Oculomics for sarcopenia prediction: a machine learning approach toward predictive, preventive, and personalized medicine

Development and validation of machine learning models for predicting low muscle mass in patients with obesity and diabetes

BACKGROUND AND AIMS

Low muscle mass (LMM) is a critical complication in patients with obesity and diabetes, exacerbating metabolic and cardiovascular risks. Novel obesity indices, such as the body roundness index (BRI), conicity index, and relative fat mass, have shown promise for assessing body composition. This study aimed to investigate the associations of these indices with LMM and to develop machine learning models for accurate and accessible LMM prediction.

METHOD

Data from NHANES 2011-2018 (n = 2,176) were analyzed. Obesity was defined by body fat percentage, and LMM was determined using skeletal muscle mass index thresholds adjusted for BMI. Predictive models were developed using logistic regression, random forest, and other algorithms, with feature selection via LASSO regression. Validation included NHANES 2005-2006 data (n = 310). Model performance was evaluated using AUROC, Brier scores, and SHapley Additive exPlanations (SHAP) for feature importance.

RESULTS

BRI was independently associated with LMM (odds ratio 1.39, 95% confidence interval 1.22-1.58; P < 0.001). Eight features were included in the random forest model, which achieved excellent discrimination (AUROC = 0.721 in the validation set) and calibration (Brier score = 0.184). Feature importance analysis highlighted BRI, creatinine, race, age, and HbA1c as key contributors to the model's predictive performance. SHAP analysis emphasized BRI's role in predicting LMM. An online prediction tool was developed.

CONCLUSIONS

BRI is a significant predictor of LMM in patients with obesity and diabetes. The random forest model demonstrated strong performance and offers a practical tool for early LMM detection, supporting clinical decision-making and personalized interventions.

Oculomics approaches using retinal imaging to predict mental health disorders: a systematic review and meta-analysis

OBJECTIVE

This meta-analysis evaluated the diagnostic performance of oculomics approaches, including deep learning, machine learning, and logistic regression models, in detecting major mental disorders using retinal imaging.

METHODS

A systematic review identified 11 studies for inclusion. Study quality was assessed using the QUADAS-2 tool, revealing a high risk of bias, particularly in patient selection and index test design. Pooled sensitivity and specificity were estimated using random-effects models, and diagnostic performance was evaluated through a summary receiver operating characteristic curve.

RESULTS

The analysis included 13 diagnostic models across 11 studies, covering major depressive disorder, bipolar disorder, schizophrenia, obsessive-compulsive disorder, and autism spectrum disorder using color fundus photography, and optical coherence tomography (OCT), and OCT angiography. The pooled sensitivity was 0.89 (95% CI: 0.78-0.94), and specificity was 0.87 (95% CI: 0.74-0.95). The pooled area under the curve was 0.904, indicating high diagnostic accuracy. However, all studies exhibited a high risk of bias, primarily due to case-control study designs, lack of external validation, and selection bias in 77% of studies. Some models showed signs of overfitting, likely due to small sample sizes, insufficient validation, or dataset limitations. Additionally, no distinct retinal patterns specific to mental disorders were identified.

CONCLUSION

While oculomics demonstrates potential for detecting mental disorders through retinal imaging, significant methodological limitations, including high bias, overfitting risks, and the absence of disease-specific retinal biomarkers, limit its current clinical applicability. Future research should focus on large-scale, externally validated studies with prospective designs to establish reliable retinal markers for psychiatric diagnosis.

