{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:55:22Z","timestamp":1775580922889,"version":"3.50.1"},"reference-count":79,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2022,6,7]],"date-time":"2022-06-07T00:00:00Z","timestamp":1654560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Cardiovascular diseases (CVD) are the leading cause of death worldwide. People affected by CVDs may go undiagnosed until the occurrence of a serious heart failure event such as stroke, heart attack, and myocardial infraction. In Qatar, there is a lack of studies focusing on CVD diagnosis based on non-invasive methods such as retinal image or dual-energy X-ray absorptiometry (DXA). In this study, we aimed at diagnosing CVD using a novel approach integrating information from retinal images and DXA data. We considered an adult Qatari cohort of 500 participants from Qatar Biobank (QBB) with an equal number of participants from the CVD and the control groups. We designed a case-control study with a novel multi-modal (combining data from multiple modalities\u2014DXA and retinal images)\u2014to propose a deep learning (DL)-based technique to distinguish the CVD group from the control group. Uni-modal models based on retinal images and DXA data achieved 75.6% and 77.4% accuracy, respectively. The multi-modal model showed an improved accuracy of 78.3% in classifying CVD group and the control group. We used gradient class activation map (GradCAM) to highlight the areas of interest in the retinal images that influenced the decisions of the proposed DL model most. It was observed that the model focused mostly on the centre of the retinal images where signs of CVD such as hemorrhages were present. This indicates that our model can identify and make use of certain prognosis markers for hypertension and ischemic heart disease. From DXA data, we found higher values for bone mineral density, fat content, muscle mass and bone area across majority of the body parts in CVD group compared to the control group indicating better bone health in the Qatari CVD cohort. This seminal method based on DXA scans and retinal images demonstrate major potentials for the early detection of CVD in a fast and relatively non-invasive manner.<\/jats:p>","DOI":"10.3390\/s22124310","type":"journal-article","created":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T02:01:44Z","timestamp":1655085704000},"page":"4310","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":80,"title":["Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5636-7632","authenticated-orcid":false,"given":"Hamada R. H.","family":"Al-Absi","sequence":"first","affiliation":[{"name":"College of Science and Engineering, Hamad Bin Khalifa University, Doha 34110, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1226-3986","authenticated-orcid":false,"given":"Mohammad Tariqul","family":"Islam","sequence":"additional","affiliation":[{"name":"Computer Science Department, Southern Connecticut State University, New Haven, CT 06515, USA"}]},{"given":"Mahmoud Ahmed","family":"Refaee","sequence":"additional","affiliation":[{"name":"Geriatric Department, Hamad Medical Corporation, Doha 3050, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0744-8206","authenticated-orcid":false,"given":"Muhammad E. H.","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Qatar University, Doha 2713, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7033-3693","authenticated-orcid":false,"given":"Tanvir","family":"Alam","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, Hamad Bin Khalifa University, Doha 34110, Qatar"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2982","DOI":"10.1016\/j.jacc.2020.11.010","article-title":"Global burden of cardiovascular diseases and risk factors, 1990\u20132019: Update from the GBD 2019 study","volume":"76","author":"Roth","year":"2020","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref_2","unstructured":"World Health Organization (2021). Cardiovascular Diseases (CVDs), World Health Organization."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100775","DOI":"10.1016\/j.eclinm.2021.100775","article-title":"Prevalence of subclinical retinal ischemia in patients with cardiovascular disease\u2014A hypothesis driven study","volume":"33","author":"Long","year":"2021","journal-title":"EClinicalMedicine"},{"key":"ref_4","unstructured":"WHO-EMRO (2021). Cardiovascular Diseases, World Health Organization, Regional Office for the Eastern Mediterranean."},{"key":"ref_5","unstructured":"Planning and Statistics Authority (Qatar) (2021, September 18). Births & Deaths in the State of Qatar (Review & Analysis). Report 2018, Available online: https:\/\/www.psa.gov.qa\/en\/statistics\/Statistical%20Releases\/General\/StatisticalAbstract\/2018\/Birth_death_2018_EN.pdf."