Artificial intelligence (AI) and machine learning (ML) in precision oncology: a review on enhancing discoverability through multiomics integration

Artificial intelligence and the impact of multiomics on the reporting of case reports

The integration of artificial intelligence (AI) and multiomics has transformed clinical and life sciences, enabling precision medicine and redefining disease understanding. Scientific publications grew significantly from 2.1 million in 2012 to 3.3 million in 2022, with AI research tripling during this period. Multiomics fields, including genomics and proteomics, also advanced, exemplified by the Human Proteome Project achieving a 90% complete blueprint by 2021. This growth highlights opportunities and challenges in integrating AI and multiomics into clinical reporting. A review of studies and case reports was conducted to evaluate AI and multiomics integration. Key areas analyzed included diagnostic accuracy, predictive modeling, and personalized treatment approaches driven by AI tools. Case examples were studied to assess impacts on clinical decision-making. AI and multiomics enhanced data integration, predictive insights, and treatment personalization. Fields like radiomics, genomics, and proteomics improved diagnostics and guided therapy. For instance, the “AI radiomics, genomics, oncopathomics, and surgomics project” combined radiomics and genomics for surgical decision-making, enabling preoperative, intraoperative, and postoperative interventions. AI applications in case reports predicted conditions like postoperative delirium and monitored cancer progression using genomic and imaging data. AI and multiomics enable standardized data analysis, dynamic updates, and predictive modeling in case reports. Traditional reports often lack objectivity, but AI enhances reproducibility and decision-making by processing large datasets. Challenges include data standardization, biases, and ethical concerns. Overcoming these barriers is vital for optimizing AI applications and advancing personalized medicine. AI and multiomics integration is revolutionizing clinical research and practice. Standardizing data reporting and addressing challenges in ethics and data quality will unlock their full potential. Emphasizing collaboration and transparency is essential for leveraging these tools to improve patient care and scientific communication.

Predicting overall survival in glioblastoma patients using machine learning: an analysis of treatment efficacy and patient prognosis

Introduction

Glioblastoma (GBM), the most aggressive primary brain tumor, poses a significant challenge in predicting patient survival due to its heterogeneity and resistance to treatment. Accurate survival prediction is essential for optimizing treatment strategies and improving clinical outcomes.

Methods

This study utilized metadata from 135 GBM patients, including demographic, clinical, and molecular variables such as age, Karnofsky Performance Status (KPS), MGMT promoter methylation, and EGFR amplification. Six machine learning models-XGBoost, Random Forests, Support Vector Machines, Artificial Neural Networks, Extra Trees Regressor, and K- Nearest Neighbors-were employed to classify patients into predefined survival categories. Data preprocessing included label encoding for categorical variables and MinMax scaling for numerical features. Model performance was assessed using ROC-AUC and accuracy metrics, with hyperparameters optimized through grid search.

Results

XGBoost demonstrated the highest predictive accuracy, achieving a mean ROC-AUC of 0.90 and an accuracy of 0.78. Ensemble models outperformed simpler classifiers, emphasizing the predictive value of metadata. The models identified key prognostic markers, including MGMT promoter methylation and KPS, as significant contributors to survival prediction.

Conclusions

The application of machine learning to GBM metadata offers a robust approach to predicting patient survival. The study highlights the potential of ML models to enhance clinical decision-making and contribute to personalized treatment strategies, with a focus on accuracy, reliability, and interpretability.

Intraplaque haemorrhage quantification and molecular characterisation using attention based multiple instance learning