Oculomics: Current concepts and evidence

The eye provides novel insights into general health, as well as pathogenesis and development of systemic diseases. In the past decade, growing evidence has demonstrated that the eye's structure and function mirror multiple systemic health conditions, especially in cardiovascular diseases, neurodegenerative disorders, and kidney impairments. This has given rise to the field of oculomics-the application of ophthalmic biomarkers to understand mechanisms, detect and predict disease. The development of this field has been accelerated by three major advances: 1) the availability and widespread clinical adoption of high-resolution and non-invasive ophthalmic imaging ("hardware"); 2) the availability of large studies to interrogate associations ("big data"); 3) the development of novel analytical methods, including artificial intelligence (AI) ("software"). Oculomics offers an opportunity to enhance our understanding of the interplay between the eye and the body, while supporting development of innovative diagnostic, prognostic, and therapeutic tools. These advances have been further accelerated by developments in AI, coupled with large-scale linkage datasets linking ocular imaging data with systemic health data. Oculomics also enables the detection, screening, diagnosis, and monitoring of many systemic health conditions. Furthermore, oculomics with AI allows prediction of the risk of systemic diseases, enabling risk stratification, opening up new avenues for prevention or individualized risk prediction and prevention, facilitating personalized medicine. In this review, we summarise current concepts and evidence in the field of oculomics, highlighting the progress that has been made, remaining challenges, and the opportunities for future research.

Multimodal Artificial Intelligence Models Predicting Glaucoma Progression Using Electronic Health Records and Retinal Nerve Fiber Layer Scans

Purpose

The purpose of this study was to develop models that predict which patients with glaucoma will progress to require surgery, combining structured data from electronic health records (EHRs) and retinal fiber layer optical coherence tomography (RNFL OCT) scans.

Methods

EHR data (demographics and clinical eye examinations) and RNFL OCT scans were identified for patients with glaucoma from an academic center (2008-2023). Comparing the novel TabNet deep learning architecture to a baseline XGBoost model, we trained and evaluated single modality models using either EHR or RNFL features, as well as fusion models combining both EHR and RNFL features as inputs, to predict glaucoma surgery within 12 months (binary).

Results

We had 1472 patients with glaucoma who were included in this study, of which 29.9% (N = 367) progressed to glaucoma surgery. The TabNet fusion model achieved the highest performance on the test set with an area under the receiver operating characteristic curve (AUROC) of 0.832, compared to the XGBoost fusion model (AUROC = 0.747). EHR only models performed with an AUROC of 0.764 and 0.720 for the deep learning model and XGBoost models, respectively. RNFL only models performed with an AUROC of 0.624 and 0.633 for the deep learning and XGBoost models, respectively.

Conclusions

Fusion models which integrate both RNFL with EHR data outperform models only utilizing one datatype or the other to predict glaucoma progression. The deep learning TabNet architecture demonstrated superior performance to traditional XGBoost models.

Translational Relevance

Prediction models that utilize the wealth of structured clinical and imaging data to predict glaucoma progression could form the basis of future clinical decision support tools to personalize glaucoma care.

Machine learning based on nutritional assessment to predict adverse events in older inpatients with possible sarcopenia

BACKGROUND

The accuracy of current tools for predicting adverse events in older inpatients with possible sarcopenia is still insufficient to develop individualized nutrition-related management strategies. The objectives were to develop a machine learning model based on nutritional assessment for the prediction of all-cause death and infectious complications.

METHODS

A cohort of older patients with possible sarcopenia (divided into training group [70%] and validation group [30%]) from 30 hospitals in 14 major cities in China was retrospectively analyzed. Clinical characteristics, laboratory examination, Nutritional risk Screening-2002 (NRS-2002) and mini-nutritional Assessment-Short form (MNA-SF) were used to construct machine learning models to predict in-hospital adverse events, including all-cause mortality and infectious complications. The applied algorithms included decision tree, random forest, gradient boosting machine (GBM), LightGBM, extreme gradient boosting and neural network. Model performance was assessed according to learning a series of learning metrics including area under the receiver operating characteristic curve (AUC) and accuracy.

RESULTS

Among 3 999 participants (mean age 75.89 years [SD 7.14]; 1 805 [45.1%] were female), 373 (9.7%) had adverse events, including 62 (1.6%) of in-hospital death and 330 (8.5%) of infectious complications. The decision tree model showed a better AUC of 0.7072 (95% CI 0.6558-0.7586) in the validation cohort, using the five most important variables (i.e., mobility, reduced food intake, white blood cell count, upper arm circumference, and hypoalbuminemia).