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ghantous, C.M., Kamareddine, L., Farhat, R., Zouein, F.A., Mondello, S., Kobeissy, F., and Zeidan, A. (2020). Advances in cardiovascular biomarker discovery. Biomedicines, 8.","DOI":"10.3390\/biomedicines8120552"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"29929","DOI":"10.1109\/ACCESS.2021.3059469","article-title":"Risk Factors and Comorbidities Associated to Cardiovascular Disease in Qatar: A Machine Learning Based Case-Control Study","volume":"9","author":"Refaee","year":"2021","journal-title":"IEEE Access"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rehman, A.U., Alam, T., and Belhaouari, S.B. (2020, January 2\u20135). Investigating Potential Risk Factors for Cardiovascular Diseases in Adult Qatari Population. Proceedings of the 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT), Doha, Qatar.","DOI":"10.1109\/ICIoT48696.2020.9089468"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1837","DOI":"10.1161\/01.CIR.97.18.1837","article-title":"Prediction of coronary heart disease using risk factor categories","volume":"97","author":"Wilson","year":"1998","journal-title":"Circulation"},{"key":"ref_10","unstructured":"American College of Cardiology (2022). ASCVD Risk Estimator, American College of Cardiology. Available online: https:\/\/tools.acc.org\/ascvd-risk-estimator-plus\/."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.media.2018.09.001","article-title":"Direct delineation of myocardial infarction without contrast agents using a joint motion feature learning architecture","volume":"50","author":"Xu","year":"2018","journal-title":"Med. Image Anal."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.compbiomed.2016.01.028","article-title":"An integrated index for automated detection of infarcted myocardium from cross-sectional echocardiograms using texton-based features (Part 1)","volume":"71","author":"Sudarshan","year":"2016","journal-title":"Comput. Biol. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41746-018-0065-x","article-title":"Deep echocardiography: Data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease","volume":"1","author":"Madani","year":"2018","journal-title":"NPJ Digit. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.compbiomed.2015.03.033","article-title":"Computer-aided diagnosis of myocardial infarction using ultrasound images with DWT, GLCM and HOS methods: A comparative study","volume":"62","author":"Vidya","year":"2015","journal-title":"Comput. Biol. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1471","DOI":"10.1002\/mp.12783","article-title":"Texture analysis of cardiac cine magnetic resonance imaging to detect nonviable segments in patients with chronic myocardial infarction","volume":"45","author":"Larroza","year":"2018","journal-title":"Med. Phys."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Snaauw, G., Gong, D., Maicas, G., Van Den Hengel, A., Niessen, W.J., Verjans, J., and Carneiro, G. (2019, January 8\u201311). End-to-end diagnosis and segmentation learning from cardiac magnetic resonance imaging. Proceedings of the 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy.","DOI":"10.1109\/ISBI.2019.8759276"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1148\/radiol.2019190101","article-title":"Cardiac MRI and texture analysis of myocardial T1 and T2 maps in myocarditis with acute versus chronic symptoms of heart failure","volume":"292","author":"Baessler","year":"2019","journal-title":"Radiology"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1097\/RLI.0000000000000448","article-title":"Texture analysis and machine learning for detecting myocardial infarction in noncontrast low-dose computed tomography: Unveiling the invisible","volume":"53","author":"Mannil","year":"2018","journal-title":"Investig. Radiol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e007217","DOI":"10.1161\/CIRCIMAGING.117.007217","article-title":"Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography\u2013based fractional flow reserve: Result from the MACHINE consortium","volume":"11","author":"Coenen","year":"2018","journal-title":"Circ. Cardiovasc. Imaging"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1588","DOI":"10.1109\/TMI.2018.2883807","article-title":"A recurrent CNN for automatic detection and classification of coronary artery plaque and stenosis in coronary CT angiography","volume":"38","author":"Zreik","year":"2018","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0933-3657(02)00055-6","article-title":"Bayesian learning for cardiac SPECT image interpretation","volume":"26","author":"Sacha","year":"2002","journal-title":"Artif. Intell. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1007\/s12149-018-1306-4","article-title":"Accuracy of an artificial neural network for detecting a regional abnormality in myocardial perfusion SPECT","volume":"33","author":"Shibutani","year":"2019","journal-title":"Ann. Nucl. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"109835","DOI":"10.1016\/j.ejrad.2021.109835","article-title":"Deep learning powered coronary CT angiography for detecting obstructive coronary artery disease: The effect of reader experience, calcification and image quality","volume":"142","author":"Liu","year":"2021","journal-title":"Eur. J. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.kint.2020.01.039","article-title":"The eye, the kidney, and cardiovascular disease: Old concepts, better tools, and new horizons","volume":"98","author":"Farrah","year":"2020","journal-title":"Kidney Int."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/S0039-6257(01)00234-X","article-title":"Retinal microvascular abnormalities and their relationship with hypertension, cardiovascular disease, and mortality","volume":"46","author":"Wong","year":"2001","journal-title":"Surv. Ophthalmol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, L., Yuan, M., An, Z., Zhao, X., Wu, H., Li, H., Wang, Y., Sun, B., Li, H., and Ding, S. (2020). Prediction of hypertension, hyperglycemia and dyslipidemia from retinal fundus photographs via deep learning: A cross-sectional study of chronic diseases in central China. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0233166"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"15686","DOI":"10.1109\/ACCESS.2021.3052477","article-title":"DiaNet: A deep learning based architecture to diagnose diabetes using retinal images only","volume":"9","author":"Islam","year":"2021","journal-title":"IEEE Access"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","article-title":"Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning","volume":"2","author":"Poplin","year":"2018","journal-title":"Nat. Biomed. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1038\/s41551-020-00626-4","article-title":"A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre","volume":"5","author":"Cheung","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.numecd.2016.06.011","article-title":"The association of lean and fat mass with all-cause mortality in older adults: The Cardiovascular Health Study","volume":"26","author":"Spahillari","year":"2016","journal-title":"Nutr. Metab. Cardiovasc. Dis."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1045098","DOI":"10.1155\/2019\/1045098","article-title":"Bone Mineral Density as a Predictor of Atherogenic Indexes of Cardiovascular Disease, Especially in Nonobese Adults","volume":"2019","author":"Chuang","year":"2019","journal-title":"Dis. Markers"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.21037\/qims.2020.03.02","article-title":"Body composition with dual energy X-ray absorptiometry: From basics to new tools","volume":"10","author":"Messina","year":"2020","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1040","DOI":"10.1136\/heartjnl-2020-318764","article-title":"Prognostic value of lower bone mineral density in predicting adverse cardiovascular disease in Asian women","volume":"107","author":"Park","year":"2021","journal-title":"Heart"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.nut.2018.11.028","article-title":"Current technologies in body composition assessment: Advantages and disadvantages","volume":"62","author":"Ceniccola","year":"2019","journal-title":"Nutrition"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1111\/j.1600-0420.2004.00347.x","article-title":"Screening for diabetic retinopathy using a digital non-mydriatic camera compared with standard 35-mm stereo colour transparencies","volume":"82","author":"Hansen","year":"2004","journal-title":"Acta Ophthalmol. Scand."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-031-01660-8","article-title":"Digital Image Processing for Ophthalmology: Detection and Modeling of Retinal Vascular Architecture","volume":"9","author":"Oloumi","year":"2014","journal-title":"Synth. Lect. Biomed. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"19053","DOI":"10.1038\/srep19053","article-title":"Retinal information is independently associated with cardiovascular disease in patients with type 2 diabetes","volume":"6","author":"Guo","year":"2016","journal-title":"Sci. Rep."