Non-Invasive Biomarkers in the Era of Big Data and Machine Learning
Abstract
:1. Introduction
2. The Non-Invasive Perspective in Diagnostics and Data Analysis
3. Recent Advances in Non-Invasive Biomarker Identification
3.1. Imaging-Data-Based Studies
3.2. Molecular-Data-Based Studies
3.3. Signal-Data-Based Studies
3.4. Clinica-Data-Based Studies
3.5. Combined Modality Studies
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Chen, H.; Mo, L.; Hu, H.; Ou, Y.; Luo, J. Risk factors of postoperative delirium after cardiac surgery: A meta-analysis. J. Cardiothorac. Surg. 2021, 16, 113. [Google Scholar] [CrossRef]
- Zhang, Y.; Wu, K.M.; Yang, L.; Dong, Q.; Yu, J.T. Tauopathies: New perspectives and challenges. Mol. Neurodegener. 2022, 17, 28. [Google Scholar] [CrossRef]
- Park, S.m.; Ge, T.J.; Won, D.D.; Lee, J.K.; Liao, J.C. Digital biomarkers in human excreta. Nat. Rev. Gastroenterol. Hepatol. 2021, 18, 521–522. [Google Scholar] [CrossRef]
- Pandey, R.; Ngaju, P.; Janghorban, M.; Abuelazm, H.; Malaeb, K.; Aryal, K.P. Noninvasive Biomarkers for Disease Diagnosis and Health Monitoring. In Biosensors for Personalized Healthcare; Springer: Singapore, 2024; pp. 27–47. [Google Scholar]
- Kumar, P.; Gupta, S.; Das, B.C. Saliva as a potential non-invasive liquid biopsy for early and easy diagnosis/prognosis of head and neck cancer. Transl. Oncol. 2024, 40, 101827. [Google Scholar] [CrossRef]
- Khan, I.A.; Saraya, A. Circulating MicroRNAs as noninvasive diagnostic and prognostic biomarkers in pancreatic cancer: A review. J. Gastrointest. Cancer 2023, 54, 720–730. [Google Scholar] [CrossRef] [PubMed]
- Felekkis, K.; Papaneophytou, C. The Circulating Biomarkers League: Combining miRNAs with Cell-Free DNAs and Proteins. Int. J. Mol. Sci. 2024, 25, 3403. [Google Scholar] [CrossRef] [PubMed]
- Trimarchi, G.; Pizzino, F.; Paradossi, U.; Gueli, I.A.; Palazzini, M.; Gentile, P.; Di Spigno, F.; Ammirati, E.; Garascia, A.; Tedeschi, A.; et al. Charting the unseen: How non-invasive imaging could redefine cardiovascular prevention. J. Cardiovasc. Dev. Dis. 2024, 11, 245. [Google Scholar] [CrossRef] [PubMed]
- Edvardsen, T.; Asch, F.M.; Davidson, B.; Delgado, V.; DeMaria, A.; Dilsizian, V.; Gaemperli, O.; Garcia, M.J.; Kamp, O.; Lee, D.C.; et al. Non-invasive imaging in coronary syndromes: Recommendations of the European Association of Cardiovascular Imaging and the American Society of Echocardiography, in collaboration with the American Society of Nuclear Cardiology, Society of Cardiovascular Computed Tomography, and Society for Cardiovascular Magnetic Resonance. Eur. Heart J. Cardiovasc. Imaging 2022, 23, e6–e33. [Google Scholar]
- Callewaert, B.; Jones, E.A.; Himmelreich, U.; Gsell, W. Non-invasive evaluation of cerebral microvasculature using pre-clinical MRI: Principles, advantages and limitations. Diagnostics 2021, 11, 926. [Google Scholar] [CrossRef]
- Su, D.; Wu, K.; Saha, R.; Peng, C.; Wang, J.P. Advances in magnetoresistive biosensors. Micromachines 2019, 11, 34. [Google Scholar] [CrossRef] [PubMed]
- Bai, Y.; Xu, T.; Zhang, X. Graphene-based biosensors for detection of biomarkers. Micromachines 2020, 11, 60. [Google Scholar] [CrossRef]
- Hoffman, M.S.; McKeage, J.W.; Xu, J.; Ruddy, B.P.; Nielsen, P.M.; Taberner, A.J. Minimally invasive capillary blood sampling methods. Expert Rev. Med. Devices 2023, 20, 5–16. [Google Scholar] [CrossRef] [PubMed]
- Volani, C.; Malfertheiner, C.; Caprioli, G.; Fjelstrup, S.; Pramstaller, P.P.; Rainer, J.; Paglia, G. VAMS-based blood capillary sampling for mass spectrometry-based human metabolomics studies. Metabolites 2023, 13, 146. [Google Scholar] [CrossRef]
- Khoubnasabjafari, M.; Mogaddam, M.R.A.; Rahimpour, E.; Soleymani, J.; Saei, A.A.; Jouyban, A. Breathomics: Review of sample collection and analysis, data modeling and clinical applications. Crit. Rev. Anal. Chem. 2022, 52, 1461–1487. [Google Scholar] [CrossRef]
