AI for Biomarker Analysis in Early Cancer Detection

Version	Summary	Created by	Modification	Content Size	Created at	Operation
1		Hsin-Yao Wang	--	2721	2024-02-28 15:57:47	\|
2	layout	Jessie Wu	+ 6 word(s)	2727	2024-02-29 02:20:30	\|

This entry is adapted from the peer-reviewed paper 10.3390/cancers16050862

Governments worldwide have prioritized multicancer early detection (MCED) for the better management of cancers. Artificial intelligence (AI) is a promising technology to enhance the performance of MCED. In the field of MCED, applying AI has also proven to be efficient in improving diagnostic performance. Harnessing AI has become a must-use technology in analyzing MCED data because MCED tools typically target tens of analytical targets.

AI multi-cancer early detection (MCED) serum biomarkers

1. Serum Biomarkers as Critical Indicators

1.1. Protein Biomarkers: Unveiling Diagnostic Potential

Cancer cells or other cell types in the tumor microenvironment release soluble molecules that are identified as serum tumor markers by noninvasive diagnostic assays. These molecules ideally detect disease early, predict the response, and aid in monitoring therapies. For example, in breast cancer, different serum markers are carcinoembryonic antigen (CEA), the soluble form of the MUC-1 protein (CA15-3), circulating cytokeratins, such as tissue polypeptide antigen (TPA), tissue polypeptide-specific antigen (TPS) and cytokeratin 19 fragment (CYFRA 21-1), and the proteolytically cleaved ectodomain of the human epidermal growth factor receptor 2 (s-HER2). These markers are used majorly in follow-up ^[1], but are not used in screening breast cancer ^[2].

Protein tumor markers have not been fully exploited clinically both diagnostically and prognostically. Therefore, the expansion from individual protein biomarker analysis to protein panels or proteomes develops a comprehensive prognostic analysis to predict disease onset and progression ^[3]^[4]. The protein panel analysis far exceeds the single-biomarker analysis in facilitating specific intervention or guiding treatment, especially in drug resistance. Challenges prevail in the transition from single biomarkers to proteomic panels, both on the basis of process development and technicality. However, recent advancements in the proteomic techniques have fortified that analysis of multiple proteins simultaneously in the blood, urine, cerebrospinal fluid, or any other biological sample ^[4].

The technical difficulties in tumor marker measurement include errors due to the difference between labs and also within batches. These variation combinations to form a panel result in low robustness and reproducibility. Hence, in the development of a robust panel assay over time and across laboratories, a single analytical parameter determined by a single method permits the quantification of errors and batch variability. Further, results are compared by absolute quantitative technologies rather than relative quantitative techniques. Absolute quantification requires the lack of dependency on affinity reagents, which are instead directed by mass spectrometry-based proteomics ^[5]. The US FDA has approved 15 protein biomarker assays in serum and/or plasma. Of the 15 FDA-approved protein biomarkers for cancer proteins, 9 are applicable for serum and 6 for serum/plasma. Although both plasma and serum are identical in protein composition, the expression or recovery of individual proteins vary greatly. For instance, the free PSA concentration differs in serum and plasma ^[6]. The HUman Proteome Organization recommends plasma for proteomics studies ^[7].

The idea of panel testing for proteomic profiling has emerged as an effective method in the diagnostics of cancer; particularly, cancer proteomics is clinically feasible. The enzyme-linked immunosorbent assay, immunohistochemistry, and flow cytometry system are reliable, sensitive, and widely used in the clinical diagnosis, prognosis, and treatment monitoring of cancer ^[8]. Alternative techniques, like mass spectrometry, protein arrays, and microfluidics, are extensively used and are being developed for clinical application ^[9]. On top of the massive data created by panel testing, proteomic workflows for the targeted analysis of protein panels have improved with highly standardized sample-preparation protocols ^[10], data-independent acquisition techniques ^[4], sensitivity, and faster mass spectrometers conjoined with micro- and analytical flow rate chromatography ^[11]. The absolute quantification has improved the statistical analysis, cross-study, and cross-laboratory comparability, simplifying the accreditation of analytical tests ^[12].