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"9432","DOI":"10.1038\/s41598-020-65794-4","article-title":"Age and sex affect deep learning prediction of cardiometabolic risk factors from retinal images","volume":"10","author":"Gerrits","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_39","first-page":"e368","article-title":"Retinal microvascular complexity comparing mono-and multifractal dimensions in relation to cardiometabolic risk factors in a Middle Eastern population","volume":"99","author":"Gerrits","year":"2021","journal-title":"Acta Ophthalmol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1002\/ajhb.22221","article-title":"Body mass index versus dual energy X-ray absorptiometry-derived indexes: Predictors of cardiovascular and diabetic disease risk factors","volume":"24","author":"Sharp","year":"2012","journal-title":"Am. J. Hum. Biol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.jjcc.2014.03.010","article-title":"Markers of metabolic and cardiovascular health in adults: Comparative analysis of DEXA-based body composition components and BMI categories","volume":"65","author":"Lang","year":"2015","journal-title":"J. Cardiol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.ijcard.2016.07.135","article-title":"Sarcopenia in patients with heart failure with preserved ejection fraction: Impact on muscle strength, exercise capacity and quality of life","volume":"222","author":"Bekfani","year":"2016","journal-title":"Int. J. Cardiol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1080\/00015385.2020.1771885","article-title":"Heart failure is associated with accelerated age related metabolic bone disease","volume":"76","author":"Martens","year":"2021","journal-title":"Acta Cardiol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"175","DOI":"10.2147\/DMSO.S238748","article-title":"Adiposity indicators as cardio-metabolic risk predictors in adults from country with high burden of obesity","volume":"13","author":"Kerkadi","year":"2020","journal-title":"Diabetes Metab. Syndr. Obesity Targets Ther."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1186\/s12937-020-00569-1","article-title":"Age and gender specific cut-off points for body fat parameters among adults in Qatar","volume":"19","author":"Bawadi","year":"2020","journal-title":"Nutr. J."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Bartl, R., and Bartl, C. (2019). Bone densitometry. The Osteoporosis Manual: Prevention, Diagnosis and Management, Springer International Publishing.","DOI":"10.1007\/978-3-030-00731-7_8"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1002\/jcsm.12516","article-title":"Bone in heart failure","volume":"11","author":"Loncar","year":"2020","journal-title":"J. Cachexia Sarcopenia Muscle"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"115943","DOI":"10.1016\/j.bone.2021.115943","article-title":"Machine learning for automated abdominal aortic calcification scoring of DXA vertebral fracture assessment images: A pilot study","volume":"148","author":"Reid","year":"2021","journal-title":"Bone"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Bawadi, H., Abouwatfa, M., Alsaeed, S., Kerkadi, A., and Shi, Z. (2019). Body shape index is a stronger predictor of diabetes. Nutrients, 11.","DOI":"10.3390\/nu11051018"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1038\/s41598-018-36745-x","article-title":"Learning from longitudinal data in electronic health record and genetic data to improve cardiovascular event prediction","volume":"9","author":"Zhao","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"115007","DOI":"10.1088\/1361-6579\/abc323","article-title":"Detection of coronary artery disease using multi-modal feature fusion and hybrid feature selection","volume":"41","author":"Zhang","year":"2020","journal-title":"Physiol. Meas."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.inffus.2020.06.008","article-title":"A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion","volume":"63","author":"Ali","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.ejmp.2021.04.011","article-title":"Multi-input deep learning approach for cardiovascular disease diagnosis using myocardial perfusion imaging and clinical data","volume":"84","author":"Apostolopoulos","year":"2021","journal-title":"Phys. Medica"},{"key":"ref_54","unstructured":"Chaves, J.M.Z., Chaudhari, A.S., Wentland, A.L., Desai, A.D., Banerjee, I., Boutin, R.D., Maron, D.J., Rodriguez, F., Sandhu, A.T., and Jeffrey, R.B. (2021). Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: A multimodal explainable artificial intelligence approach. medRxiv."