations of psychosis.

ChatGPT compared to national guidelines for management of ovarian cancer: Did ChatGPT get it right? - A Memorial Sloan Kettering Cancer Center Team Ovary study

OBJECTIVES

We evaluated the performance of a chatbot compared to the National Comprehensive Cancer Network (NCCN) Guidelines for the management of ovarian cancer.

METHODS

Using NCCN Guidelines, we generated 10 questions and answers regarding management of ovarian cancer at a single point in time. Questions were thematically divided into risk factors, surgical management, medical management, and surveillance. We asked ChatGPT (GPT-4) to provide responses without prompting (unprompted GPT) and with prompt engineering (prompted GPT). Responses were blinded and evaluated for accuracy and completeness by 5 gynecologic oncologists. A score of 0 was defined as inaccurate, 1 as accurate and incomplete, and 2 as accurate and complete. Evaluations were compared among NCCN, unprompted GPT, and prompted GPT answers.

RESULTS

Overall, 48% of responses from NCCN, 64% from unprompted GPT, and 66% from prompted GPT were accurate and complete. The percentage of accurate but incomplete responses was higher for NCCN vs GPT-4. The percentage of accurate and complete scores for questions regarding risk factors, surgical management, and surveillance was higher for GPT-4 vs NCCN; however, for questions regarding medical management, the percentage was lower for GPT-4 vs NCCN. Overall, 14% of responses from unprompted GPT, 12% from prompted GPT, and 10% from NCCN were inaccurate.

CONCLUSIONS

GPT-4 provided accurate and complete responses at a single point in time to a limited set of questions regarding ovarian cancer, with best performance in areas of risk factors, surgical management, and surveillance. Occasional inaccuracies, however, should limit unsupervised use of chatbots at this time.

Development of a machine learning-based model for the prediction and progression of diabetic kidney disease: A single centred retrospective study

BACKGROUND

Diabetic kidney disease (DKD) is a diabetic microvascular complication often characterized by an unpredictable progression. Hence, early detection and recognition of patients vulnerable to progression is crucial.

OBJECTIVE

To develop a prediction model to identify the stages of DKD and the factors contributing to progression to each stage using machine learning.

METHODOLOGY

A retrospective study was conducted in a South Indian tertiary care hospital and collected the details of patients diagnosed with DKD from January 2017 to January 2022. Bayesian optimization-based machine learning techniques such as classification and regression were employed. The model was developed with the help of an optimization framework that effectively balances classification, prediction accuracy, and explainability.

RESULTS

Of the 311 patients diagnosed with DKD, 227 were selected for the study. A system for predicting DKD has been created for a patient dataset utilizing a variety of machine-learning approaches. The eXtreme gradient (XG) Boost method excelled, achieving 88.75% accuracy, 88.57% precision, 91.4% sensitivity,100% specificity, and 89.49% F1-score. An interpretable data-driven method highlights significant features for early DKD diagnosis. The best explainable prediction model uses the XG Boost classifier, revealing serum uric acid, urea, phosphorous, red blood cells, calcium, and absolute eosinophil count as the major predictors influencing the progression of DKD. In the case of regression models, the gradient boost regressor performed the best, with an R2 score of 0.97.

CONCLUSION

Machine learning algorithms can effectively predict the stages of DKD and thus help physicians in providing patients with personalized care at the right time.

Automated image transcription for perinatal blood pressure monitoring using mobile health technology

This paper introduces a novel approach to address the challenges associated with transferring blood pressure (BP) data obtained from oscillometric devices used in self-measured BP monitoring systems to integrate this data into medical health records or a proxy database accessible by clinicians, particularly in low literacy populations. To this end, we developed an automated image transcription technique to effectively transcribe readings from BP devices, ultimately enhancing the accessibility and usability of BP data for monitoring and managing BP during pregnancy and the postpartum period, particularly in low-resource settings and low-literate populations. In the designed study, the photos of the BP devices were captured as part of perinatal mobile health (mHealth) monitoring programs, conducted in four studies across two countries. The Guatemala Set 1 and Guatemala Set 2 datasets include the data captured by a cohort of 49 lay midwives from 1697 and 584 pregnant women carrying singletons in the second and third trimesters in rural Guatemala during routine screening. Additionally, we designed an mHealth system in Georgia for postpartum women to monitor and report their BP at home with 23 and 49 African American participants contributing to the Georgia I3 and Georgia IMPROVE projects, respectively. We developed a deep learning-based model which operates in two steps: LCD localization using the You Only Look Once (YOLO) object detection model and digit recognition using a convolutional neural network-based model capable of recognizing multiple digits. We applied color correction and thresholding techniques to minimize the impact of reflection and artifacts. Three experiments were conducted based on the devices used for training the digit recognition model. Overall, our results demonstrate that the device-specific model with transfer learning and the device independent model outperformed the device-specific model without transfer learning. The mean absolute error (MAE) of image transcription on held-out test datasets using the device-independent digit recognition were 1.2 and 0.8 mmHg for systolic and diastolic BP in the Georgia IMPROVE and 0.9 and 0.5 mmHg in Guatemala Set 2 datasets. The MAE, far below the FDA recommendation of 5 mmHg, makes the proposed automatic image transcription model suitable for general use when used with appropriate low-error BP devices.

Assessing the response quality and readability of chatbots in cardiovascular health, oncology, and psoriasis: A comparative study

BACKGROUND

Chatbots using the Large Language Model (LLM) generate human responses to questions from all categories. Due to staff shortages in healthcare systems, patients waiting for an appointment increasingly use chatbots to get information about their condition. Given the number of chatbots currently available, assessing the responses they generate is essential.

METHODS

Five chatbots with free access were selected (Gemini, Microsoft Copilot, PiAI, ChatGPT, ChatSpot) and blinded using letters (A, B, C, D, E). Each chatbot was asked questions about cardiology, oncology, and psoriasis. Responses were compared to guidelines from the European Society of Cardiology, American Academy of Dermatology and American Society of Clinical Oncology. All answers were assessed using readability scales (Flesch Reading Scale, Gunning Fog Scale Level, Flesch-Kincaid Grade Level and Dale-Chall Score). Using a 3-point Likert scale, two independent medical professionals assessed the compliance of the responses with the guidelines.

RESULTS

A total of 45 questions were asked of all chatbots. Chatbot C gave the shortest answers, 7.0 (6.0 - 8.0), and Chatbot A the longest 17.5 (13.0 - 24.5). The Flesch Reading Ease Scale ranged from 16.3 (12.2 - 21.9) (Chatbot D) to 39.8 (29.0 - 50.4) (Chatbot A). Flesch-Kincaid Grade Level ranged from 12.5 (10.6 - 14.6) (Chatbot A) to 15.9 (15.1 - 17.1) (Chatbot D). Gunning Fog Scale Level ranged from 15.77 (Chatbot A) to 19.73 (Chatbot D). Dale-Chall Score ranged from 10.3 (9.3 - 11.3) (Chatbot A) to 11.9 (11.5 - 12.4) (Chatbot D).