CONCLUSIONS

Machine learning prediction models are feasible and effective for identifying adverse events, and may be helpful to guide clinical nutrition decision-making in older inpatients with possible sarcopenia.

Application of ChatGPT-4 to oculomics: a cost-effective osteoporosis risk assessment to enhance management as a proof-of-principles model in 3PM

Background

Oculomics is an emerging medical field that focuses on the study of the eye to detect and understand systemic diseases. ChatGPT-4 is a highly advanced AI model with multimodal capabilities, allowing it to process text and statistical data. Osteoporosis is a chronic condition presenting asymptomatically but leading to fractures if untreated. Current diagnostic methods like dual X-ray absorptiometry (DXA) are costly and involve radiation exposure. This study aims to develop a cost-effective osteoporosis risk prediction tool using ophthalmological data and ChatGPT-4 based on oculomics, aligning with predictive, preventive, and personalized medicine (3PM) principles.

Working hypothesis and methods

We hypothesize that leveraging ophthalmological data (oculomics) combined with AI-driven regression models developed by ChatGPT-4 can significantly improve the predictive accuracy for osteoporosis risk. This integration will facilitate earlier detection, enable more effective preventive strategies, and support personalized treatment plans tailored to individual patients. We utilized DXA and ophthalmological data from the Korea National Health and Nutrition Examination Survey to develop and validate osteopenia and osteoporosis prediction models. Ophthalmological and demographic data were integrated into logistic regression analyses, facilitated by ChatGPT-4, to create prediction formulas. These models were then converted into calculator software through automated coding by ChatGPT-4.

Results

ChatGPT-4 automatically developed prediction models based on key predictors of osteoporosis and osteopenia included age, gender, weight, and specific ophthalmological conditions such as cataracts and early age-related macular degeneration, and successfully implemented a risk calculator tool. The oculomics-based models outperformed traditional methods, with area under the curve of the receiver operating characteristic values of 0.785 for osteopenia and 0.866 for osteoporosis in the validation set. The calculator demonstrated high sensitivity and specificity, providing a reliable tool for early osteoporosis screening.

Conclusions and expert recommendations in the framework of 3PM

This study illustrates the value of integrating ophthalmological data into multi-level diagnostics for osteoporosis, significantly improving the accuracy of health risk assessment and the identification of at-risk individuals. Aligned with the principles of 3PM, this approach fosters earlier detection and enables the development of individualized patient profiles, facilitating personalized and targeted treatment strategies. This study also highlights the potential of AI, specifically ChatGPT-4, in developing accessible, cost-effective, and radiation-free screening tools for advancing 3PM in clinical practice. Our findings emphasize the importance of a holistic approach, incorporating comprehensive health indices and interdisciplinary collaboration, to deliver personalized management plans. Preventive strategies should focus on lifestyle modifications and targeted interventions to enhance bone health, thereby preventing the progression of osteoporosis and contributing to overall patient well-being.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-024-00378-0.

Retina Fundus Photograph-Based Artificial Intelligence Algorithms in Medicine: A Systematic Review

We conducted a systematic review of research in artificial intelligence (AI) for retinal fundus photographic images. We highlighted the use of various AI algorithms, including deep learning (DL) models, for application in ophthalmic and non-ophthalmic (i.e., systemic) disorders. We found that the use of AI algorithms for the interpretation of retinal images, compared to clinical data and physician experts, represents an innovative solution with demonstrated superior accuracy in identifying many ophthalmic (e.g., diabetic retinopathy (DR), age-related macular degeneration (AMD), optic nerve disorders), and non-ophthalmic disorders (e.g., dementia, cardiovascular disease). There has been a significant amount of clinical and imaging data for this research, leading to the potential incorporation of AI and DL for automated analysis. AI has the potential to transform healthcare by improving accuracy, speed, and workflow, lowering cost, increasing access, reducing mistakes, and transforming healthcare worker education and training.