Intraplaque haemorrhage (IPH) represents a critical feature of plaque vulnerability as it is robustly associated with adverse cardiovascular events, including stroke and myocardial infarction. How IPH drives plaque instability is unknown. However, its identification and quantification in atherosclerotic plaques is currently performed manually, with high interobserver variability, limiting its accurate assessment in large cohorts. Leveraging the Athero-Express biobank, an ongoing study comprising a comprehensive dataset of histological, transcriptional, and clinical information from 2,595 carotid endarterectomy patients, we developed an attention-based additive multiple instance learning (MIL) framework to automate the detection and quantification of IPH across whole-slide images of nine distinct histological stains. We demonstrate that routinely available Haematoxylin and Eosin (H&E) staining outperformed all other plaque relevant Immunohistochemistry (IHC) stains tested (AUROC = 0.86), underscoring its utility in quantifying IPH. When combining stains through ensemble models, we see that H&E + CD68 (a macrophage marker) as well as H&E + Verhoeff-Van Gieson elastic fibers staining (EVG) leads to a substantial improvement (AUROC = 0.92). Using our model, we could derive IPH area from the MIL-derived patch-level attention scores, enabling not only classification but precise localisation and quantification of IPH area in each plaque, facilitating downstream analyses of its association and cellular composition with clinical outcomes. By doing so, we demonstrate that IPH presence and area are the most significant predictors of both preoperative symptom presentation and major adverse cardiovascular events (MACE), outperforming manual scoring methods. Automating IPH detection also allowed us to characterise IPH on a molecular level at scale. Pairing IPH measurements with single-cell transcriptomic analyses revealed key molecular pathways involved in IPH, including TNF-α signalling, extracellular matrix remodelling and the presence of foam cells. This study represents the largest effort in the cardiovascular field to integrate digital pathology, machine learning, and molecular data to predict and characterize IPH which leads to better understanding how it drives symptoms and MACE. Our model provides a scalable, interpretable, and reproducible method for plaque phenotyping, enabling the derivation of plaque phenotypes for predictive modelling of MACE outcomes.

C. S, Devkota HP, Khadka D. Immune Modulation and Immunotherapy in Solid Tumors: Mechanisms of Resistance and Potential Therapeutic Strategies

Understanding the modulation of specific immune cells within the tumor microenvironment (TME) offers new hope in cancer treatments, especially in cancer immunotherapies. In recent years, immune modulation and resistance to immunotherapy have become critical challenges in cancer treatments. However, novel strategies for immune modulation have emerged as promising approaches for oncology due to the vital roles of the immunomodulators in regulating tumor progression and metastasis and modulating immunological responses to standard of care in cancer treatments. With the progress in immuno-oncology, a growing number of novel immunomodulators and mechanisms are being uncovered, offering the potential for enhanced clinical immunotherapy in the near future. Thus, gaining a comprehensive understanding of the broader context is essential. Herein, we particularly summarize the paradoxical role of tumor-related immune cells, focusing on how targeted immune cells and their actions are modulated by immunotherapies to overcome immunotherapeutic resistance in tumor cells. We also highlight the molecular mechanisms employed by tumors to evade the long-term effects of immunotherapeutic agents, rendering them ineffective.

Immunotherapy for advanced-stage squamous cell lung cancer: the state of the art and outstanding questions

Immune-checkpoint inhibitors (ICIs) have transformed the treatment paradigm for advanced-stage squamous non-small-cell lung cancer (LUSC), a histological subtype associated with inferior outcomes compared with lung adenocarcinoma. However, only a subset of patients derive durable clinical benefit. In the first-line setting, multiple ICI regimens are available, including anti-PD-(L)1 antibodies as monotherapy, in combination with chemotherapy, or with an anti-CTLA4 antibody with or without chemotherapy. Several important questions persist regarding the optimal regimen for individual patients, particularly how to identify patients who might benefit from adding chemotherapy and/or anti-CTLA4 antibodies to anti-PD-(L)1 antibodies. An urgent need exists for predictive biomarkers beyond PD-L1 to better guide precision oncology approaches. Deeper knowledge of the underlying molecular biology of LUSC and its implications for response to ICIs will be important in this regard. Integration of this knowledge into multi-omics methods coupled with artificial intelligence might enable the development of more robust biomarkers. Finally, several novel therapeutic strategies, including novel ICIs, bispecific antibodies and personalized cancer vaccines, are emerging. Addressing these unresolved questions through innovative clinical trials and translational research will be crucial to further improving the outcomes of patients with LUSC. In this Review, we provide a comprehensive overview of current immunotherapeutic approaches, unresolved challenges and emerging strategies for patients with LUSC.

Intricacies of human-AI interaction in dynamic decision-making for precision oncology

AI decision support systems can assist clinicians in planning adaptive treatment strategies that can dynamically react to individuals' cancer progression for effective personalized care. However, AI's imperfections can lead to suboptimal therapeutics if clinicians over or under rely on AI. To investigate such collaborative decision-making process, we conducted a Human-AI interaction study on response-adaptive radiotherapy for non-small cell lung cancer and hepatocellular carcinoma. We investigated two levels of collaborative behavior: model-agnostic and model-specific; and found that Human-AI interaction is multifactorial and depends on the complex interrelationship between prior knowledge and preferences, patient's state, disease site, treatment modality, model transparency, and AI's learned behavior and biases. In summary, some clinicians may disregard AI recommendations due to skepticism; others will critically analyze AI recommendations on a case-by-case basis; clinicians will adjust their decisions if they find AI recommendations beneficial to patients; and clinician will disregard AI recommendations if deemed harmful or suboptimal and seek alternatives.