- Kiss, H.; Örlős, Z.; Gellért, Á.; Megyesfalvi, Z.; Mikáczó, A.; Sárközi, A.; Vaskó, A.; Miklós, Z.; Horváth, I. Exhaled biomarkers for point-of-care diagnosis: Recent advances and new challenges in breathomics. Micromachines 2023, 14, 391. [Google Scholar] [CrossRef] [PubMed]
- Gokulakrishnan, K.; Nikhil, J.; Viswanath, B.; Thirumoorthy, C.; Narasimhan, S.; Devarajan, B.; Joseph, E.; David, A.K.D.; Sharma, S.; Vasudevan, K.; et al. Comparison of gut microbiome profile in patients with schizophrenia and healthy controls-A plausible non-invasive biomarker? J. Psychiatr. Res. 2023, 162, 140–149. [Google Scholar] [CrossRef]
- Wang, Z.; Zhu, H.; Jiang, Q.; Zhu, Y.Z. The gut microbiome as non-invasive biomarkers for identifying overweight people at risk for osteoarthritis. Microb. Pathog. 2021, 157, 104976. [Google Scholar] [CrossRef]
- Song, R.; Liu, F.; Ping, Y.; Zhang, Y.; Wang, L. Potential non-invasive biomarkers in tumor immune checkpoint inhibitor therapy: Response and prognosis prediction. Biomark. Res. 2023, 11, 57. [Google Scholar] [CrossRef]
- Vrahatis, A.G.; Skolariki, K.; Krokidis, M.G.; Lazaros, K.; Exarchos, T.P.; Vlamos, P. Revolutionizing the early detection of Alzheimer’s disease through non-invasive biomarkers: The role of artificial intelligence and deep learning. Sensors 2023, 23, 4184. [Google Scholar] [CrossRef] [PubMed]
- Dongiovanni, P.; Meroni, M.; Casati, S.; Goldoni, R.; Thomaz, D.V.; Kehr, N.S.; Galimberti, D.; Del Fabbro, M.; Tartaglia, G.M. Salivary biomarkers: Novel noninvasive tools to diagnose chronic inflammation. Int. J. Oral Sci. 2023, 15, 27. [Google Scholar] [CrossRef]
- Rehman, M.U.; Driss, M.; Khakimov, A.; Khalid, S. Non-Invasive Early Diagnosis of Obstructive Lung Diseases Leveraging Machine Learning Algorithms. Comput. Mater. Contin. 2022, 72, 5681–5697. [Google Scholar] [CrossRef]
- Keskenler, M.F.; Çelik, E.; Dal, D. A New Multi-Layer Machine Learning (MLML) Architecture for Non-invasive Skin Cancer Diagnosis on Dermoscopic Images. J. Electr. Eng. Technol. 2024, 19, 2739–2755. [Google Scholar] [CrossRef]
- Vasudevan, B.; SenthilKumaran, R.; Immanuel, K.; Karthikeyan, M. Non-Invasive Early Pancreatic Cancer Prediction with Gradient Boosting Algorithms Machine Learning Models with Clinical Dataset Collected from Urinary Biomarkers. In Proceedings of the 2024 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), Chennai, India, 9–10 May 2024; IEEE: New York, NY, USA, 2024; pp. 1–6. [Google Scholar]
- Kumar, N.; Kumar, D. Machine Learning Based Heart Disease Diagnosis Using Non-Invasive Methods: A Review. In Journal of Physics: Conference Series, Proceedings of the International Conference on Mechatronics and Artificial Intelligence (ICMAI) 2021, Gurgaon, India, 27 February 2021; IOP Publishing: Bristol, UK, 2021; Volume 1950, p. 012081. [Google Scholar]
- Bevacqua, E.; Ammirato, S.; Cione, E.; Curcio, R.; Dolce, V.; Tucci, P. The potential of microRNAs as non-invasive prostate cancer biomarkers: A systematic literature review based on a machine learning approach. Cancers 2022, 14, 5418. [Google Scholar] [CrossRef]
- Lekha, S.; Suchetha, M. Recent advancements and future prospects on e-nose sensors technology and machine learning approaches for non-invasive diabetes diagnosis: A review. IEEE Rev. Biomed. Eng. 2020, 14, 127–138. [Google Scholar] [CrossRef] [PubMed]
- Kulkarni, K.; Isselbacher, E.M.; Armoundas, A.A. Artificial Intelligence Based Commercial Non-Invasive and Invasive Devices for Heart Failure Diagnosis and Prediction. In Predicting Heart Failure: Invasive, Non-Invasive, Machine Learning and Artificial Intelligence Based Methods; John Wiley & Sons Ltd.: Hoboken, NJ, USA, 2022; pp. 269–293. [Google Scholar]
- Kainz, B.; Heinrich, M.P.; Makropoulos, A.; Oppenheimer, J.; Mandegaran, R.; Sankar, S.; Deane, C.; Mischkewitz, S.; Al-Noor, F.; Rawdin, A.C.; et al. Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning. NPJ Digit. Med. 2021, 4, 137. [Google Scholar] [CrossRef] [PubMed]