Oculomics: A Crusade Against the Four Horsemen of Chronic Disease

Chronic, non-communicable diseases present a major barrier to living a long and healthy life. In many cases, early diagnosis can facilitate prevention, monitoring, and treatment efforts, improving patient outcomes. There is therefore a critical need to make screening techniques as accessible, unintimidating, and cost-effective as possible. The association between ocular biomarkers and systemic health and disease (oculomics) presents an attractive opportunity for detection of systemic diseases, as ophthalmic techniques are often relatively low-cost, fast, and non-invasive. In this review, we highlight the key associations between structural biomarkers in the eye and the four globally leading causes of morbidity and mortality: cardiovascular disease, cancer, neurodegenerative disease, and metabolic disease. We observe that neurodegenerative disease is a particularly promising target for oculomics, with biomarkers detected in multiple ocular structures. Cardiovascular disease biomarkers are present in the choroid, retinal vasculature, and retinal nerve fiber layer, and metabolic disease biomarkers are present in the eyelid, tear fluid, lens, and retinal vasculature. In contrast, only the tear fluid emerged as a promising ocular target for the detection of cancer. The retina is a rich source of oculomics data, the analysis of which has been enhanced by artificial intelligence-based tools. Although not all biomarkers are disease-specific, limiting their current diagnostic utility, future oculomics research will likely benefit from combining data from various structures to improve specificity, as well as active design, development, and optimization of instruments that target specific disease signatures, thus facilitating differential diagnoses.

Machine-learning-based models to predict cardiovascular risk using oculomics and clinic variables in KNHANES

BACKGROUND

Recent researches have found a strong correlation between the triglyceride-glucose (TyG) index or the atherogenic index of plasma (AIP) and cardiovascular disease (CVD) risk. However, there is a lack of research on non-invasive and rapid prediction of cardiovascular risk. We aimed to develop and validate a machine-learning model for predicting cardiovascular risk based on variables encompassing clinical questionnaires and oculomics.

METHODS

We collected data from the Korean National Health and Nutrition Examination Survey (KNHANES). The training dataset (80% from the year 2008 to 2011 KNHANES) was used for machine learning model development, with internal validation using the remaining 20%. An external validation dataset from the year 2012 assessed the model's predictive capacity for TyG-index or AIP in new cases. We included 32122 participants in the final dataset. Machine learning models used 25 algorithms were trained on oculomics measurements and clinical questionnaires to predict the range of TyG-index and AIP. The area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1 score were used to evaluate the performance of our machine learning models.

RESULTS

Based on large-scale cohort studies, we determined TyG-index cut-off points at 8.0, 8.75 (upper one-third values), 8.93 (upper one-fourth values), and AIP cut-offs at 0.318, 0.34. Values surpassing these thresholds indicated elevated cardiovascular risk. The best-performing algorithm revealed TyG-index cut-offs at 8.0, 8.75, and 8.93 with internal validation AUCs of 0.812, 0.873, and 0.911, respectively. External validation AUCs were 0.809, 0.863, and 0.901. For AIP at 0.34, internal and external validation achieved similar AUCs of 0.849 and 0.842. Slightly lower performance was seen for the 0.318 cut-off, with AUCs of 0.844 and 0.836. Significant gender-based variations were noted for TyG-index at 8 (male AUC=0.832, female AUC=0.790) and 8.75 (male AUC=0.874, female AUC=0.862) and AIP at 0.318 (male AUC=0.853, female AUC=0.825) and 0.34 (male AUC=0.858, female AUC=0.831). Gender similarity in AUC (male AUC=0.907 versus female AUC=0.906) was observed only when the TyG-index cut-off point equals 8.93.

CONCLUSION

We have established a simple and effective non-invasive machine learning model that has good clinical value for predicting cardiovascular risk in the general population.