CONCLUSION

This study indicates that chatbots vary in length, quality, and readability. They answer each question in their own way, based on the data they have pulled from the web. Reliability of the responses generated by chatbots is high. This suggests that people who want information from a chatbot need to be careful and verify the answers they receive, particularly when they ask about medical and health aspects.

Advances in AI and machine learning for predictive medicine

The field of omics, driven by advances in high-throughput sequencing, faces a data explosion. This abundance of data offers unprecedented opportunities for predictive modeling in precision medicine, but also presents formidable challenges in data analysis and interpretation. Traditional machine learning (ML) techniques have been partly successful in generating predictive models for omics analysis but exhibit limitations in handling potential relationships within the data for more accurate prediction. This review explores a revolutionary shift in predictive modeling through the application of deep learning (DL), specifically convolutional neural networks (CNNs). Using transformation methods such as DeepInsight, omics data with independent variables in tabular (table-like, including vector) form can be turned into image-like representations, enabling CNNs to capture latent features effectively. This approach not only enhances predictive power but also leverages transfer learning, reducing computational time, and improving performance. However, integrating CNNs in predictive omics data analysis is not without challenges, including issues related to model interpretability, data heterogeneity, and data size. Addressing these challenges requires a multidisciplinary approach, involving collaborations between ML experts, bioinformatics researchers, biologists, and medical doctors. This review illuminates these complexities and charts a course for future research to unlock the full predictive potential of CNNs in omics data analysis and related fields.

Spatial lung imaging in clinical and translational settings

For many severe lung diseases, non-invasive biomarkers from imaging could improve early detection of lung injury or disease onset, establish a diagnosis, or help follow-up disease progression and treatment strategies. Imaging of the thorax and lung is challenging due to its size, respiration movement, transferred cardiac pulsation, vast density range and gravitation sensitivity. However, there is extensive ongoing research in this fast-evolving field. Recent improvements in spatial imaging have allowed us to study the three-dimensional structure of the lung, providing both spatial architecture and transcriptomic information at single-cell resolution. This fast progression, however, comes with several challenges, including significant image file storage and network capacity issues, increased costs, data processing and analysis, the role of artificial intelligence and machine learning, and mechanisms to combine several modalities. In this review, we provide an overview of advances and current issues in the field of spatial lung imaging.

Accuracy of a Commercial Large Language Model (ChatGPT) to Perform Disaster Triage of Simulated Patients Using the Simple Triage and Rapid Treatment (START) Protocol: Gage Repeatability and Reproducibility Study

BACKGROUND

The release of ChatGPT (OpenAI) in November 2022 drastically reduced the barrier to using artificial intelligence by allowing a simple web-based text interface to a large language model (LLM). One use case where ChatGPT could be useful is in triaging patients at the site of a disaster using the Simple Triage and Rapid Treatment (START) protocol. However, LLMs experience several common errors including hallucinations (also called confabulations) and prompt dependency.

OBJECTIVE

This study addresses the research problem: "Can ChatGPT adequately triage simulated disaster patients using the START protocol?" by measuring three outcomes: repeatability, reproducibility, and accuracy.

METHODS

Nine prompts were developed by 5 disaster medicine physicians. A Python script queried ChatGPT Version 4 for each prompt combined with 391 validated simulated patient vignettes. Ten repetitions of each combination were performed for a total of 35,190 simulated triages. A reference standard START triage code for each simulated case was assigned by 2 disaster medicine specialists (JMF and MV), with a third specialist (LC) added if the first two did not agree. Results were evaluated using a gage repeatability and reproducibility study (gage R and R). Repeatability was defined as variation due to repeated use of the same prompt. Reproducibility was defined as variation due to the use of different prompts on the same patient vignette. Accuracy was defined as agreement with the reference standard.

RESULTS

Although 35,102 (99.7%) queries returned a valid START score, there was considerable variability. Repeatability (use of the same prompt repeatedly) was 14% of the overall variation. Reproducibility (use of different prompts) was 4.1% of the overall variation. The accuracy of ChatGPT for START was 63.9% with a 32.9% overtriage rate and a 3.1% undertriage rate. Accuracy varied by prompt with a maximum of 71.8% and a minimum of 46.7%.

CONCLUSIONS

This study indicates that ChatGPT version 4 is insufficient to triage simulated disaster patients via the START protocol. It demonstrated suboptimal repeatability and reproducibility. The overall accuracy of triage was only 63.9%. Health care professionals are advised to exercise caution while using commercial LLMs for vital medical determinations, given that these tools may commonly produce inaccurate data, colloquially referred to as hallucinations or confabulations. Artificial intelligence-guided tools should undergo rigorous statistical evaluation-using methods such as gage R and R-before implementation into clinical settings.

Data-driven toxicity prediction in drug discovery: Current status and future directions

Early toxicity assessment plays a vital role in the drug discovery process on account of its significant influence on the attrition rate of candidates. Recently, constant upgrading of information technology has greatly promoted the continuous development of toxicity prediction. To give an overview of the current state of data-driven toxicity prediction, we reviewed relevant studies and summarize them in three main respects: the features and difficulties of toxicity prediction, the evolution of modeling approaches, and the available tools for toxicity prediction. For each approach, we expound the research status, existing challenges, and feasible solutions. Finally, several new directions and suggestions for toxicity prediction are also put forward.

Uncovering the scientific landscape: A bibliometric and Visualized Analysis of artificial intelligence in Traditional Chinese Medicine

The emergence of artificial intelligence (AI) technology has presented new challenges and opportunities for Traditional Chinese Medicine (TCM), aiming to provide objective assessments and improve clinical effectiveness. However, there is a lack of comprehensive analyses on the research trajectory, key directions, current trends, and future perspectives in this field. This research aims to comprehensively update the progress of AI in TCM over the past 24 years, based on data from the Web of Science database covering January 1, 2000, to March 1, 2024. Using advanced analytical tools, we conducted detailed bibliometric and visual analyses. The results highlight China's predominant influence, contributing 54.35 % of the total publications and playing a key role in shaping research in this field. Significant productivity was observed at institutions such as the China Academy of Chinese Medical Sciences, Beijing University of Chinese Medicine, and Shanghai University of Traditional Chinese Medicine, with Wang Yu being the most prolific contributor. The journal Molecules contributed the most publications in this field. This study identified hepatocellular carcinoma, chemical and drug-induced liver injury, Papillon-Lefèvre disease, Parkinson's disease, and anorexia as the most significant disorders researched. This comprehensive bibliometric assessment benefits both seasoned researchers and newcomers, offering quick access to essential information and fostering the generation of innovative ideas in this field.

Prompt-guided and multimodal landscape scenicness assessments with vision-language models

Recent advances in deep learning and Vision-Language Models (VLM) have enabled efficient transfer to downstream tasks even when limited labelled training data is available, as well as for text to be directly compared to image content. These properties of VLMs enable new opportunities for the annotation and analysis of images. We test the potential of VLMs for landscape scenicness prediction, i.e., the aesthetic quality of a landscape, using zero- and few-shot methods. We experiment with few-shot learning by fine-tuning a single linear layer on a pre-trained VLM representation. We find that a model fitted to just a few hundred samples performs favourably compared to a model trained on hundreds of thousands of examples in a fully supervised way. We also explore the zero-shot prediction potential of contrastive prompting using positive and negative landscape aesthetic concepts. Our results show that this method outperforms a linear probe with few-shot learning when using a small number of samples to tune the prompt configuration. We introduce Landscape Prompt Ensembling (LPE), which is an annotation method for acquiring landscape scenicness ratings through rated text descriptions without needing an image dataset during annotation. We demonstrate that LPE can provide landscape scenicness assessments that are concordant with a dataset of image ratings. The success of zero- and few-shot methods combined with their ability to use text-based annotations highlights the potential for VLMs to provide efficient landscape scenicness assessments with greater flexibility.