- Ottakath, N.; Akbari, Y.; Al-Maadeed, S.A.; Bouridane, A.; Zughaier, S.M.; Chowdhury, M.E. Bi-attention DoubleUNet: A deep learning approach for carotid artery segmentation in transverse view images for non-invasive stenosis diagnosis. Biomed. Signal Process. Control 2024, 94, 106350. [Google Scholar] [CrossRef]
- Villanueva, M.I.; Garcia-Cañadilla, P.; Camara, O.; Garcia-Criado, A.; Camprecios, G.; Perez-Campuzano, V.; Hernandez-Gea, V.; Turon, F.; Baiges, A.; Sainz, A.L.; et al. Computational Modelling of the Cardiovascular System for the Non-Invasive Diagnosis of Portal Hypertension. In International Conference on Functional Imaging and Modeling of the Heart; Springer: Cham, Switzerland, 2023; pp. 465–474. [Google Scholar]
- Sun, Y.; Zhang, L.; Huang, J.Q.; Su, J.; Cui, L.G. Non-invasive diagnosis of pancreatic steatosis with ultrasound images using deep learning network. Heliyon 2024, 10, e37580. [Google Scholar] [CrossRef] [PubMed]
- Alfi, I.A.; Rahman, M.M.; Shorfuzzaman, M.; Nazir, A. A non-invasive interpretable diagnosis of melanoma skin cancer using deep learning and ensemble stacking of machine learning models. Diagnostics 2022, 12, 726. [Google Scholar] [CrossRef] [PubMed]
- Qu, Y.; Meng, Y.; Fan, H.; Xu, R.X. Low-cost thermal imaging with machine learning for non-invasive diagnosis and therapeutic monitoring of pneumonia. Infrared Phys. Technol. 2022, 123, 104201. [Google Scholar] [CrossRef] [PubMed]
- Prince, E.W.; Hankinson, T.C.; Görg, C. The Iterative Design Process of an Explainable AI Application for Non-Invasive Diagnosis of CNS Tumors: A User-Centered Approach. In Proceedings of the 2023 Workshop on Visual Analytics in Healthcare (VAHC), Melbourne, Australia, 22 October 2023; IEEE: New York, NY, USA, 2023; pp. 7–13. [Google Scholar]
- Adjei, P.E.; Otoo, O.K.; Yang, J.; Rao, N. Towards Non-Invasive Biomarkers in Colorectal Cancer Management: A Study on Integrating Radiomics and Deep Learning-Based Image Processing for Tumor-Stroma Interaction. In Proceedings of the 2024 8th International Conference on Medical and Health Informatics, Yokohama, Japan, 17–19 May 2024; IEEE: New York, NY, USA, 2024; pp. 58–64. [Google Scholar]
- Tamehisa, T.; Sato, S.; Sakai, T.; Maekawa, R.; Tanabe, M.; Ito, K.; Sugino, N. Establishment of Non-Invasive Prediction Models for the Diagnosis of Uterine Leiomyoma Subtypes. Obstet. Gynecol. 2022, 10-1097. [Google Scholar] [CrossRef]
- van der Lubbe, M.F.; Vaidyanathan, A.; de Wit, M.; van den Burg, E.L.; Postma, A.A.; Bruintjes, T.D.; Bilderbeek-Beckers, M.A.; Dammeijer, P.F.; Bossche, S.V.; Van Rompaey, V.; et al. A non-invasive, automated diagnosis of Menière’s disease using radiomics and machine learning on conventional magnetic resonance imaging: A multicentric, case-controlled feasibility study. La Radiol. Medica 2022, 127, 72–82. [Google Scholar] [CrossRef]
- Abdeltawab, H.A.E. Role of Deep Learning Techniques in Non-Invasive Diagnosis of Human Diseases. Ph.D. Thesis, University of Louisville, Louisville, KY, USA, August 2022. [Google Scholar]
- Chen, C.; Guo, X.; Wang, J.; Guo, W.; Ma, X.; Xu, J. The diagnostic value of radiomics-based machine learning in predicting the grade of meningiomas using conventional magnetic resonance imaging: A preliminary study. Front. Oncol. 2019, 9, 1338. [Google Scholar] [CrossRef] [PubMed]
- Hu, P.; Xu, L.; Qi, Y.; Yan, T.; Ye, L.; Wen, S.; Yuan, D.; Zhu, X.; Deng, S.; Liu, X.; et al. Combination of multi-modal MRI radiomics and liquid biopsy technique for preoperatively non- invasive diagnosis of glioma based on deep learning: Protocol for a double-center, ambispective, diagnostical observational study. Front. Mol. Neurosci. 2023, 16, 1183032. [Google Scholar] [CrossRef]