Deep learning prediction of steep and flat corneal curvature using fundus photography in post-COVID telemedicine era

Recently, fundus photography (FP) is being increasingly used. Corneal curvature is an essential factor in refractive errors and is associated with several pathological corneal conditions. As FP-based examination systems have already been widely distributed, it would be helpful for telemedicine to extract information such as corneal curvature using FP. This study aims to develop a deep learning model based on FP for corneal curvature prediction by categorizing corneas into steep, regular, and flat groups. The EfficientNetB0 architecture with transfer learning was used to learn FP patterns to predict flat, regular, and steep corneas. In validation, the model achieved a multiclass accuracy of 0.727, a Matthews correlation coefficient of 0.519, and an unweighted Cohen's κ of 0.590. The areas under the receiver operating characteristic curves for binary prediction of flat and steep corneas were 0.863 and 0.848, respectively. The optic nerve and its peripheral areas were the main focus of the model. The developed algorithm shows that FP can potentially be used as an imaging modality to estimate corneal curvature in the post-COVID-19 era, whereby patients may benefit from the detection of abnormal corneal curvatures using FP in the telemedicine setting.

A machine learning-based online web calculator to aid in the diagnosis of sarcopenia in the US community

Background

Sarcopenia places a heavy healthcare burden on individuals and society. Recognizing sarcopenia and intervening at an early stage is critical. However, there is no simple and easy-to-use prediction tool for diagnosing sarcopenia. The aim of this study was to construct a well-performing online web calculator based on a machine learning approach to predict the risk of low lean body mass (LBM) to assist in the diagnosis of sarcopenia.

Methods

Data from the National Health and Nutritional Examination Surveys 1999-2004 were selected for model construction, and the included data were randomly divided into training and validation sets in the ratio of 75:25. Six machine learning methods- Classification and Regression Trees, Logistic Regression, Neural Network, Random Forest, Support Vector Machine, and Extreme Gradient Boosting (XGBoost)-were used to develop the model. They are screened for features and evaluated for performance. The best-performing models were further developed as an online web calculator for clinical applications.

Results

There were 3046 participants enrolled in the study and 815 (26.8%) participants with LBM. Through feature screening, height, waist circumference, race, and age were used as machine learning features to construct the model. After performance evaluation and sensitivity analysis, the XGBoost-based model was determined to be the best model with better discriminative performance, clinical utility, and robustness.

Conclusion

The XGBoost-based model in this study has excellent performance, and the online web calculator based on it can easily and quickly predict the risk of LBM to aid in the diagnosis of sarcopenia in adults over the age of 60.

Machine Learning for Sarcopenia Prediction in the Elderly Using Socioeconomic, Infrastructure, and Quality-of-Life Data

Since the WHO's 2021 aging redefinition emphasizes "healthy aging" by focusing on the elderly's ability to perform daily activities, sarcopenia, which is defined as the loss of skeletal muscle mass, is now becoming a critical health concern, especially in South Korea with a rapidly aging population. Therefore, we develop a prediction model for sarcopenia by using machine learning (ML) techniques based on the Korea National Health and Nutrition Examination Survey (KNHANES) data 2008-2011, in which we focus on the role of socioeconomic status (SES), social infrastructure, and quality of life (QoL) in the prevalence of sarcopenia. We successfully identify sarcopenia with approximately 80% accuracy by using random forest (RF) and LightGBM (LGB), CatBoost (CAT), and a deep neural network (DNN). For prediction reliability, we achieve area under curve (AUC) values of 0.831, 0.868, and 0.773 for both genders, males, and females, respectively. Especially when using only male data, all the models consistently exhibit better performance overall. Furthermore, using the SHapley Additive exPlanations (SHAP) analysis, we find several common key features, which mainly contribute to model building. These include SES features, such as monthly household income, housing type, marriage status, and social infrastructure accessibility. Furthermore, the causal relationships of household income, per capita neighborhood sports facility area, and life satisfaction are analyzed to establish an effective prediction model for sarcopenia management in an aging population.