Global cross-sectional student survey on AI in medical, dental, and veterinary education and practice at 192 faculties

BACKGROUND

The successful integration of artificial intelligence (AI) in healthcare depends on the global perspectives of all stakeholders. This study aims to answer the research question: What are the attitudes of medical, dental, and veterinary students towards AI in education and practice, and what are the regional differences in these perceptions?

METHODS

An anonymous online survey was developed based on a literature review and expert panel discussions. The survey assessed students' AI knowledge, attitudes towards AI in healthcare, current state of AI education, and preferences for AI teaching. It consisted of 16 multiple-choice items, eight demographic queries, and one free-field comment section. Medical, dental, and veterinary students from various countries were invited to participate via faculty newsletters and courses. The survey measured technological literacy, AI knowledge, current state of AI education, preferences for AI teaching, and attitudes towards AI in healthcare using Likert scales. Data were analyzed using descriptive statistics, Mann-Whitney U-test, Kruskal-Wallis test, and Dunn-Bonferroni post hoc test.

RESULTS

The survey included 4313 medical, 205 dentistry, and 78 veterinary students from 192 faculties and 48 countries. Most participants were from Europe (51.1%), followed by North/South America (23.3%) and Asia (21.3%). Students reported positive attitudes towards AI in healthcare (median: 4, IQR: 3-4) and a desire for more AI teaching (median: 4, IQR: 4-5). However, they had limited AI knowledge (median: 2, IQR: 2-2), lack of AI courses (76.3%), and felt unprepared to use AI in their careers (median: 2, IQR: 1-3). Subgroup analyses revealed significant differences between the Global North and South (r = 0.025 to 0.185, all P < .001) and across continents (r = 0.301 to 0.531, all P < .001), with generally small effect sizes.

CONCLUSIONS

This large-scale international survey highlights medical, dental, and veterinary students' positive perceptions of AI in healthcare, their strong desire for AI education, and the current lack of AI teaching in medical curricula worldwide. The study identifies a need for integrating AI education into medical curricula, considering regional differences in perceptions and educational needs.

TRIAL REGISTRATION

Not applicable (no clinical trial).

Readiness, knowledge, and perception towards artificial intelligence of medical students at faculty of medicine, Pelita Harapan University, Indonesia: a cross sectional study

INTRODUCTION

Artificial intelligence (AI) enables machines to perform many complicated human skills which require various levels of human intelligence. In the field of medicine, AI helps physicians in making diagnoses and treatments for patients with more efficiency, accuracy, and precision. In order to prepare medical students who are the future healthcare workforce, it is important to enhance their readiness, knowledge and perception toward AI. This study aims to assess Pelita Harapan University (PHU) medical students' readiness, knowledge, and perception toward AI.

METHODS

A quantitative cross-sectional study was conducted to assess respondents' readiness, knowledge and perception toward AI. An online questionnaire was distributed via Google Forms to all batch of medical students. Medical Artificial Intelligence Readiness Scale for Medical Students (MAIRS-MS) questionnaire was used to evaluate AI readiness, while an adapted questionnaires was used to evaluate knowledge and perception toward AI. Data were then analyzed using IBM Statistical Package for Social Sciences (SPSS) version 23.0.

RESULTS

A total of 650 respondents were included in this study. Most respondents were in pre-clinical phase (88%) while the remaining were in clinical phase (12%). Overall, the total mean score for AI readiness was 73.34 of 100. Respondents had a mean score 24.52 ± 5.26 of 40, 27.78 ± 4.65 of 40, 10.57 ± 2.07 of 15, and 10.47 ± 2.00 of 15 in the cognitive, ability, vision, and ethics domain respectively. Generally, respondents had sufficient knowledge and positive perception toward AI. There were also significant correlation between readiness and knowledge with gender, having studied coding previously in high school, and having family or close friends working in AI field. Social media also had a good influence on enchancing readiness in the domain of ability and ethics, and perception towards AI.

CONCLUSION

Medical students of PHU mostly showed neutral to favorable response on readiness, knowledge, and perception towards AI. Incorporating AI into high school and medical curriculum is an important step to prepare medical students' encounter and partnership with AI as the future workforce in medicine.

A comprehensive review of machine learning techniques for multi-omics data integration: challenges and applications in precision oncology

Multi-omics data play a crucial role in precision medicine, mainly to understand the diverse biological interaction between different omics. Machine learning approaches have been extensively employed in this context over the years. This review aims to comprehensively summarize and categorize these advancements, focusing on the integration of multi-omics data, which includes genomics, transcriptomics, proteomics and metabolomics, alongside clinical data. We discuss various machine learning techniques and computational methodologies used for integrating distinct omics datasets and provide valuable insights into their application. The review emphasizes both the challenges and opportunities present in multi-omics data integration, precision medicine and patient stratification, offering practical recommendations for method selection in various scenarios. Recent advances in deep learning and network-based approaches are also explored, highlighting their potential to harmonize diverse biological information layers. Additionally, we present a roadmap for the integration of multi-omics data in precision oncology, outlining the advantages, challenges and implementation difficulties. Hence this review offers a thorough overview of current literature, providing researchers with insights into machine learning techniques for patient stratification, particularly in precision oncology. Contact:  anirban@klyuniv.ac.in.

Safeguarding Patients in the AI Era: Ethics at the Forefront of Pharmacovigilance

Artificial intelligence is increasingly being used in pharmacovigilance. However, the use of artificial intelligence in pharmacovigilance raises ethical concerns related to fairness, non-discrimination, compliance, and responsibility as the central ethical principles in risk assessment and regulatory requirements. This paper explores these concerns and provides a roadmap to how to address these challenges by considering data collection, privacy protection, transparency and accountability, model training, and explainability in artificial intelligence decision making for drug safety surveillance. A number of responsible approaches have been identified including an ethics framework and best practices to enhance artificial intelligence use in healthcare. The document also recognizes some initiatives that have demonstrated the importance of ethics in artificial intelligence pharmacovigilance. Nevertheless, the major needs mentioned in this paper are transparency, accountability, data protection, and fairness, which stress the necessity of collaboration to construct a cognitive framework aimed at integrating ethical artificial intelligence into pharmacovigilance. In conclusion, innovation should be balanced with ethical responsibility to enhance public health outcomes as well as patient safety.