- Cook, D.; Biancalana, M.; Liadis, N.; Lopez Ramos, D.; Zhang, Y.; Patel, S.; Peterson, J.R.; Pfeiffer, J.R.; Cole, J.A.; Antony, A.K. Next generation immuno-oncology tumor profiling using a rapid, non-invasive, computational biophysics biomarker in early-stage breast cancer. Front. Artif. Intell. 2023, 6, 1153083. [Google Scholar] [CrossRef]
- Lorenzovici, N.; Dulf, E.H.; Mocan, T.; Mocan, L. Artificial intelligence in colorectal cancer diagnosis using clinical data: Non-invasive approach. Diagnostics 2021, 11, 514. [Google Scholar] [CrossRef]
- Demir, R.; Koc, S.; Ozturk, D.G.; Bilir, S.; Ozata, H.I.; Williams, R.; Christy, J.; Akkoc, Y.; Tinay, I.; Gunduz-Demir, C.; et al. Artificial intelligence assisted patient blood and urine droplet pattern analysis for non-invasive and accurate diagnosis of bladder cancer. Sci. Rep. 2024, 14, 2488. [Google Scholar] [CrossRef]
- Sajid, M.; Hassan, A.; Khan, D.A.; Khan, S.A.; Bakhshi, A.D.; Akram, M.U.; Babar, M.; Hussain, F.; Abdul, W. AI-CADR: Artificial Intelligence Based Risk Stratification of Coronary Artery Disease using Novel Non-invasive Biomarkers. IEEE J. Biomed. Health Inform. 2024, 28, 7543–7552. [Google Scholar] [CrossRef] [PubMed]
- Pillai, A.; Bliznashki, K.; Hutchison, E.; Kumar, C.; Challis, B.; Patel, M. Machine Learning Enabled Non-invasive Diagnosis of Nonalcoholic Fatty Liver Disease and Assessment of Abdominal Fat from MRI Data. medRxiv 2022. [Google Scholar] [CrossRef]
- Javanshir, H.T.; Malekraeisi, M.A.; Ebrahimi, S.S.S.; Bereimipour, A.; Kashani, S.F.; Bostaki, A.A.; Mahmoodzadeh, H.; Nayernia, K. Investigation of key signaling pathways and appropriate diagnostic biomarkers selection between non-invasive to invasive stages in pancreatic cancer: A computational observation. J. Med. Life 2022, 15, 1143. [Google Scholar] [CrossRef]
- Wang, R.; Wu, Y.; Yu, J.; Yang, G.; Yi, H.; Xu, B. Plasma messenger RNAs identified through bioinformatics analysis are novel, non-invasive prostate cancer biomarkers. OncoTargets Ther. 2020, 13, 541–548. [Google Scholar] [CrossRef] [PubMed]
- Saidijam, M.; Afshar, S.; Taherkhani, A. Identifying Potential Biomarkers in Colorectal Cancer and Developing Non-invasive Diagnostic Models Using Bioinformatics Approaches. Avicenna J. Med. Biochem. 2020, 8, 99–111. [Google Scholar] [CrossRef]
- Rehan, I.; Ullah, R.; Khan, S. Non-invasive Characterization of Glycosuria and Identification of Biomarkers in Diabetic Urine Using Fluorescence Spectroscopy and Machine Learning Algorithm. J. Fluoresc. 2024, 34, 1391–1399. [Google Scholar] [CrossRef] [PubMed]
- Hou, X.; Tian, C.; Liu, W.; Li, Y.; Li, W.; Wang, Z. Construction of artificial intelligence non-invasive diagnosis model for common glomerular diseases based on hyperspectral and urine analysis. Photodiagnosis Photodyn. Ther. 2023, 44, 103736. [Google Scholar] [CrossRef] [PubMed]
- Beltran, J.F.; Wahba, B.M.; Hose, N.; Shasha, D.; Kline, R.P.; Initiative, A.D.N. Inexpensive, non-invasive biomarkers predict Alzheimer transition using machine learning analysis of the Alzheimer’s Disease Neuroimaging (ADNI) database. PLoS ONE 2020, 15, e0235663. [Google Scholar] [CrossRef]
- Han, S.; Chen, C.; Chen, C.; Wu, L.; Wu, X.; Lu, C.; Zhang, X.; Chao, P.; Lv, X.; Jia, Z.; et al. Coupling annealed silver nanoparticles with a porous silicon Bragg mirror SERS substrate and machine learning for rapid non-invasive disease diagnosis. Anal. Chim. Acta 2023, 1254, 341116. [Google Scholar] [CrossRef]
- Duc, L.A.; Tung, N.T.; Oanh, T.T.; Tri, N.Q.; Linh, N.T. Non-invasive in vivo type 2 diabetes Mellitus diagnosis using Raman Spectroscopy in Combination with Machine Learning. Mob. Netw. Appl. 2023, 1–13. [Google Scholar] [CrossRef]
- Wang, L.; Mu, Y.; Zhao, J.; Wang, X.; Che, H. IGRNet: A deep learning model for non-invasive, real-time diagnosis of prediabetes through electrocardiograms. Sensors 2020, 20, 2556. [Google Scholar] [CrossRef] [PubMed]