Diagnosing Systemic Disorders with AI Algorithms Based on Ocular Images

The advent of artificial intelligence (AI), especially the state-of-the-art deep learning frameworks, has begun a silent revolution in all medical subfields, including ophthalmology. Due to their specific microvascular and neural structures, the eyes are anatomically associated with the rest of the body. Hence, ocular image-based AI technology may be a useful alternative or additional screening strategy for systemic diseases, especially where resources are scarce. This review summarizes the current applications of AI related to the prediction of systemic diseases from multimodal ocular images, including cardiovascular diseases, dementia, chronic kidney diseases, and anemia. Finally, we also discuss the current predicaments and future directions of these applications.

Pain Increases the Risk for Sarcopenia in Community-Dwelling Adults: Results From the English Longitudinal Study of Ageing

BACKGROUND

Pain and sarcopenia are common in older people. Cross-sectional studies have reported a significant association between these two conditions, but cohort studies exploring pain as a potential risk factor for sarcopenia are scarce. Given this background, the aim of the present work was to investigate the association between pain (and its severity) at baseline, and the incidence of sarcopenia over 10 years of follow-up in a large representative sample of the English older adult population.

METHODS

Pain was diagnosed using self-reported information and categorized as mild to severe pain at four sites (low back, hip, knee, and feet). Incident sarcopenia was defined as having low handgrip strength and low skeletal muscle mass during the follow-up period. The association between pain at baseline and incident sarcopenia was assessed using an adjusted logistic regression analysis, and reported as odds ratios (ORs) with their 95% confidence intervals (CIs).

RESULTS

The 4 102 participants without sarcopenia at baseline had a mean ± standard deviation age of 69.7 ± 7.2 years, and they were mainly male (55.6%). Pain was present in 35.3% of the sample. Over 10 years of follow-up, 13.9% of the participants developed sarcopenia. After adjusting for 12 potential confounders, people with pain reported a significantly higher risk of sarcopenia (OR = 1.46: 95% CI: 1.18-1.82). However, only severe pain was significantly associated with incident sarcopenia, without significant differences across the four sites assessed.

CONCLUSIONS

The presence of pain, particularly severe pain, was associated with a significantly higher risk of incident sarcopenia.

Sarcopenia Prediction for Elderly People Using Machine Learning: A Case Study on Physical Activity

Sarcopenia is a well-known age-related disease that can lead to musculoskeletal disorders and chronic metabolic syndromes, such as sarcopenic obesity. Numerous studies have researched the relationship between sarcopenia and various risk factors, leading to the development of predictive models based on these factors. In this study, we explored the impact of physical activity (PA) in daily life and obesity on sarcopenia prediction. PA is easier to measure using personal devices, such as smartphones and watches, or lifelogs, than using other factors that require medical equipment and examination. To demonstrate the feasibility of sarcopenia prediction using PA, we trained various machine learning models, including gradient boosting machine (GBM), xgboost (XGB), lightgbm (LGB), catboost (CAT), logistic regression, support vector classifier, k-nearest neighbors, random forest (RF), multi-layer perceptron, and deep neural network (DNN), using data samples from the Korea National Health and Nutrition Examination Survey. Among the models, the DNN achieved the most precise accuracy on average, 81%, with PA features across all data combinations, and the accuracy increased up to 90% with the addition of obesity information, such as total fat mass and fat percentage. Considering the difficulty of measuring the obesity feature, when adding waist circumference to the PA features, the DNN recorded the highest accuracy of 84%. This model accuracy could be improved by using separate training sets according to gender. As a result of measurement with various metrics for accurate evaluation of models, GBM, XGB, LGB, CAT, RF, and DNN demonstrated significant predictive performance using only PA features including waist circumference, with AUC values at least around 0.85 and often approaching or exceeding 0.9. We also found the key features for a highly performing model such as the quantified PA value and metabolic equivalent score in addition to a simple obesity measure such as body mass index (BMI) and waist circumference using SHAP analysis.