Exosomes in cancer diagnosis based on the Latest Evidence: Where are We?

Exosomes are small extracellular vesicles (EVs) derived from various cellular sources and have emerged as favorable biomarkers for cancer diagnosis and prognosis. These vesicles contain a variety of molecular components, including nucleic acids, proteins, and lipids, which can provide valuable information for cancer detection, classification, and monitoring. However, the clinical application of exosomes faces significant challenges, primarily related to the standardization and scalability of their use. In order to overcome these challenges, sophisticated methods such as liquid biopsy and imaging are being combined to augment the diagnostic capabilities of exosomes. Additionally, a deeper understanding of the interaction between exosomes and immune system components within the tumor microenvironment (TME) is essential. This review discusses the biogenesis and composition of exosomes, addresses the current challenges in their clinical translation, and highlights recent technological advancements and integrative approaches that support the role of exosomes in cancer diagnosis and prognosis.

AI and ML-based risk assessment of chemicals: predicting carcinogenic risk from chemical-induced genomic instability

Chemical risk assessment plays a pivotal role in safeguarding public health and environmental safety by evaluating the potential hazards and risks associated with chemical exposures. In recent years, the convergence of artificial intelligence (AI), machine learning (ML), and omics technologies has revolutionized the field of chemical risk assessment, offering new insights into toxicity mechanisms, predictive modeling, and risk management strategies. This perspective review explores the synergistic potential of AI/ML and omics in deciphering clastogen-induced genomic instability for carcinogenic risk prediction. We provide an overview of key findings, challenges, and opportunities in integrating AI/ML and omics technologies for chemical risk assessment, highlighting successful applications and case studies across diverse sectors. From predicting genotoxicity and mutagenicity to elucidating molecular pathways underlying carcinogenesis, integrative approaches offer a comprehensive framework for understanding chemical exposures and mitigating associated health risks. Future perspectives for advancing chemical risk assessment and cancer prevention through data integration, advanced machine learning techniques, translational research, and policy implementation are discussed. By implementing the predictive capabilities of AI/ML and omics technologies, researchers and policymakers can enhance public health protection, inform regulatory decisions, and promote sustainable development for a healthier future.

Artificial Intelligence-Driven Computational Approaches in the Development of Anticancer Drugs

The integration of AI has revolutionized cancer drug development, transforming the landscape of drug discovery through sophisticated computational techniques. AI-powered models and algorithms have enhanced computer-aided drug design (CADD), offering unprecedented precision in identifying potential anticancer compounds. Traditionally, cancer drug design has been a complex, resource-intensive process, but AI introduces new opportunities to accelerate discovery, reduce costs, and optimize efficiency. This manuscript delves into the transformative applications of AI-driven methodologies in predicting and developing anticancer drugs, critically evaluating their potential to reshape the future of cancer therapeutics while addressing their challenges and limitations.

Cancer Biomarkers and Precision Oncology: A Review of Recent Trends and Innovations

The discovery of cancer-specific biomarkers has resulted in major advancements in the field of cancer diagnostics and therapeutics, therefore significantly lowering cancer-related morbidity and mortality. Cancer biomarkers can be generally classified as prognostic biomarkers that predict specific disease outcomes and predictive biomarkers that predict disease response to targeted therapeutic interventions. As research in the area of predictive biomarkers continues to grow, precision medicine becomes far more integrated in cancer treatment. This article presents a general overview on the most recent advancements in the area of cancer biomarkers, immunotherapy, artificial intelligence, and pharmacogenomics of the Middle East.