- Torshizi, H.M.; Khorgami, M.R.; Omidi, N.; Khalaj, F.; Ahmadi, M. Rapid and non-invasive diagnosis of hyperkalemia in patients with systolic myocardial failure using a model based on machine learning algorithms. J. Fam. Med. Prim. Care 2024, 13, 3393–3397. [Google Scholar] [CrossRef] [PubMed]
- Liu, J.; Xu, H.; Wang, J.; Peng, X.; He, C. Non-invasive diagnosis of fetal arrhythmia based on multi-domain feature and hierarchical extreme learning machine. Biomed. Signal Process. Control. 2023, 79, 104191. [Google Scholar] [CrossRef]
- Evans, S.; Booth, A.; Howson, S.; Bacchi, S.; Thiyagarajah, A.; Fitzgerald, J.; Abbas, M.; Kamsani, S.; Emami, M.; Middeldorp, M.; et al. Using ECG and Artificial Intelligence to Predict HbA1c: A Non-Invasive Biomarker for Diabetes Mellitus? Heart Lung Circ. 2024, 33, S392. [Google Scholar] [CrossRef]
- Grochowina, M.; Leniowska, L.; Gala-Błądzińska, A. The prototype device for non-invasive diagnosis of arteriovenous fistula condition using machine learning methods. Sci. Rep. 2020, 10, 16387. [Google Scholar] [CrossRef]
- Wang, J.; Gao, J.; Xiao, J.; Li, J.; Li, H.; Xie, X.; Tan, R.; Jia, Y.; Zhang, X.; Zhang, C.; et al. A new strategy on Early diagnosis of cognitive impairment via novel cross-lingual language markers: A non-invasive description and AI analysis for the cookie theft picture. medRxiv 2024. [Google Scholar] [CrossRef]
- Anand, R.; Reddy, S.; Yadav, D.K. Non-Invasive Parameter-Based Machine Learning Models for Accurate Diagnosis of Congenital Heart Disease. In Proceedings of the 2023 12th International Conference on Advanced Computing (ICoAC), Chennai, India, 17–19 August 2023; IEEE: New York, NY, USA, 2023; pp. 1–6. [Google Scholar]
- Dey, A.; Mittal, S. An Integrated Approach to Non-Invasive Diagnosis of Dementia Using Natural Language Processing and Machine Learning. In Proceedings of the 2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA), Dalian, China, 28–30 October 2022; IEEE: New York, NY, USA, 2022; pp. 75–79. [Google Scholar]
- Emu, M.; Kamal, F.B.; Choudhury, S.; de Oliveira, T.E.A. Assisting the Non-Invasive Diagnosis of Liver Fibrosis Stages Using Machine Learning Methods. In Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC), Montreal, QC, Canada, 20–24 July 2020; IEEE: New York, NY, USA, 2020; pp. 5382–5387. [Google Scholar]
- Maddali, M.V.; Kalra, A.; Muelly, M.; Reicher, J.J. Development and validation of a CT-based deep learning algorithm to augment non-invasive diagnosis of idiopathic pulmonary fibrosis. Respir. Med. 2023, 219, 107428. [Google Scholar] [CrossRef] [PubMed]
- Ye, G.; Wu, G.; Qi, Y.; Li, K.; Wang, M.; Zhang, C.; Li, F.; Wee, L.; Dekker, A.; Han, C.; et al. Non-invasive multimodal CT deep learning biomarker to predict pathological complete response of non-small cell lung cancer following neoadjuvant immunochemotherapy: A multicenter study. J. Immunother. Cancer 2024, 12, e009348. [Google Scholar] [CrossRef] [PubMed]
- Muljono; Wulandari, S.A.; Al Azies, H.; Naufal, M.; Prasetyanto, W.A.; Zahra, F.A. Breaking Boundaries in Diagnosis: Non-Invasive Anemia Detection Empowered by AI. IEEE Access 2024, 12, 9292–9307. [Google Scholar] [CrossRef]
- Sathyaseelan, G.; Maheswari, L.S.; Sophiya, S.; Malini, M.; Santhoshkumar, S.; Vikram, D. Smartphone-Based Strep Throat Detection Using MTCNN: A Deep Learning Approach for Non-Invasive Diagnosis. In Proceedings of the 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Kirtipur, Nepal, 3–5 October 2024; IEEE: New York, NY, USA, 2024; pp. 1778–1781. [Google Scholar]
- Shahrbabak, S.M.; Kim, S.; Youn, B.D.; Cheng, H.M.; Chen, C.H.; Mukkamala, R.; Hahn, J.O. Peripheral artery disease diagnosis based on deep learning-enabled analysis of non-invasive arterial pulse waveforms. Comput. Biol. Med. 2024, 168, 107813. [Google Scholar] [CrossRef] [PubMed]
- Ma, P.; Ge, B.; Yang, H.; Guo, T.; Pan, J.; Wang, W. Application of time-frequency domain and deep learning fusion feature in non-invasive diagnosis of congenital heart disease-related pulmonary arterial hypertension. MethodsX 2023, 10, 102032. [Google Scholar] [CrossRef]