Pronouns reactivate conceptual representations in human hippocampal neurons

During discourse comprehension, every new word adds to an evolving representation of meaning that accumulates over consecutive sentences and constrains the next words. To minimize repetition and utterance length, languages use pronouns, like the word "she," to refer to nouns and phrases that were previously introduced. It has been suggested that language comprehension requires that pronouns activate the same neuronal representations as the nouns themselves. We recorded from individual neurons in the human hippocampus during a reading task. Cells that were selective to a particular noun were later reactivated by pronouns that refer to the cells' preferred noun. These results imply that concept cells contribute to a rapid and dynamic semantic memory network that is recruited during language comprehension.

Integration of QTL and transcriptome approaches for the identification of genes involved in tomato response to nitrogen deficiency

Optimizing plant nitrogen (N) usage and inhibiting N leaching loss in the soil-crop system is crucial to maintaining crop yield and reducing environmental pollution. This study aimed at identifying quantitative trait loci (QTLs) and differentially expressed genes (DEGs) between two N treatments in order to list candidate genes related to nitrogen-related contrasting traits in tomato varieties. We characterized a genetic diversity core-collection (CC) and a multi-parental advanced generation intercross (MAGIC) tomato population grown in a greenhouse under two nitrogen levels and assessed several N-related traits and mapped QTLs. Transcriptome response under the two N conditions was also investigated through RNA sequencing of fruit and leaves in four parents of the MAGIC population. Significant differences in response to N input reduction were observed at the phenotypic level for biomass and N-related traits. Twenty-seven QTLs were detected for three target traits (leaf N content, leaf nitrogen balance index, and petiole NO3- content), 10 and six in the low and high N condition, respectively, while 19 QTLs were identified for plasticity traits. At the transcriptome level, 4752 and 2405 DEGs were detected between the two N conditions in leaves and fruits, respectively, among which 3628 (50.6%) in leaves and 1717 (71.4%) in fruit were genotype specific. When considering all the genotypes, 1677 DEGs were shared between organs or tissues. Finally, we integrated DEG and QTL analyses to identify the most promising candidate genes. The results highlighted a complex genetic architecture of N homeostasis in tomato and novel putative genes useful for breeding tomato varieties requiring less N input.

Triage Accuracy and the Safety of User-Initiated Symptom Assessment With an Electronic Symptom Checker in a Real-Life Setting: Instrument Validation Study

BACKGROUND

Previous studies have evaluated the accuracy of the diagnostics of electronic symptom checkers (ESCs) and triage using clinical case vignettes. National Omaolo digital services (Omaolo) in Finland consist of an ESC for various symptoms. Omaolo is a medical device with a Conformité Européenne marking (risk class: IIa), based on Duodecim Clinical Decision Support, EBMEDS.

OBJECTIVE

This study investigates how well triage performed by the ESC nurse triage within the chief symptom list available in Omaolo (anal region symptoms, cough, diarrhea, discharge from the eye or watery or reddish eye, headache, heartburn, knee symptom or injury, lower back pain or injury, oral health, painful or blocked ear, respiratory tract infection, sexually transmitted disease, shoulder pain or stiffness or injury, sore throat or throat symptom, and urinary tract infection). In addition, the accuracy, specificity, sensitivity, and safety of the Omaolo ESC were assessed.

METHODS

This is a clinical validation study in a real-life setting performed at multiple primary health care (PHC) centers across Finland. The included units were of the walk-in model of primary care, where no previous phone call or contact was required. Upon arriving at the PHC center, users (patients) answered the ESC questions and received a triage recommendation; a nurse then assessed their triage. Findings on 877 patients were analyzed by matching the ESC recommendations with triage by the triage nurse.

RESULTS

Safe assessments by the ESC accounted for 97.6% (856/877; 95% CI 95.6%-98.0%) of all assessments made. The mean of the exact match for all symptom assessments was 53.7% (471/877; 95% CI 49.2%-55.9%). The mean value of the exact match or overly conservative but suitable for all (ESC's assessment was 1 triage level higher than the nurse's triage) symptom assessments was 66.6% (584/877; 95% CI 63.4%-69.7%). When the nurse concluded that urgent treatment was needed, the ESC's exactly matched accuracy was 70.9% (244/344; 95% CI 65.8%-75.7%). Sensitivity for the Omaolo ESC was 62.6% and specificity of 69.2%. A total of 21 critical assessments were identified for further analysis: there was no indication of compromised patient safety.

CONCLUSIONS

The primary objectives of this study were to evaluate the safety and to explore the accuracy, specificity, and sensitivity of the Omaolo ESC. The results indicate that the ESC is safe in a real-life setting when appraised with assessments conducted by triage nurses. Furthermore, the Omaolo ESC exhibits the potential to guide patients to appropriate triage destinations effectively, helping them to receive timely and suitable care.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.2196/41423.

(Semi)automated approaches to data extraction for systematic reviews and meta-analyses in social sciences: A living review

Background

An abundance of rapidly accumulating scientific evidence presents novel opportunities for researchers and practitioners alike, yet such advantages are often overshadowed by resource demands associated with finding and aggregating a continually expanding body of scientific information. Data extraction activities associated with evidence synthesis have been described as time-consuming to the point of critically limiting the usefulness of research. Across social science disciplines, the use of automation technologies for timely and accurate knowledge synthesis can enhance research translation value, better inform key policy development, and expand the current understanding of human interactions, organizations, and systems. Ongoing developments surrounding automation are highly concentrated in research for evidence-based medicine with limited evidence surrounding tools and techniques applied outside of the clinical research community. The goal of the present study is to extend the automation knowledge base by synthesizing current trends in the application of extraction technologies of key data elements of interest for social scientists.

Methods

We report the baseline results of a living systematic review of automated data extraction techniques supporting systematic reviews and meta-analyses in the social sciences. This review follows PRISMA standards for reporting systematic reviews.

Results

The baseline review of social science research yielded 23 relevant studies.

Conclusions

When considering the process of automating systematic review and meta-analysis information extraction, social science research falls short as compared to clinical research that focuses on automatic processing of information related to the PICO framework. With a few exceptions, most tools were either in the infancy stage and not accessible to applied researchers, were domain specific, or required substantial manual coding of articles before automation could occur. Additionally, few solutions considered extraction of data from tables which is where key data elements reside that social and behavioral scientists analyze.

Language models outperform cloze predictability in a cognitive model of reading

Although word predictability is commonly considered an important factor in reading, sophisticated accounts of predictability in theories of reading are lacking. Computational models of reading traditionally use cloze norming as a proxy of word predictability, but what cloze norms precisely capture remains unclear. This study investigates whether large language models (LLMs) can fill this gap. Contextual predictions are implemented via a novel parallel-graded mechanism, where all predicted words at a given position are pre-activated as a function of contextual certainty, which varies dynamically as text processing unfolds. Through reading simulations with OB1-reader, a cognitive model of word recognition and eye-movement control in reading, we compare the model's fit to eye-movement data when using predictability values derived from a cloze task against those derived from LLMs (GPT-2 and LLaMA). Root Mean Square Error between simulated and human eye movements indicates that LLM predictability provides a better fit than cloze. This is the first study to use LLMs to augment a cognitive model of reading with higher-order language processing while proposing a mechanism on the interplay between word predictability and eye movements.

Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook

In the complex and multidimensional field of medicine, multimodal data are prevalent and crucial for informed clinical decisions. Multimodal data span a broad spectrum of data types, including medical images (eg, MRI and CT scans), time-series data (eg, sensor data from wearable devices and electronic health records), audio recordings (eg, heart and respiratory sounds and patient interviews), text (eg, clinical notes and research articles), videos (eg, surgical procedures), and omics data (eg, genomics and proteomics). While advancements in large language models (LLMs) have enabled new applications for knowledge retrieval and processing in the medical field, most LLMs remain limited to processing unimodal data, typically text-based content, and often overlook the importance of integrating the diverse data modalities encountered in clinical practice. This paper aims to present a detailed, practical, and solution-oriented perspective on the use of multimodal LLMs (M-LLMs) in the medical field. Our investigation spanned M-LLM foundational principles, current and potential applications, technical and ethical challenges, and future research directions. By connecting these elements, we aimed to provide a comprehensive framework that links diverse aspects of M-LLMs, offering a unified vision for their future in health care. This approach aims to guide both future research and practical implementations of M-LLMs in health care, positioning them as a paradigm shift toward integrated, multimodal data-driven medical practice. We anticipate that this work will spark further discussion and inspire the development of innovative approaches in the next generation of medical M-LLM systems.

Assessing the Quality of ChatGPT's Responses to Questions Related to Radiofrequency Ablation for Varicose Veins

OBJECTIVE

This study aimed to evaluate the accuracy and reproducibility of information provided by ChatGPT, in response to frequently asked questions (FAQs) about radiofrequency ablation (RFA) for varicose veins.

METHODS

This cross-sectional study was conducted at The Aga Khan University Hospital, Karachi, Pakistan. A set of 18 FAQs regarding RFA for varicose veins were compiled from credible online sources and presented to ChatGPT twice, separately, using the 'new chat' option. Twelve experienced vascular surgeons (with over 2 years of experience and at least 20 RFA procedures performed annually) independently evaluated the accuracy of the responses using a 4-point Likert scale and assessed their reproducibility.

RESULTS

Most evaluators were males (n=10/12, 83.3%) with an average of 12.3 ± 6.2 years of experience as a vascular surgeon. Six (50%) evaluators were from the UK followed by three (25.0%) from Saudi Arabia, two (16.7%) from Pakistan, and one (8.3%) from the USA. Among the 216 accuracy grades, most of the evaluators graded the responses as 'comprehensive' (n=87/216, 40.3%) or 'accurate but insufficient' (n=70/216, 32.4%), whereas only 17.1% (n=37/216) were graded as 'a mixture of both accurate and inaccurate information' and 10.8% (n=22/216) as 'entirely inaccurate'. Overall, 89.8% (n=194/216) of the responses were deemed reproducible. Of the total responses, 70.4% (n=152/216) were classified as 'good quality' and 'reproducible'. The remaining responses were 'poor quality' with 19.4% (n=42/216) 'reproducible' and 10.2% (n=22/216) 'non-reproducible'. There was non-significant inter-rater disagreement among the vascular surgeons for overall responses (Fleiss' Kappa: -0.028, p=0.131).

CONCLUSION

ChatGPT provided generally accurate and reproducible information on RFA for varicose veins, however, variability in response quality and limited inter-rater reliability highlight the need for further improvements. While it has the potential to enhance patient education and support healthcare decision-making, improvements in its training, validation, transparency, and mechanisms to address inaccurate or incomplete information are essential.

Artificial intelligence (AI) applications in improvement of IMRT and VMAT radiotherapy treatment planning processes: A systematic review

INTRODUCTION

Radiotherapy is a common option in the treatment of many types of cancer. Intensity-Modulated Radiation Therapy (IMRT) and Volumetric-Modulated Arc Therapy (VMAT) are the latest radiotherapy techniques. However, clinicians face problems due to these techniques' complexity and time-consuming planning. Various studies have pointed out the importance and role of artificial intelligence (AI) in radiotherapy and accelerating and improving its quality. This research explores different AI methods in different fields of IMRT and VMAT. This study evaluated both quantitative and qualitative methods used within the reviewed articles.

METHODS

Various articles were reviewed from Google Scholar, Science Direct, and PubMed databases between 2018 and 2024. According to PRISMA 2020 guidelines, study selection processes, screening, and inclusion and exclusion criteria were defined. The critical Appraisal Skill Program qualitative checklist tool was used for the qualitative evaluation of articles.

RESULTS

26 articles met the inclusion among the 33 articles obtained. The search procedure was displayed using the PRISMA flow diagram. The evaluation of the articles shows the automation of various treatment planning processes by AI methods and their better performance than traditional methods. The qualitative evaluation of studies has demonstrated the high quality of all studies. The lowest score obtained from the qualitative evaluation of the article is 7 out of 9.

CONCLUSION

AI methods used in radiotherapy reduce time and increase prediction accuracy. They also work better than other methods in different areas, such as dose prediction, treatment design, and dose delivery.

IMPLICATIONS FOR PRACTICE

Healthcare providers should consider integrating artificial intelligence technologies into their practice to optimize treatment planning and enhance patient care in radiation therapy. Additionally, fostering collaboration between radiotherapy experts and artificial intelligence specialists can significantly improve the development and application of AI technologies in this field.

An outlook on structural biology after AlphaFold: tools, limits and perspectives

AlphaFold and similar groundbreaking, AI-based tools, have revolutionized the field of structural bioinformatics, with their remarkable accuracy in ab-initio protein structure prediction. This success has catalyzed the development of new software and pipelines aimed at incorporating AlphaFold's predictions, often focusing on addressing the algorithm's remaining challenges. Here, we present the current landscape of structural bioinformatics shaped by AlphaFold, and discuss how the field is dynamically responding to this revolution, with new software, methods, and pipelines. While the excitement around AI-based tools led to their widespread application, it is essential to acknowledge that their practical success hinges on their integration into established protocols within structural bioinformatics, often neglected in the context of AI-driven advancements. Indeed, user-driven intervention is still as pivotal in the structure prediction process as in complementing state-of-the-art algorithms with functional and biological knowledge.

Can AI-Generated Clinical Vignettes in Japanese Be Used Medically and Linguistically?

BACKGROUND

Creating clinical vignettes requires considerable effort. Recent developments in generative artificial intelligence (AI) for natural language processing have been remarkable and may allow for the easy and immediate creation of diverse clinical vignettes.

OBJECTIVE

In this study, we evaluated the medical accuracy and grammatical correctness of AI-generated clinical vignettes in Japanese and verified their usefulness.

METHODS

Clinical vignettes were created using the generative AI model GPT-4-0613. The input prompts for the clinical vignettes specified the following seven elements: (1) age, (2) sex, (3) chief complaint and time course since onset, (4) physical findings, (5) examination results, (6) diagnosis, and (7) treatment course. The list of diseases integrated into the vignettes was based on 202 cases considered in the management of diseases and symptoms in Japan's Primary Care Physicians Training Program. The clinical vignettes were evaluated for medical and Japanese-language accuracy by three physicians using a five-point scale. A total score of 13 points or above was defined as "sufficiently beneficial and immediately usable with minor revisions," a score between 10 and 12 points was defined as "partly insufficient and in need of modifications," and a score of 9 points or below was defined as "insufficient."