Integrating oculomics with genomics reveals imaging biomarkers for preventive and personalized prediction of arterial aneurysms

Objective

Arterial aneurysms are life-threatening but usually asymptomatic before requiring hospitalization. Oculomics of retinal vascular features (RVFs) extracted from retinal fundus images can reflect systemic vascular properties and therefore were hypothesized to provide valuable information on detecting the risk of aneurysms. By integrating oculomics with genomics, this study aimed to (i) identify predictive RVFs as imaging biomarkers for aneurysms and (ii) evaluate the value of these RVFs in supporting early detection of aneurysms in the context of predictive, preventive and personalized medicine (PPPM).

Methods

This study involved 51,597 UK Biobank participants who had retinal images available to extract oculomics of RVFs. Phenome-wide association analyses (PheWASs) were conducted to identify RVFs associated with the genetic risks of the main types of aneurysms, including abdominal aortic aneurysm (AAA), thoracic aneurysm (TAA), intracranial aneurysm (ICA) and Marfan syndrome (MFS). An aneurysm-RVF model was then developed to predict future aneurysms. The performance of the model was assessed in both derivation and validation cohorts and was compared with other models employing clinical risk factors. An RVF risk score was derived from our aneurysm-RVF model to identify patients with an increased risk of aneurysms.

Results

PheWAS identified a total of 32 RVFs that were significantly associated with the genetic risks of aneurysms. Of these, the number of vessels in the optic disc ('ntreeA') was associated with both AAA (β = -0.36, P = 6.75e-10) and ICA (β = -0.11, P = 5.51e-06). In addition, the mean angles between each artery branch ('curveangle_mean_a') were commonly associated with 4 MFS genes (FBN1: β = -0.10, P = 1.63e-12; COL16A1: β = -0.07, P = 3.14e-09; LOC105373592: β = -0.06, P = 1.89e-05; C8orf81/LOC441376: β = 0.07, P = 1.02e-05). The developed aneurysm-RVF model showed good discrimination ability in predicting the risks of aneurysms. In the derivation cohort, the C-index of the aneurysm-RVF model was 0.809 [95% CI: 0.780-0.838], which was similar to the clinical risk model (0.806 [0.778-0.834]) but higher than the baseline model (0.739 [0.733-0.746]). Similar performance was observed in the validation cohort, with a C-index of 0.798 (0.727-0.869) for the aneurysm-RVF model, 0.795 (0.718-0.871) for the clinical risk model and 0.719 (0.620-0.816) for the baseline model. An aneurysm risk score was derived from the aneurysm-RVF model for each study participant. The individuals in the upper tertile of the aneurysm risk score had a significantly higher risk of aneurysm compared to those in the lower tertile (hazard ratio = 17.8 [6.5-48.8], P = 1.02e-05).

Conclusion

We identified a significant association between certain RVFs and the risk of aneurysms and revealed the impressive capability of using RVFs to predict the future risk of aneurysms by a PPPM approach. Our finds have great potential to support not only the predictive diagnosis of aneurysms but also a preventive and more personalized screening plan which may benefit both patients and the healthcare system.

Graphical abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-023-00315-7.

An Overview of Deep-Learning-Based Methods for Cardiovascular Risk Assessment with Retinal Images

Cardiovascular diseases (CVDs) are one of the most prevalent causes of premature death. Early detection is crucial to prevent and address CVDs in a timely manner. Recent advances in oculomics show that retina fundus imaging (RFI) can carry relevant information for the early diagnosis of several systemic diseases. There is a large corpus of RFI systematically acquired for diagnosing eye-related diseases that could be used for CVDs prevention. Nevertheless, public health systems cannot afford to dedicate expert physicians to only deal with this data, posing the need for automated diagnosis tools that can raise alarms for patients at risk. Artificial Intelligence (AI) and, particularly, deep learning models, became a strong alternative to provide computerized pre-diagnosis for patient risk retrieval. This paper provides a novel review of the major achievements of the recent state-of-the-art DL approaches to automated CVDs diagnosis. This overview gathers commonly used datasets, pre-processing techniques, evaluation metrics and deep learning approaches used in 30 different studies. Based on the reviewed articles, this work proposes a classification taxonomy depending on the prediction target and summarizes future research challenges that have to be tackled to progress in this line.