- Hu, J.; Qian, H.; Han, S.; Zhang, P.; Lu, Y. Light-Activated Virtual Sensor Array with Machine Learning for Non-Invasive Diagnosis of Coronary Heart Disease. Nano-Micro Lett. 2024, 16, 274. [Google Scholar] [CrossRef]
- Cao, Y.; Jiang, L.; Zhang, J.; Fu, Y.; Li, Q.; Fu, W.; Zhu, J.; Xiang, X.; Zhao, G.; Kong, D.; et al. A fast and non-invasive artificial intelligence olfactory-like system that aids diagnosis of Parkinson’s disease. Eur. J. Neurol. 2024, 31, e16167. [Google Scholar] [CrossRef] [PubMed]
- Jain, A.; Yadav, K.; Alharbi, H.F.; Tiwari, S. Iot & ai enabled three-phase secure and non-invasive covid 19 diagnosis system. Comput. Mater. Contin. 2022, 71, 423–438. [Google Scholar] [CrossRef]
- Thomas, J.N.; Roopkumar, J.; Patel, T. Machine learning analysis of volatolomic profiles in breath can identify non-invasive biomarkers of liver disease: A pilot study. PLoS ONE 2021, 16, e0260098. [Google Scholar] [CrossRef] [PubMed]
- Roy, S.; Sharma, V.; Ghose, A.; Kimbahune, S.; Pal, A.; Guha, P.K. Machine Learning-Driven Resistive Sensing of Artificial Breath Biomarkers from Lipid Metabolism: A Step Toward Non-Invasive Healthcare. IEEE Sens. J. 2024, 24, 38677–38684. [Google Scholar] [CrossRef]
- Choudhury, K.; Khadanga, A.; Purty, R.S. Computational inhibition of S100A8 (calgranulin A) as a potential non-invasive biomarker for rheumatoid arthritis. Silico Pharmacol. 2024, 12, 25. [Google Scholar] [CrossRef] [PubMed]
- Charu, V.; Liang, J.W.; Mannalithara, A.; Kwong, A.; Tian, L.; Kim, W.R. Benchmarking clinical risk prediction algorithms with ensemble machine learning: An illustration of the superlearner algorithm for the non-invasive diagnosis of liver fibrosis in non-alcoholic fatty liver disease. medRxiv 2023. [Google Scholar] [CrossRef]
- Attia, N.M.; Franzoi, M.; McHale, M.P.; Gargiulo, A.R.; Abrao, M.S.; Vidali, A. IDENTIFICATION OF IMMUNOLOGIC PREDICTIVE BIOMARKERS OF ENDOMETRIOSIS USING A NON-INVASIVE IMMUNE SCREENING TEST IN ASSOCIATION WITH MACHINE LEARNING MODELING. Fertil. Steril. 2023, 120, e226–e227. [Google Scholar] [CrossRef]
- Wang, C.; Tan, X.; Zhu, B.; Zhao, Z.; Wang, Q.; Yang, Y.; Liu, J.; Fu, C.; Wang, J.; Lin, Y. Deep learning-assisted non-invasive pediatric tic disorder diagnosis using EEG features extracted by residual neural networks. J. Radiat. Res. Appl. Sci. 2024, 17, 101151. [Google Scholar] [CrossRef]
- Song, D.; Huang, D.; Qin, J.; Adeleye, A.; Rinaudo, P.; Zablotska, L.; Cedars, M.I. HYPERTENSIVE DISORDERS OF PREGNANCY (HDP) IN PATIENTS WITH UNDERLYING INFERTILITY. Fertil. Steril. 2024, 122, e393–e394. [Google Scholar] [CrossRef]
- Yi, J.; Krusenbaum, L.; Unger, P.; Hüging, H.; Seidel, S.J.; Schaaf, G.; Gall, J. Deep learning for non-invasive diagnosis of nutrient deficiencies in sugar beet using RGB images. Sensors 2020, 20, 5893. [Google Scholar] [CrossRef] [PubMed]
- Anstee, Q.M.; Castera, L.; Loomba, R. Impact of non-invasive biomarkers on hepatology practice: Past, present and future. J. Hepatol. 2022, 76, 1362–1378. [Google Scholar] [CrossRef] [PubMed]
- Rueda, J.R.; Sola, I.; Pascual, A.; Casacuberta, M.S. Non-invasive interventions for improving well-being and quality of life in patients with lung cancer. Cochrane Database Syst. Rev. 2011, 9. [Google Scholar] [CrossRef]
- Dash, S.; Shakyawar, S.K.; Sharma, M.; Kaushik, S. Big data in healthcare: Management, analysis and future prospects. J. Big Data 2019, 6, 54. [Google Scholar] [CrossRef]
- Javaid, M.; Haleem, A.; Singh, R.P. Health informatics to enhance the healthcare industry’s culture: An extensive analysis of its features, contributions, applications and limitations. Inform. Health 2024, 1, 123–148. [Google Scholar] [CrossRef]
Data Type | Modality | Description | Reference(s) |
---|---|---|---|