RESULTS

Regarding medical accuracy, of the 202 clinical vignettes, 118 scored 13 points or above, 78 scored between 10 and 12 points, and 6 scored 9 points or below. Regarding Japanese-language accuracy, 142 vignettes scored 13 points or above, 56 scored between 10 and 12 points, and 4 scored 9 points or below. Overall, 97% (196/202) of vignettes were available with some modifications.

CONCLUSION

Overall, 97% of the clinical vignettes proved practically useful, based on confirmation and revision by Japanese medical physicians. Given the significant effort required by physicians to create vignettes without AI, using GPT is expected to greatly optimize this process.

Ethical Considerations in Human-Centered AI: Advancing Oncology Chatbots through Large Language Models

UNSTRUCTURED

The integration of chatbots in oncology underscores the pressing need for human-centered AI that addresses patient and family concerns with empathy and precision. Human-centered AI emphasizes ethical principles, empathy, and user-centric approaches, ensuring technology aligns with human values and needs. This review critically examines the ethical implications of employing Large Language Models (LLMs) like GPT-3 and GPT-4 in oncology chatbots. It examines how these models replicate human-like language patterns, impacting the design of ethical AI systems. The paper identifies key strategies for ethically developing oncology chatbots, focusing on potential biases arising from extensive datasets and neural networks. Specific datasets, such as those sourced from predominantly Western medical literature and patient interactions, may introduce biases by over-representing certain demographic groups. Moreover, the training methodologies of LLMs, including fine-tuning processes, can exacerbate these biases, leading to outputs that may disproportionately favor affluent or Western populations while neglecting marginalized communities. By providing examples of biased outputs in oncology chatbots, the review highlights the ethical challenges LLMs present and the need for mitigation strategies. The study emphasizes integrating human-centric values into AI to mitigate these biases, ultimately advocating for the development of oncology chatbots that are aligned with ethical principles and capable of serving diverse patient populations equitably.

GastricAITool: A Clinical Decision Support Tool for the Diagnosis and Prognosis of Gastric Cancer

BACKGROUND/OBJECTIVE

Gastric cancer (GC) is a complex disease representing a significant global health concern. Advanced tools for the early diagnosis and prediction of adverse outcomes are crucial. In this context, artificial intelligence (AI) plays a fundamental role. The aim of this work was to develop a diagnostic and prognostic tool for GC, providing support to clinicians in critical decision-making and enabling personalised strategies.

METHODS

Different machine learning and deep learning techniques were explored to build diagnostic and prognostic models, ensuring model interpretability and transparency through explainable AI methods. These models were developed and cross-validated using data from 590 Spanish Caucasian patients with primary GC and 633 cancer-free individuals. Up to 261 variables were analysed, including demographic, environmental, clinical, tumoral, and genetic data. Variables such as Helicobacter pylori infection, tobacco use, family history of GC, TNM staging, metastasis, tumour location, treatment received, gender, age, and genetic factors (single nucleotide polymorphisms) were selected as inputs due to their association with the risk and progression of the disease.

RESULTS

The XGBoost algorithm (version 1.7.4) achieved the best performance for diagnosis, with an AUC value of 0.68 using 5-fold cross-validation. As for prognosis, the Random Survival Forest algorithm achieved a C-index of 0.77. Of interest, the incorporation of genetic data into the clinical-demographics models significantly increased discriminatory ability in both diagnostic and prognostic models.

CONCLUSIONS

This article presents GastricAITool, a simple and intuitive decision support tool for the diagnosis and prognosis of GC.

Lenition in L2 Spanish: The Impact of Study Abroad on Phonological Acquisition

Objective: This study investigated the degrees of lenition, or consonantal weakening, in the production of Spanish stop consonants by native English speakers during a study abroad (SA) program. Lenition is a key phonological process in Spanish, where voiced stops (/b/, /d/, /ɡ/) typically weaken to fricatives or approximants in specific phonetic environments. For L2 learners, mastering this subtle process is essential for achieving native-like pronunciation. Methods: To assess the learners' progress in acquiring lenition, we employed Phonet, a deep learning model. Unlike traditional quantitative acoustic methods that focus on measuring the physical properties of speech sounds, Phonet utilizes recurrent neural networks to predict the posterior probabilities of phonological features, particularly sonorant and continuant characteristics, which are central to the lenition process. Results: The results indicated that while learners showed progress in producing the fricative-like variants of lenition during the SA program and understood how to produce lenition in appropriate contexts, the retention of these phonological gains was not sustained after their return. Additionally, unlike native speakers, the learners never fully achieved the approximant-like realization of lenition. Conclusions: These findings underscore the need for sustained exposure and practice beyond the SA experience to ensure the long-term retention of L2 phonological patterns. While SA programs offer valuable opportunities for enhancing L2 pronunciation, they should be supplemented with ongoing support to consolidate and extend the gains achieved during the immersive experience.

The Promise of Artificial Intelligence in Peyronie's Disease

PURPOSE OF REVIEW

The application of artificial intelligence (AI) to enhance clinical decision-making in Peyronie's disease (PD) has generated significant interest. This review explores the current landscape of AI in PD evaluation.

RECENT FINDINGS

Recent advances in 3D modeling offer a more sophisticated approach to assessing PD deformities; however, the implementation of 3D modeling in clinical practice faces challenges, including the need for specialized equipment and time-consuming data processing, sometimes taking several hours of labor. AI holds promise for overcoming these hurdles through its ability to efficiently process large volumes of data and to perform accurate predictions based on such data. Future integration of AI with 3D modeling techniques could revolutionize PD evaluation by improving patient counseling, surgical planning, and clinical decision-making. Significant gaps in the literature have yet to be addressed, including the absence of robust evidence that incorporating such technology is superior to standard diagnostics.

Comparing the Ability of Google and ChatGPT to Accurately Respond to Oculoplastics-Related Patient Questions and Generate Customized Oculoplastics Patient Education Materials

Purpose

To compare the accuracy and readability of responses to oculoplastics patient questions provided by Google and ChatGPT. Additionally, to assess the ability of ChatGPT to create customized patient education materials.

Methods

We executed a Google search to identify the 3 most frequently asked patient questions (FAQs) related to 10 oculoplastics conditions. FAQs were entered into both the Google search engine and the ChatGPT tool and responses were recorded. Responses were graded for readability using five validated readability indices and for accuracy by six oculoplastics surgeons. ChatGPT was instructed to create patient education materials at various reading levels for 8 oculoplastics procedures. The accuracy and readability of ChatGPT-generated procedural explanations were assessed.

Results

ChatGPT responses to patient FAQs were written at a significantly higher average grade level than Google responses (grade 15.6 vs 10.0, p < 0.001). ChatGPT responses (93% accuracy) were significantly more accurate (p < 0.001) than Google responses (78% accuracy) and were preferred by expert panelists (79%). ChatGPT accurately explained oculoplastics procedures at an above average reading level. When instructed to rewrite patient education materials at a lower reading level, grade level was reduced by approximately 4 (15.7 vs 11.7, respectively, p < 0.001) without sacrificing accuracy.