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"e021976","DOI":"10.1161\/JAHA.121.021976","article-title":"Unsupervised Learning for Automated Detection of Coronary Artery Disease Subgroups","volume":"10","author":"Flores","year":"2021","journal-title":"J. Am. Heart Assoc."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1420","DOI":"10.1093\/aje\/kwz084","article-title":"Qatar biobank cohort study: Study design and first results","volume":"188","author":"Fthenou","year":"2019","journal-title":"Am. J. Epidemiol."},{"key":"ref_57","first-page":"1","article-title":"The Qatar Biobank: Background and methods","volume":"15","author":"Abderrahim","year":"2015","journal-title":"BMC Public Health"},{"key":"ref_58","first-page":"45","article-title":"Min max normalization based data perturbation method for privacy protection","volume":"2","author":"Jain","year":"2011","journal-title":"Int. J. Comput. Commun. Technol."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J. (2017). Classification and Regression Trees, Routledge.","DOI":"10.1201\/9781315139470"},{"key":"ref_60","unstructured":"Hagan, M., Demuth, H., and Beale, M. (1987). Neural Net and Traditional Classifiers, Lincoln Laboratory."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_62","unstructured":"Brownlee, J. (2021, October 27). XGBoost with Python: Gradient Boosted Trees with XGBoost and Scikit-Learn. Machine Learning Mastery 2016. Available online: https:\/\/machinelearningmastery.com\/xgboost-with-python\/."},{"key":"ref_63","unstructured":"Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. arXiv."},{"key":"ref_64","unstructured":"Hoffman, J.I. (2015). Biostatistics for Medical and Biomedical Practitioners, Academic Press."},{"key":"ref_65","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_66","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_67","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_68","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_69","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_70","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50\u00d7 fewer parameters and< 0.5 MB model size. arXiv."},{"key":"ref_71","doi-asserted-by":"crossref","unstructured":"Smith, L.N., and Topin, N. (2019, January 10). Super-convergence: Very fast training of neural networks using large learning rates. Proceedings of the Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, Baltimore, MD, USA.","DOI":"10.1117\/12.2520589"},{"key":"ref_72","unstructured":"Smith, L.N. (2018). A disciplined approach to neural network hyper-parameters: Part 1\u2013learning rate, batch size, momentum, and weight decay. arXiv."},{"key":"ref_73","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.1002\/jbmr.5650090904","article-title":"Lifestyle factors and bone density in the elderly: Implications for osteoporosis prevention","volume":"9","author":"Nguyen","year":"1994","journal-title":"J. Bone Miner. Res."},{"key":"ref_74","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1093\/oxfordjournals.aje.a008920","article-title":"Risk factors for osteoporotic fractures in elderly men","volume":"144","author":"Ngugyen","year":"1996","journal-title":"Am. J. Epidemiol."},{"key":"ref_75","doi-asserted-by":"crossref","unstructured":"Khondaker, M., Islam, T., Khan, J.Y., Refaee, M.A., Hajj, N.E., Rahman, M.S., and Alam, T. (2020). Obesity in Qatar: A Case-Control Study on the Identification of Associated Risk Factors. Diagnostics, 10.","DOI":"10.3390\/diagnostics10110883"},{"key":"ref_76","unstructured":"Gildenblat, J. (2022, January 02). PyTorch Library for CAM Methods. Available online: https:\/\/github.com\/jacobgil\/pytorch-grad-cam."},{"key":"ref_77","doi-asserted-by":"crossref","first-page":"2310","DOI":"10.1056\/NEJMra032865","article-title":"Hypertensive retinopathy","volume":"351","author":"Wong","year":"2004","journal-title":"N. Engl. J. Med."},{"key":"ref_78","unstructured":"Kanukollu, V.M., and Ahmad, S.S. (2022, January 16). Retinal Hemorrhage. StatPearls, Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK560777\/."},{"key":"ref_79","first-page":"372","article-title":"Obesity, osteoporosis and bone metabolism","volume":"20","author":"Gkastaris","year":"2020","journal-title":"J. Musculoskelet. Neuronal Interact."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/12\/4310\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:25:13Z","timestamp":1760138713000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/12\/4310"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,7]]},"references-count":79,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,6]]}},"alternative-id":["s22124310"],"URL":"https:\/\/doi.org\/10.3390\/s22124310","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,7]]}}}