Imaging | Ultrasound | Deep learning and computational models, including segmentation-based bi-attention DoubleUNet, compression ultrasound interpretation networks, 0D cardiovascular simulations, and AlexNet-based classifiers, were employed to enhance the non-invasive diagnosis of vascular, hepatic, and pancreatic conditions. | [29,30,31,32] |
Dermoscopy | Multi-layer machine learning (decision trees, random forests, SVM, KNN) and deep learning ensembles (MobileNet, Xception, ResNet50, DenseNet121) for melanoma diagnosis using dermoscopic images. | [23,33] | |
RGB | Support vector machine (SVM), K-nearest neighbor (KNN), decision tree, and discriminant analysis models applied to RGB and thermal imaging data for non-invasive pneumonia diagnosis and therapeutic monitoring. | [34] | |
CT scan | Deep learning and machine learning models, including ResNet V2 with a multi-task autoencoder for CNS tumor diagnosis and radiomics-based random forest and gradient boosting machines for colorectal cancer prognosis, were applied to analyze CT scan images non-invasively. | [35,36] | |
MRI | Various machine learning models were applied to MRI images, including ResNet V2 and a multi-task autoencoder for CNS tumor diagnosis, a multi-layer perceptron for Menière’s disease classification, deep learning radiomics with liquid biopsy for glioma diagnosis, CNNs for non-invasive disease detection, integrative biophysical modeling for breast cancer immunotherapy profiling, a non-local ResNet and MMoE for NAFLD assessment, SVM and logistic regression for uterine leiomyoma subtyping, and radiomics-based LDA and SVM for meningioma grading. | [31,37,38,39,40,41,42] | |
Molecular | Blood | Multi-task deep learning, deep and shallow neural networks, ResNet-18, and ensemble machine learning models were used for glioma diagnosis, colorectal cancer detection, bladder cancer classification, and coronary artery disease risk stratification using blood-based biomarkers. | [41,43,44,45] |
ctDNA/RNA/microRNA | Latent Dirichlet allocation (LDA) was used for microRNA biomarker discovery in prostate cancer, while computational frameworks integrating circulating microRNAs, cell-free DNAs, and proteins employed machine learning models for enhanced disease detection and monitoring. | [6,7,26] | |
Microarrays/RNA-seq | Machine learning models, including SVM for colorectal cancer biomarker identification, CNN for NAFLD classification, bioinformatics-driven PPI network analysis for pancreatic cancer biomarkers, and differential expression analysis with machine learning for plasma mRNA-based prostate cancer detection, were applied to microarray and RNA-seq data. | [30,46,47,48,49] | |
Urine | Deep and shallow neural networks for colorectal cancer diagnosis, ResNet-18 for bladder cancer classification using urine droplet patterns, hierarchical cluster analysis for glycosuria and diabetes biomarker identification, and a 34-layer residual network for non-invasive glomerular disease diagnosis using hyperspectral urine analysis were applied to urine-based data. | [43,44,50,51] | |
Plasma | Random forest, gradient boosting, CART, and SVM were used for Alzheimer’s disease prediction based on plasma biomarkers, while bioinformatics-driven differential gene expression analysis and statistical machine learning identified novel plasma mRNA biomarkers for prostate cancer diagnosis. | [48,52] | |
Signal | Spectroscopy | PCA-SVM was used for serum feature extraction and disease classification, while a customized ANN and PCA-SVM were applied for non-invasive type 2 diabetes mellitus diagnosis using spectroscopy-based data. | [53,54] |
ECG | Deep learning and machine learning models, including IGRNet (CNN) for prediabetes diagnosis, random forest with PCA for hyperkalemia classification, hierarchical extreme learning machine (H-ELM) for fetal arrhythmia detection, and a CNN for HbA1c-based diabetes prediction, were applied to ECG-based data. | [55,56,57,58] | |