Conclusion

ChatGPT has the potential to provide patients with accurate information regarding their oculoplastics conditions. ChatGPT may also be utilized by oculoplastic surgeons as an accurate tool to provide customizable patient education for patients with varying health literacy. A better understanding of oculoplastics conditions and procedures amongst patients can lead to informed eye care decisions.

Reliability of AlphaFold2 Models in Virtual Drug Screening: A Focus on Selected Class A GPCRs

Protein three-dimensional (3D) structure prediction is one of the most challenging issues in the field of computational biochemistry, which has overwhelmed scientists for almost half a century. A significant breakthrough in structural biology has been established by developing the artificial intelligence (AI) system AlphaFold2 (AF2). The AF2 system provides a state-of-the-art prediction of protein structures from nearly all known protein sequences with high accuracy. This study examined the reliability of AF2 models compared to the experimental structures in drug discovery, focusing on one of the most common protein drug-targeted classes known as G protein-coupled receptors (GPCRs) class A. A total of 32 representative protein targets were selected, including experimental structures of X-ray crystallographic and Cryo-EM structures and their corresponding AF2 models. The quality of AF2 models was assessed using different structure validation tools, including the pLDDT score, RMSD value, MolProbity score, percentage of Ramachandran favored, QMEAN Z-score, and QMEANDisCo Global. The molecular docking was performed using the Genetic Optimization for Ligand Docking (GOLD) software. The AF2 models' reliability in virtual drug screening was determined by their ability to predict the ligand binding poses closest to the native binding pose by assessing the Root Mean Square Deviation (RMSD) metric and docking scoring function. The quality of the docking and scoring function was evaluated using the enrichment factor (EF). Furthermore, the capability of using AF2 models in molecular docking to identify hits with key protein-ligand interactions was analyzed. The posing power results showed that the AF2 models successfully predicted ligand binding poses (RMSD < 2 Å). However, they exhibited lower screening power, with average EF values of 2.24, 2.42, and 1.82 for X-ray, Cryo-EM, and AF2 structures, respectively. Moreover, our study revealed that molecular docking using AF2 models can identify competitive inhibitors. In conclusion, this study found that AF2 models provided docking results comparable to experimental structures, particularly for certain GPCR targets, and could potentially significantly impact drug discovery.

The Emerging Role of Artificial Intelligence and Automated Platforms for the Assessment of Penile Curvature: A Scoping Review

PURPOSE OF THE REVIEW

The estimation of penile curvature is an essential component in the assessment of both Peyronie's disease and hypospadias-associated congenital penile curvature, as the degree of curvature can significantly impact treatment decision-making. However, there is a lack of standardization in curvature assessment and current methodologies are prone to inaccuracies. With the rise of artificial intelligence (AI) in urology, new research has explored its applications in penile curvature assessment. This review aims to evaluate the current uses of AI and other automated platforms for assessing penile curvature.

RECENT FINDINGS

Several novel and promising tools have been developed to estimate penile curvature, some utilizing AI-driven models and others employing automated computational models. These platforms aim to improve curvature assessment in various settings, including at-home evaluation of Peyronie's disease, in-office assessments using three-dimensional (3D) methodologies, and preoperative evaluations for hypospadias repair. In general, these new platforms produce highly accurate and reproducible angle estimates in non-clinical studies, however their effectiveness and relation to patient outcomes has had limited evaluation in clinical settings. Significant advancements have been made in the assessment and estimation of penile curvature in both Peyronie's and pediatric patients, largely driven by AI and other automated platforms. Continued research is needed to validate these findings in clinical studies, confirm their efficacy, and assess their feasibility for real-world applications.

Unveiling the clinical incapabilities: a benchmarking study of GPT-4V(ision) for ophthalmic multimodal image analysis

PURPOSE

To evaluate the capabilities and incapabilities of a GPT-4V(ision)-based chatbot in interpreting ocular multimodal images.

METHODS

We developed a digital ophthalmologist app using GPT-4V and evaluated its performance with a dataset (60 images, 60 ophthalmic conditions, 6 modalities) that included slit-lamp, scanning laser ophthalmoscopy, fundus photography of the posterior pole (FPP), optical coherence tomography, fundus fluorescein angiography and ocular ultrasound images. The chatbot was tested with ten open-ended questions per image, covering examination identification, lesion detection, diagnosis and decision support. The responses were manually assessed for accuracy, usability, safety and diagnosis repeatability. Auto-evaluation was performed using sentence similarity and GPT-4-based auto-evaluation.

RESULTS

Out of 600 responses, 30.6% were accurate, 21.5% were highly usable and 55.6% were deemed as no harm. GPT-4V performed best with slit-lamp images, with 42.0%, 38.5% and 68.5% of the responses being accurate, highly usable and no harm, respectively. However, its performance was weaker in FPP images, with only 13.7%, 3.7% and 38.5% in the same categories. GPT-4V correctly identified 95.6% of the imaging modalities and showed varying accuracies in lesion identification (25.6%), diagnosis (16.1%) and decision support (24.0%). The overall repeatability of GPT-4V in diagnosing ocular images was 63.3% (38/60). The overall sentence similarity between responses generated by GPT-4V and human answers is 55.5%, with Spearman correlations of 0.569 for accuracy and 0.576 for usability.

CONCLUSION

GPT-4V currently is not yet suitable for clinical decision-making in ophthalmology. Our study serves as a benchmark for enhancing ophthalmic multimodal models.

Ethical framework for artificial intelligence in healthcare research: A path to integrity

The integration of Artificial Intelligence (AI) into healthcare research promises unprecedented advancements in medical diagnostics, treatment personalization, and patient care management. However, these innovations also bring forth significant ethical challenges that must be addressed to maintain public trust, ensure patient safety, and uphold data integrity. This article sets out to introduce a detailed framework designed to steer governance and offer a systematic method for assuring that AI applications in healthcare research are developed and executed with integrity and adherence to medical research ethics.

ICGA-GPT: report generation and question answering for indocyanine green angiography images

BACKGROUND

Indocyanine green angiography (ICGA) is vital for diagnosing chorioretinal diseases, but its interpretation and patient communication require extensive expertise and time-consuming efforts. We aim to develop a bilingual ICGA report generation and question-answering (QA) system.

METHODS

Our dataset comprised 213 129 ICGA images from 2919 participants. The system comprised two stages: image-text alignment for report generation by a multimodal transformer architecture, and large language model (LLM)-based QA with ICGA text reports and human-input questions. Performance was assessed using both qualitative metrics (including Bilingual Evaluation Understudy (BLEU), Consensus-based Image Description Evaluation (CIDEr), Recall-Oriented Understudy for Gisting Evaluation-Longest Common Subsequence (ROUGE-L), Semantic Propositional Image Caption Evaluation (SPICE), accuracy, sensitivity, specificity, precision and F1 score) and subjective evaluation by three experienced ophthalmologists using 5-point scales (5 refers to high quality).