Precision oncology platforms: practical strategies for genomic database utilization in cancer treatment

In recent years, the expansion of molecularly targeted cancer therapies has significantly advanced precision oncology. Parallel developments in next-generation sequencing (NGS) technologies have also improved precision oncology applications, making genomic analysis of tumors more affordable and accessible. Targeted NGS panels now enable the rapid identification of diverse actionable mutations, requiring clinicians to efficiently assess the predictive value of cancer biomarkers for specific treatments. The urgency for timely and accurate decision-making in oncology emphasizes the importance of reliable precision oncology software. Online clinical decision-making tools and associated cancer databases have been designed by consolidating genomic data into standardized, accessible formats. These new platforms are highly integrated and crucial for identifying actionable somatic genomic biomarkers essential for tumor survival, determining corresponding drug targets, and selecting appropriate treatments based on the mutational profile of each patient's tumor. To help oncologists and translational cancer researchers unfamiliar with these tools, we review the utility, accuracy, and comprehensiveness of several commonly used precision medicine software options currently available. Our analysis categorized selected genomic databases based on their primary content, utility, and how well they provide practical guidance for interpreting somatic biomarker data. We identified several comprehensive, mostly open-access platforms that are easy to use for genetic biomarker searches, each with unique features and limitations. Among the precision oncology tools we evaluated, we found MyCancerGenome and OncoKB to be the first choice, offering comprehensive, accurate up-to-date information on the clinical significance of somatic mutations. To illustrate the application of these precision oncology tools in clinical settings, we evaluated three case studies to see how use of the platforms could have influenced treatment planning. Most of the precision oncology software evaluated could be easily streamlined into clinical workflows to provide updated information on approved drugs and clinical trials related the actionable mutations detected. Some platforms were very intuitive and easy to use, while others, often developed in smaller academic settings, were more difficult to navigate and may not be updated consistently. Future enhancements, incorporating artificial intelligence algorithms, are likely to improve integration of the platforms with diverse big data sources, enabling more accurate predictions of potential therapeutic responses.

Relationship between EZH2 expression and prognosis of patients with hepatocellular carcinoma using a pathomics predictive model

Background

Enhancer of zeste 2 polycomb repressive complex 2 subunit (EZH2) is overexpressed in hepatocellular carcinoma, promoting tumorigenesis and correlating with poor prognosis. Traditional histopathological examinations are insufficient to accurately predict hepatocellular carcinoma (HCC) survival; however, pathomics models can predict EZH2 expression and HCC prognosis. This study aimed to investigate the relationship between pathomics features and EZH2 expression for predicting overall survival of patients with HCC.

Methods

We analyzed 267 patients with HCC from the Cancer Genome Atlas database, with available pathological images and gene expression data. RNA sequencing data were divided into high and low EZH2 expression groups for prognosis and survival analysis. Pathological image features were screened using mRMR_RFE. A pathological model was constructed using a gradient boosting machine (GBM) algorithm, and efficiency evaluation and survival analysis of the model were performed. The R package "survminer" took the pathomics score (PS) cutoff value of 0.4628 to divide the patients into two groups: high and low PS expression. Survival analyses included Kaplan-Meier curve analysis, univariate and multivariate Cox regression analyses, and interaction tests. Potential pathomechanisms were explored through enrichment, differential, immune cell infiltration abundance, and gene mutation analyses.

Result

EZH2 was highly expressed in tumor samples but poorly expressed in normal tissue samples. Univariate and multivariate Cox regression analyses revealed that EZH2 was an independent risk factor for HCC (hazard ratio [HR], 2.792 and 3.042, respectively). Seven imaging features were selected to construct a pathomics model to predict EZH2. Decision curve analysis showed that the model had high clinical utility. Multivariate Cox regression analysis showed that high PS expression was an independent risk factor for HCC prognosis (HR, 2.446). The Kaplan-Meier curve showed that high PS expression was a risk factor for overall survival.

Conclusion

EZH2 expression can affect the prognosis of patients with liver cancer. Our pathological model could predict EZH2 expression and prognosis of patients with HCC with high accuracy and robustness, making it a new and potentially valuable tool.

Contemporary Update on Clinical and Experimental Prostate Cancer Biomarkers: A Multi-Omics-Focused Approach to Detection and Risk Stratification

Prostate cancer remains a significant health challenge, being the most prevalent non-cutaneous cancer in men worldwide. This review discusses the critical advancements in biomarker discovery using single-omics and multi-omics approaches. Multi-omics, integrating genomic, transcriptomic, proteomic, metabolomic, and epigenomic data, offers a comprehensive understanding of the molecular heterogeneity of prostate cancer, leading to the identification of novel biomarkers and therapeutic targets. This holistic approach not only enhances the specificity and sensitivity of prostate cancer detection but also supports the development of personalized treatment strategies. Key studies highlighted include the identification of novel genes, genetic mutations, peptides, metabolites, and potential biomarkers through multi-omics analyses, which have shown promise in improving prostate cancer management. The integration of multi-omics in clinical practice can potentially revolutionize prostate cancer prognosis and treatment, paving the way for precision medicine. This review underscores the importance of continued research and the application of multi-omics to overcome current challenges in prostate cancer diagnosis and therapy.