Acoustic | KNN, SVM, and random forest were used for arteriovenous fistula classification with phono-angiography signals, while logistic regression, SVM, and random forest were applied for cognitive impairment diagnosis using cross-lingual speech features. | [59,60] | |
Clinical | Patient Record | Random forest, gradient boosting, CART, and SVM were used for Alzheimer’s disease prediction based on cognitive scores and genetic risk factors, ANN, random forest, XGBoost, AdaBoost, decision tree, naïve Bayes, logistic regression, and SGD for congenital heart disease diagnosis using electronic health records, a random forest model with NLP for dementia diagnosis using qualitative cognitive assessments, and multi-layer perceptron, random forest, and logistic regression for liver fibrosis staging using clinical parameters. | [24,52,61,62,63] |
Disease Class | Condition | Reference(s) |
---|---|---|
Cancer | Colorectal | [36,43,49] |
Skin | [23,33] | |
NSCLC | [65] | |
Pancreatic | [24,47] | |
Bladder | [44] | |
Prostate | [48] | |
Glioma | [41] | |
Breast | [42] | |
Uterine Fibroid | [37] | |
Cardiovascular | Deep Vein Thrombosis | [29] |
Peripheral Artery Disease | [68] | |
Coronary Heart Disease | [61,69,70] | |
Arrhythmia | [57] | |
Neurodegenerative | Alzheimer’s Disease | [52,60] |
Parkinson’s Disease | [71] | |
Dementia | [52,62] | |
Respiratory | Pneumonia | [34] |
Idiopathic Pulmonary Fibrosis | [64] | |
COVID-19 | [34,72] | |
Metabolic | Diabetic Nephropathy | [51,53] |
Diabetes Mellitus | [32,50,54,58] | |
Autoimmune | Sjogren’s Syndrome | [53] |
Liver | Portal Fibrosis | [63] |
Septa | [63] | |
Cirrhosis | [31,63,73] |
Computational Methodology | Algorithm | Reference(s) |
---|---|---|
Supervised ML | SVM | [22,33,34,49,53,54,56,59,60,61,66,73] |
Random Forest | [22,33,36,45,52,56,59,62,63,65,71] | |
Decision Tree | [34,56,62,63,71,74] | |
Gradient Boosting | [24,33,36,45,52,71] | |
KNN | [24,34,61,73] | |
Logistic Regression | [56,60,61,62,63,77] | |
XGBoost | [24,61,69] | |
LightGBM | [24] | |
Gaussian Naive Bayes | [73] | |
LASSO | [40] | |
Linear Discriminant Analysis | [34,40] | |
Quadratic Discriminant Analysis | [34] | |
CART | [70] | |
Ensemble | [22,33,76] | |
Unsupervised ML | K-Means Clustering | [62] |
Hierarchical Cluster Analysis (HCA) | [50] | |
Gaussian Mixture Models | [35] | |
Deep Learning | ANN | [41,54,61] |
Convolutional Neural Networks | [29,39,46,68] | |
Fully Convolutional Networks | [39] | |
ResNet | [33,35,44,46,51,64,78] | |
AlexNet | [32,55] | |
CapsNet | [72] | |
U-Net | [29,46] | |
ResNeXt | [46] | |
Masked Autoencoder | [65] | |
Principal Component Analysis | [22,34,38,52,53,54,56,59,65,70] | |
t-SNE | [70] | |
Neighborhood Component Analysis | [57] | |
Dimensionality Reduction | Wavelet Entropy | [57] |
Hilbert–Huang Transform | [57] | |
Fast Fourier Transform | [59] | |
Feature Selection and Extraction | SHAP | [35,40,45,60] |
Saliency Maps | [35] | |
Bioinformatics pipeline | [48,49] | |
Other | Cytoscape | [49] |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lazaros, K.; Adam, S.; Krokidis, M.G.; Exarchos, T.; Vlamos, P.; Vrahatis, A.G. Non-Invasive Biomarkers in the Era of Big Data and Machine Learning. Sensors 2025, 25, 1396. https://doi.org/10.3390/s25051396
Lazaros K, Adam S, Krokidis MG, Exarchos T, Vlamos P, Vrahatis AG. Non-Invasive Biomarkers in the Era of Big Data and Machine Learning. Sensors. 2025; 25(5):1396. https://doi.org/10.3390/s25051396
Chicago/Turabian StyleLazaros, Konstantinos, Styliani Adam, Marios G. Krokidis, Themis Exarchos, Panagiotis Vlamos, and Aristidis G. Vrahatis. 2025. "Non-Invasive Biomarkers in the Era of Big Data and Machine Learning" Sensors 25, no. 5: 1396. https://doi.org/10.3390/s25051396
APA StyleLazaros, K., Adam, S., Krokidis, M. G., Exarchos, T., Vlamos, P., & Vrahatis, A. G. (2025). Non-Invasive Biomarkers in the Era of Big Data and Machine Learning. Sensors, 25(5), 1396. https://doi.org/10.3390/s25051396