RESULTS

We produced 8757 ICGA reports covering 39 disease-related conditions after bilingual translation (66.7% English, 33.3% Chinese). The ICGA-GPT model's report generation performance was evaluated with BLEU scores (1-4) of 0.48, 0.44, 0.40 and 0.37; CIDEr of 0.82; ROUGE of 0.41 and SPICE of 0.18. For disease-based metrics, the average specificity, accuracy, precision, sensitivity and F1 score were 0.98, 0.94, 0.70, 0.68 and 0.64, respectively. Assessing the quality of 50 images (100 reports), three ophthalmologists achieved substantial agreement (kappa=0.723 for completeness, kappa=0.738 for accuracy), yielding scores from 3.20 to 3.55. In an interactive QA scenario involving 100 generated answers, the ophthalmologists provided scores of 4.24, 4.22 and 4.10, displaying good consistency (kappa=0.779).

CONCLUSION

This pioneering study introduces the ICGA-GPT model for report generation and interactive QA for the first time, underscoring the potential of LLMs in assisting with automated ICGA image interpretation.

Unveiling the Transformative Potential of AI-Generated Imagery in Enriching Mental Health Research

Visual methods in mental health research have been extensively explored and utilized following the expanse of art-therapy. The existing literature shows visual arts as a valuable research method with multi-fold benefits for both researchers and research participants. However, the way contemporary art is understood, conceptualized, and experienced has been challenged by the current digital advancements in our society. Despite heated debates whether AI may diminish the value of human creativity, AI-generated art is a complex reality that started to influence the way visual research is conducted. Within this context, researchers employing visual methods need to develop a deeper understanding of this topic. For this purpose, this article explores the concept of AI-generated images with a focus on benefits and limitations when applied to mental health research and potentially other areas of health and social care. As this is an emerging topic, more research on the effectiveness and therapeutic value of AI-generated images is required beyond the current anecdotical evidence, from the perspective of the researchers and research participants.

Human-Robot Intimacy: Acceptance of Robots as Intimate Companions

Depictions of robots as romantic partners for humans are frequent in popular culture. As robots become part of human society, they will gradually assume the role of partners for humans whenever necessary, as assistants, collaborators, or companions. Companion robots are supposed to provide social contact to those who would not have it otherwise. These companion robots are usually not designed to fulfill one of the most important human needs: the one for romantic and intimate contact. Human-robot intimacy remains a vastly unexplored territory. In this article, we review the state-of-the-art research in intimate robotics. We discuss major issues limiting the acceptance of robots as intimate partners, the public perception of robots in intimate roles, and the possible influence of cross-cultural differences in these domains. We also discuss the possible negative effects human-robot intimacy may have on human-human contact. Most importantly, we propose a new term "intimate companion robots" to reduce the negative connotations of the other terms that have been used so far and improve the social perception of research in this domain. With this article, we provide an outlook on prospects for the development of intimate companion robots, considering the specific context of their use.

Human Neural Organoid Microphysiological Systems Show the Building Blocks Necessary for Basic Learning and Memory

Brain Microphysiological Systems including neural organoids derived from human induced pluripotent stem cells offer a unique lens to study the intricate workings of the human brain. This paper investigates the foundational elements of learning and memory in neural organoids, also known as Organoid Intelligence by quantifying immediate early gene expression, synaptic plasticity, neuronal network dynamics, and criticality to demonstrate the utility of these organoids in basic science research. Neural organoids showed synapse formation, glutamatergic and GABAergic receptor expression, immediate early gene expression basally and evoked, functional connectivity, criticality, and synaptic plasticity in response to theta-burst stimulation. In addition, pharmacological interventions on GABAergic and glutamatergic receptors, and input specific theta-burst stimulation further shed light on the capacity of neural organoids to mirror synaptic modulation and short-term potentiation, demonstrating their potential as tools for studying neurophysiological and neurological processes and informing therapeutic strategies for diseases.

Deep learning-based prediction of the dose-volume histograms for volumetric modulated arc therapy of left-sided breast cancer

BACKGROUND

The advancements in artificial intelligence and computational power have made deep learning an attractive tool for radiotherapy treatment planning. Deep learning has the potential to significantly simplify the trial-and-error process involved in inverse planning required by modern treatment techniques such as volumetric modulated arc therapy (VMAT). In this study, we explore the ability of deep learning to predict organ-at-risk (OAR) dose-volume histograms (DVHs) of left-sided breast cancer patients undergoing VMAT treatment based solely on their anatomical characteristics. The predicted DVHs could be used to derive patient-specific dose constraints and dose objectives, streamlining the treatment planning process, standardizing the quality of the plans, and personalizing the treatment planning.

PURPOSE

This study aimed to develop a deep learning-based framework for the prediction of organ-specific dose-volume histograms (DVH) based on structures delineated for left-sided breast cancer treatment.

METHODS

We used a dataset of 249 left-sided breast cancer patients treated with tangential VMAT fields. We extracted delineated structures and dose distributions for each patient and derived slice-by-slice DVHs for planning target volume (PTV) and organs-at-risk. The patients were divided into training (70%, n = 174), validation (10%, n = 24), and test (20%, n = 51) sets. Collected data were used to train a deep learning model for the prediction of the DVHs based on the delineated structures. The developed deep learning model comprised a modified DenseNet architecture followed by a recurrent neural network.

RESULTS

In the independent test set (n = 51), the point-wise differences in the slice-by-slice DVHs between the clinical and predicted DVHs were small; the mean squared errors were 3.53, 1.58, 2.28, 3.37, and 1.44 [×10-4] for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. With the derived cumulative DVHs, the mean absolute difference ± standard deviation of mean doses between the clinical and the predicted DVH were 0.08 ± 0.04 Gy, 0.24 ± 0.22 Gy, 0.73 ± 0.46 Gy, 0.07 ± 0.06 Gy, and 0.14 ± 0.14 Gy for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively.

CONCLUSIONS

The deep learning-based approach enabled automatic and reliable prediction of the DVH based on delineated structures. The predicted DVHs could potentially serve as patient-specific clinical goals used to aid treatment planning and avoid suboptimal plans or to derive optimization objectives and constraints for automated treatment planning.

A comparative evaluation of deep learning approaches for ophthalmology

There is a growing number of publicly available ophthalmic imaging datasets and open-source code for Machine Learning algorithms. This allows ophthalmic researchers and practitioners to independently perform various deep-learning tasks. With the advancement in artificial intelligence (AI) and in the field of imaging, the choice of the most appropriate AI architecture for different tasks will vary greatly. The best-performing AI-dataset combination will depend on the specific problem that needs to be solved and the type of data available. The article discusses different machine learning models and deep learning architectures currently used for various ophthalmic imaging modalities and for different machine learning tasks. It also proposes the most appropriate models based on accuracy and other important factors such as training time, the ability to deploy the model on clinical devices/smartphones, heatmaps that enhance the self-explanatory nature of classification decisions, and the ability to train/adapt on small image datasets to determine if further data collection is worthwhile. The article extensively reviews the existing state-of-the-art AI methods focused on useful machine-learning applications for ophthalmology. It estimates their performance and viability through training and evaluating architectures with different public and private image datasets of different modalities, such as full-color retinal images, OCT images, and 3D OCT scans. The article is expected to benefit the readers by enriching their knowledge of artificial intelligence applied to ophthalmology.