Artificial intelligence improves the diagnosis of human leukocyte antigen (HLA)-B27-negative axial spondyloarthritis based on multi-sequence magnetic resonance imaging and clinical features

Background

Axial spondyloarthritis (axSpA) is frequently diagnosed late, particularly in human leukocyte antigen (HLA)-B27-negative patients, resulting in a missed opportunity for optimal treatment. This study aimed to develop an artificial intelligence (AI) tool, termed NegSpA-AI, using sacroiliac joint (SIJ) magnetic resonance imaging (MRI) and clinical SpA features to improve the diagnosis of axSpA in HLA-B27-negative patients.

Methods

We retrospectively included 454 HLA-B27-negative patients with rheumatologist-diagnosed axSpA or other diseases (non-axSpA) from the Third Affiliated Hospital of Southern Medical University and Nanhai Hospital between January 2010 and August 2021. They were divided into a training set (n=328) for 5-fold cross-validation, an internal test set (n=72), and an independent external test set (n=54). To construct a prospective test set, we further enrolled 87 patients between September 2021 and August 2023 from the Third Affiliated Hospital of Southern Medical University. MRI techniques employed included T1-weighted (T1W), T2-weighted (T2W), and fat-suppressed (FS) sequences. We developed NegSpA-AI using a deep learning (DL) network to differentiate between axSpA and non-axSpA at admission. Furthermore, we conducted a reader study involving 4 radiologists and 2 rheumatologists to evaluate and compare the performance of independent and AI-assisted clinicians.

Results

NegSpA-AI demonstrated superior performance compared to the independent junior rheumatologist (≤5 years of experience), achieving areas under the curve (AUCs) of 0.878 [95% confidence interval (CI): 0.786-0.971], 0.870 (95% CI: 0.771-0.970), and 0.815 (95% CI: 0.714-0.915) on the internal, external, and prospective test sets, respectively. The assistance of NegSpA-AI promoted discriminating accuracy, sensitivity, and specificity of independent junior radiologists by 7.4-11.5%, 1.0-13.3%, and 7.4-20.6% across the 3 test sets (all P<0.05). On the prospective test set, AI assistance also improved the diagnostic accuracy, sensitivity, and specificity of independent junior rheumatologists by 7.7%, 7.7%, and 6.9%, respectively (all P<0.01).

Conclusions

The proposed NegSpA-AI effectively improves radiologists' interpretations of SIJ MRI and rheumatologists' diagnoses of HLA-B27-negative axSpA.

A joint physics and radiobiology DREAM team vision - Towards better response prediction models to advance radiotherapy

Radiotherapy developed empirically through experience balancing tumour control and normal tissue toxicities. Early simple mathematical models formalized this practical knowledge and enabled effective cancer treatment to date. Remarkable advances in technology, computing, and experimental biology now create opportunities to incorporate this knowledge into enhanced computational models. The ESTRO DREAM (Dose Response, Experiment, Analysis, Modelling) workshop brought together experts across disciplines to pursue the vision of personalized radiotherapy for optimal outcomes through advanced modelling. The ultimate vision is leveraging quantitative models dynamically during therapy to ultimately achieve truly adaptive and biologically guided radiotherapy at the population as well as individual patient-based levels. This requires the generation of models that inform response-based adaptations, individually optimized delivery and enable biological monitoring to provide decision support to clinicians. The goal is expanding to models that can drive the realization of personalized therapy for optimal outcomes. This position paper provides their propositions that describe how innovations in biology, physics, mathematics, and data science including AI could inform models and improve predictions. It consolidates the DREAM team's consensus on scientific priorities and organizational requirements. Scientifically, it stresses the need for rigorous, multifaceted model development, comprehensive validation and clinical applicability and significance. Organizationally, it reinforces the prerequisites of interdisciplinary research and collaboration between physicians, medical physicists, radiobiologists, and computational scientists throughout model development. Solely by a shared understanding of clinical needs, biological mechanisms, and computational methods, more informed models can be created. Future research environment and support must facilitate this integrative method of operation across multiple disciplines.