Body mass index-based predictions and personalized clinical strategies for colorectal cancer in the context of PPPM

Currently colorectal cancer (CRC) is the third most prevalent cancer worldwide. Body mass index (BMI) is frequently used in CRC screening and risk assessment to quantitatively evaluate weight. However, the impact of BMI on clinical strategies for CRC has received little attention. Within the framework of the predictive, preventive, and personalized medicine (3PM/PPPM), we hypothesized that BMI stratification would affect the primary, secondary, and tertiary care options for CRC and we conducted a critical evidence-based review. BMI dynamically influences CRC outcomes, which helps avoiding adverse treatment effects. The outcome of surgical and radiation treatment is adversely affected by overweight (BMI ≥ 30) or underweight (BMI < 20). A number of interventions, such as enhanced recovery after surgery and robotic surgery, can be applied to CRC at all levels of BMI. BMI-controlling modalities such as exercise, diet control, nutritional therapy, and medications may be potentially beneficial for patients with CRC. Patients with overweight are advised to lose weight through diet, medication, and physical activity while patients suffering of underweight require more focus on nutrition. BMI assists patients with CRC in better managing their weight, which decreases the incidence of adverse prognostic events during treatment. BMI is accessible, noninvasive, and highly predictive of clinical outcomes in CRC. The cost-benefit of the PPPM paradigm in developing countries can be advanced, and the clinical benefit for patients can be improved with the promotion of BMI-based clinical strategy models for CRC.

Radiomics based on readout-segmented echo-planar imaging (RS-EPI) diffusion-weighted imaging (DWI) for prognostic risk stratification of patients with rectal cancer: a two-centre, machine learning study using the framework of predictive, preventive, and personalized medicine

Background

Currently, the rate of recurrence or metastasis (ROM) remains high in rectal cancer (RC) patients treated with the standard regimen. The potential of diffusion-weighted imaging (DWI) in predicting ROM risk has been reported, but the efficacy is insufficient.

Aims

This study investigated the potential of a new sequence called readout-segmented echo-planar imaging (RS-EPI) DWI in predicting the ROM risk of patients with RC using machine learning methods to achieve the principle of predictive, preventive, and personalized medicine (PPPM) application in RC treatment.

Methods

A total of 195 RC patients from two centres who directly received total mesorectal excision were retrospectively enrolled in our study. Machine learning methods, including recursive feature elimination (RFE), the synthetic minority oversampling technique (SMOTE), and the support vector machine (SVM) classifier, were used to construct models based on clinical-pathological factors (clinical model), radiomic features from RS-EPI DWI (radiomics model), and their combination (merged model). The Harrell concordance index (C-index) and the area under the time-dependent receiver operating characteristic curve (AUC) were calculated to evaluate the predictive performance at 1 year, 3 years, and 5 years. Kaplan‒Meier analysis was performed to evaluate the ability to stratify patients according to the risk of ROM.

Findings

The merged model performed well in predicting tumour ROM in patients with RC at 1 year, 3 years, and 5 years in both cohorts (AUC = 0.887/0.813/0.794; 0.819/0.795/0.783) and was significantly superior to the clinical model (AUC = 0.87 [95% CI: 0.80-0.93] vs. 0.71 [95% CI: 0.59-0.81], p = 0.009; C-index = 0.83 [95% CI: 0.76-0.90] vs. 0.68 [95% CI: 0.56-0.79], p = 0.002). It also had a significant ability to differentiate patients with a high and low risk of ROM (HR = 12.189 [95% CI: 4.976-29.853], p < 0.001; HR = 6.427 [95% CI: 2.265-13.036], p = 0.002).

Conclusion

Our developed merged model based on RS-EPI DWI accurately predicted and effectively stratified patients with RC according to the ROM risk at an early stage with an individualized profile, which may be able to assist physicians in individualizing the treatment protocols and promote a meaningful paradigm shift in RC treatment from traditional reactive medicine to PPPM.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13167-022-00303-3.