Omics approaches open new horizons in major depressive disorder: from biomarkers to precision medicine

Major depressive disorder (MDD) is a recurrent episodic mood disorder that represents the third leading cause of disability worldwide. In MDD, several factors can simultaneously contribute to its development, which complicates its diagnosis. According to practical guidelines, antidepressants are the first-line treatment for moderate to severe major depressive episodes. Traditional treatment strategies often follow a one-size-fits-all approach, resulting in suboptimal outcomes for many patients who fail to experience a response or recovery and develop the so-called "therapy-resistant depression". The high biological and clinical inter-variability within patients and the lack of robust biomarkers hinder the finding of specific therapeutic targets, contributing to the high treatment failure rates. In this frame, precision medicine, a paradigm that tailors medical interventions to individual characteristics, would help allocate the most adequate and effective treatment for each patient while minimizing its side effects. In particular, multi-omic studies may unveil the intricate interplays between genetic predispositions and exposure to environmental factors through the study of epigenomics, transcriptomics, proteomics, metabolomics, gut microbiomics, and immunomics. The integration of the flow of multi-omic information into molecular pathways may produce better outcomes than the current psychopharmacological approach, which targets singular molecular factors mainly related to the monoamine systems, disregarding the complex network of our organism. The concept of system biomedicine involves the integration and analysis of enormous datasets generated with different technologies, creating a "patient fingerprint", which defines the underlying biological mechanisms of every patient. This review, centered on precision medicine, explores the integration of multi-omic approaches as clinical tools for prediction in MDD at a single-patient level. It investigates how combining the existing technologies used for diagnostic, stratification, prognostic, and treatment-response biomarkers discovery with artificial intelligence can improve the assessment and treatment of MDD.

Data-driven evolution of water quality models: An in-depth investigation of innovative outlier detection approaches-A case study of Irish Water Quality Index (IEWQI) model

Recently, there has been a significant advancement in the water quality index (WQI) models utilizing data-driven approaches, especially those integrating machine learning and artificial intelligence (ML/AI) technology. Although, several recent studies have revealed that the data-driven model has produced inconsistent results due to the data outliers, which significantly impact model reliability and accuracy. The present study was carried out to assess the impact of data outliers on a recently developed Irish Water Quality Index (IEWQI) model, which relies on data-driven techniques. To the author's best knowledge, there has been no systematic framework for evaluating the influence of data outliers on such models. For the purposes of assessing the outlier impact of the data outliers on the water quality (WQ) model, this was the first initiative in research to introduce a comprehensive approach that combines machine learning with advanced statistical techniques. The proposed framework was implemented in Cork Harbour, Ireland, to evaluate the IEWQI model's sensitivity to outliers in input indicators to assess the water quality. In order to detect the data outlier, the study utilized two widely used ML techniques, including Isolation Forest (IF) and Kernel Density Estimation (KDE) within the dataset, for predicting WQ with and without these outliers. For validating the ML results, the study used five commonly used statistical measures. The performance metric (R2) indicates that the model performance improved slightly (R2 increased from 0.92 to 0.95) in predicting WQ after removing the data outlier from the input. But the IEWQI scores revealed that there were no statistically significant differences among the actual values, predictions with outliers, and predictions without outliers, with a 95 % confidence interval at p < 0.05. The results of model uncertainty also revealed that the model contributed <1 % uncertainty to the final assessment results for using both datasets (with and without outliers). In addition, all statistical measures indicated that the ML techniques provided reliable results that can be utilized for detecting outliers and their impacts on the IEWQI model. The findings of the research reveal that although the data outliers had no significant impact on the IEWQI model architecture, they had moderate impacts on the rating schemes' of the model. This finding indicated that detecting the data outliers could improve the accuracy of the IEWQI model in rating WQ as well as be helpful in mitigating the model eclipsing problem. In addition, the results of the research provide evidence of how the data outliers influenced the data-driven model in predicting WQ and reliability, particularly since the study confirmed that the IEWQI model's could be effective for accurately rating WQ despite the presence of the data outliers in the input. It could occur due to the spatio-temporal variability inherent in WQ indicators. However, the research assesses the influence of data input outliers on the IEWQI model and underscores important areas for future investigation. These areas include expanding temporal analysis using multi-year data, examining spatial outlier patterns, and evaluating detection methods. Moreover, it is essential to explore the real-world impacts of revised rating categories, involve stakeholders in outlier management, and fine-tune model parameters. Analysing model performance across varying temporal and spatial resolutions and incorporating additional environmental data can significantly enhance the accuracy of WQ assessment. Consequently, this study offers valuable insights to strengthen the IEWQI model's robustness and provides avenues for enhancing its utility in broader WQ assessment applications. Moreover, the study successfully adopted the framework for evaluating how data input outliers affect the data-driven model, such as the IEWQI model. The current study has been carried out in Cork Harbour for only a single year of WQ data. The framework should be tested across various domains for evaluating the response of the IEWQI model's in terms of the spatio-temporal resolution of the domain. Nevertheless, the study recommended that future research should be conducted to adjust or revise the IEWQI model's rating schemes and investigate the practical effects of data outliers on updated rating categories. However, the study provides potential recommendations for enhancing the IEWQI model's adaptability and reveals its effectiveness in expanding its applicability in more general WQ assessment scenarios.

Intricacies of Human-AI Interaction in Dynamic Decision-Making for Precision Oncology: A Case Study in Response-Adaptive Radiotherapy

Background

Adaptive treatment strategies that can dynamically react to individual cancer progression can provide effective personalized care. Longitudinal multi-omics information, paired with an artificially intelligent clinical decision support system (AI-CDSS) can assist clinicians in determining optimal therapeutic options and treatment adaptations. However, AI-CDSS is not perfectly accurate, as such, clinicians' over/under reliance on AI may lead to unintended consequences, ultimately failing to develop optimal strategies. To investigate such collaborative decision-making process, we conducted a Human-AI interaction case study on response-adaptive radiotherapy (RT).

Methods

We designed and conducted a two-phase study for two disease sites and two treatment modalities-adaptive RT for non-small cell lung cancer (NSCLC) and adaptive stereotactic body RT for hepatocellular carcinoma (HCC)-in which clinicians were asked to consider mid-treatment modification of the dose per fraction for a number of retrospective cancer patients without AI-support (Unassisted Phase) and with AI-assistance (AI-assisted Phase). The AI-CDSS graphically presented trade-offs in tumor control and the likelihood of toxicity to organs at risk, provided an optimal recommendation, and associated model uncertainties. In addition, we asked for clinicians' decision confidence level and trust level in individual AI recommendations and encouraged them to provide written remarks. We enrolled 13 evaluators (radiation oncology physicians and residents) from two medical institutions located in two different states, out of which, 4 evaluators volunteered in both NSCLC and HCC studies, resulting in a total of 17 completed evaluations (9 NSCLC, and 8 HCC). To limit the evaluation time to under an hour, we selected 8 treated patients for NSCLC and 9 for HCC, resulting in a total of 144 sets of evaluations (72 from NSCLC and 72 from HCC). Evaluation for each patient consisted of 8 required inputs and 2 optional remarks, resulting in up to a total of 1440 data points.

Results

AI-assistance did not homogeneously influence all experts and clinical decisions. From NSCLC cohort, 41 (57%) decisions and from HCC cohort, 34 (47%) decisions were adjusted after AI assistance. Two evaluations (12%) from the NSCLC cohort had zero decision adjustments, while the remaining 15 (88%) evaluations resulted in at least two decision adjustments. Decision adjustment level positively correlated with dissimilarity in decision-making with AI [NSCLC: ρ = 0.53 ( p < 0.001); HCC: ρ = 0.60 ( p < 0.001)] indicating that evaluators adjusted their decision closer towards AI recommendation. Agreement with AI-recommendation positively correlated with AI Trust Level [NSCLC: ρ = 0.59 ( p < 0.001); HCC: ρ = 0.7 ( p < 0.001)] indicating that evaluators followed AI's recommendation if they agreed with that recommendation. The correlation between decision confidence changes and decision adjustment level showed an opposite trend [NSCLC: ρ = -0.24 ( p = 0.045), HCC: ρ = 0.28 ( p = 0.017)] reflecting the difference in behavior due to underlying differences in disease type and treatment modality. Decision confidence positively correlated with the closeness of decisions to the standard of care (NSCLC: 2 Gy/fx; HCC: 10 Gy/fx) indicating that evaluators were generally more confident in prescribing dose fractionations more similar to those used in standard clinical practice. Inter-evaluator agreement increased with AI-assistance indicating that AI-assistance can decrease inter-physician variability. The majority of decisions were adjusted to achieve higher tumor control in NSCLC and lower normal tissue complications in HCC. Analysis of evaluators' remarks indicated concerns for organs at risk and RT outcome estimates as important decision-making factors.

Conclusions

Human-AI interaction depends on the complex interrelationship between expert's prior knowledge and preferences, patient's state, disease site, treatment modality, model transparency, and AI's learned behavior and biases. The collaborative decision-making process can be summarized as follows: (i) some clinicians may not believe in an AI system, completely disregarding its recommendation, (ii) some clinicians may believe in the AI system but will critically analyze its recommendations on a case-by-case basis; (iii) when a clinician finds that the AI recommendation indicates the possibility for better outcomes they will adjust their decisions accordingly; and (iv) When a clinician finds that the AI recommendation indicate a worse possible outcome they will disregard it and seek their own alternative approach.

Machine Learning and Bias in Medical Imaging: Opportunities and Challenges

Bias in health care has been well documented and results in disparate and worsened outcomes for at-risk groups. Medical imaging plays a critical role in facilitating patient diagnoses but involves multiple sources of bias including factors related to access to imaging modalities, acquisition of images, and assessment (ie, interpretation) of imaging data. Machine learning (ML) applied to diagnostic imaging has demonstrated the potential to improve the quality of imaging-based diagnosis and the precision of measuring imaging-based traits. Algorithms can leverage subtle information not visible to the human eye to detect underdiagnosed conditions or derive new disease phenotypes by linking imaging features with clinical outcomes, all while mitigating cognitive bias in interpretation. Importantly, however, the application of ML to diagnostic imaging has the potential to either reduce or propagate bias. Understanding the potential gain as well as the potential risks requires an understanding of how and what ML models learn. Common risks of propagating bias can arise from unbalanced training, suboptimal architecture design or selection, and uneven application of models. Notwithstanding these risks, ML may yet be applied to improve gain from imaging across all 3A's (access, acquisition, and assessment) for all patients. In this review, we present a framework for understanding the balance of opportunities and challenges for minimizing bias in medical imaging, how ML may improve current approaches to imaging, and what specific design considerations should be made as part of efforts to maximize the quality of health care for all.

liquid biopsy holds a promising approach for the early detection of cancer: Current information and future perspectives

Cancer is becoming a global pandemic, and its occurrence is increasing rapidly, putting a strain on people's families, health systems, and finances, in addition to their physical, mental, and emotional well-being. Many cancer types lack screening programs, and many people at high risk of developing cancer do not follow recommended medical screening regimens because of the nature of currently available screening tests and other compliance issues, despite cancer being the second leading cause of death worldwide. Furthermore, a lot of liquid biopsy methods for early cancer screening are not sensitive enough to catch cancer early. Cancer treatment costs increase with the time it takes to diagnose the disease; therefore, early detection is essential to enhance the quality of life and survival rates. The current status of the liquid biopsy sector is examined in this paper.

Breast Imaging Physics in Mammography (Part II)

One of the most frequently detected neoplasms in women in Italy is breast cancer, for which high-sensitivity diagnostic techniques are essential for early diagnosis in order to minimize mortality rates. As addressed in Part I of this work, we have seen how conditions such as high glandular density or limitations related to mammographic sensitivity have driven the optimization of technology and the use of increasingly advanced and specific diagnostic methodologies. While the first part focused on analyzing the use of a mammography machine from a physical and dosimetric perspective, in this paper, we will examine other techniques commonly used in breast imaging: contrast-enhanced mammography, digital breast tomosynthesis, radio imaging, and include some notes on image processing. We will also explore the differences between these various techniques to provide a comprehensive overview of breast lesion detection techniques. We will examine the strengths and weaknesses of different diagnostic modalities and observe how, with the implementation of improvements over time, increasingly effective diagnoses can be achieved.

Breast Imaging Physics in Mammography (Part I)

Breast cancer is the most frequently diagnosed neoplasm in women in Italy. There are several risk factors, but thanks to screening and increased awareness, most breast cancers are diagnosed at an early stage when surgical treatment can most often be conservative and the adopted therapy is more effective. Regular screening is essential but advanced technology is needed to achieve quality diagnoses. Mammography is the gold standard for early detection of breast cancer. It is a specialized technique for detecting breast cancer and, thus, distinguishing normal tissue from cancerous breast tissue. Mammography techniques are based on physical principles: through the proper use of X-rays, the structures of different tissues can be observed. This first part of the paper attempts to explain the physical principles used in mammography. In particular, we will see how a mammogram is composed and what physical principles are used to obtain diagnostic images.