In 2009, OVA1 was approved for the evaluation of ovarian tumors in combination with the measurement of five serum proteins: apolipoprotein A1, β-2 microglobulin, CA -125, transferrin, and transthyretin ^[13]. In 2011, ROMA was approved for the prediction of ovarian malignancy along with two proteins—human epididymis protein 4 and CA-125 ^[14]. For the early detection of cancer, a total of 1261 proteins were identified that were involved in oncogenesis, in tumor angiogenesis, differentiation, proliferation, and apoptosis, in the cell cycle, and in signaling. In as many as 1261 proteins, 9 protein biomarkers have been approved as “tumor-associated antigens” by the USFDA. Although these protein biomarkers have not yet been approved for multicancer early detection (MCED), in many Asian regions, such as China ^[15], Taiwan ^[16], the Republic of Korea ^[17], etc., the use of protein biomarkers for MCED has been put into practice for more than 10 years. The popularity of this approach lies in its convenience, as cancer screening for many different cancer types can be conducted with a simple blood test. This includes many cancer types for which there is no preferred screening method ^[18]. Additionally, the cost of protein tumor marker tests is relatively low; the cost of one marker test may be around USD 10 or even lower, making it financially feasible for widespread use. In terms of the diagnostic performance, using protein biomarker panels can achieve approximately 40% sensitivity and 90% specificity ^[16]. In regions with a high accessibility of follow-up diagnostic approaches (e.g., endoscope, CT, and MRI), this is a convenient and competitive approach. The diagnostic performance of the protein biomarkers is summarized in the supplementary materials (Table S1).

In the post human genome project era, the cost of detecting genes or even genomics has kept dropping, making genetic testing approachable and offering promising biomarkers, like protein biomarkers, for MCED. Additionally, genetic biomarkers provide the possibility to detect cancer-driving mechanisms. Testing genes as the biomarkers for MCED will be addressed in the following section.

1.2. Cell-Free DNA Biomarkers: Unleashing Genomic Clues

Cell-free DNA (cfDNA) are noninvasive markers detected in serum, plasma, urine, and CSF ^[19], and a more favored biomarker for cancer, surpassing the gold-standard approach of biopsy sampling, which is invasive with a restricted frequency of usage and site. It depicts tumor heterogeneity with a comprehensive representation, allowing multiple samplings from a single blood draw and represents various tumor clones and sites, providing a comprehensive representation ^[20]. All cells release cfDNA that may be necrotic or apoptotic. The cfDNA reveals mutations, methylation, and copy number variations that may be related to cancer ^[21]. Hence, its molecular profiling has a potential role in noninvasive cancer management with the advent of ultrasensitive technologies (e.g., NGS, BEAMing (beads, emulsions, amplification, and magnetics), and droplet digital PCR (ddPCR)). It has evolved as a considerable surrogate marker in tumor detection, staging, prognosis, localization, and in the identification of acquired drug resistance mechanisms ^[22].

The sensitivity to detect tumor-derived cfDNA is expressed in terms of the mutant allele fraction (MAF), which is the ratio between the amounts of mutant alleles and wild-type alleles in a sample. The MAF detection limits of quantitative PCR ranges between 10 and 20%. However, variations in PCR techniques, like allele-specific amplification ^[23], allele-specific nonextendable primer blocker PCR ^[24], and peptide nucleic acid-locked nucleic acid PCR clamp ^[25], increase the sensitivity. Several genome-wide sequencing methods have been developed in the last decade. The methods include plasma-Seq ^[26], Parallel Analysis of RNA Ends sequencing ^[27], and modified fast aneuploidy screening test-sequencing ^[28] for cfDNA detection at 5–10% MAF. Targeted sequencing approaches include the exome sequencing ^[29], CAncer Personalized Profiling by deep Sequencing (CAPP-Seq) ^[30], and digital sequencing ^[31]. Targeted sequencing approaches are of high coverage, whereas whole-genome sequencing (WGS) approaches are of low coverage. Targeted approaches detect mutations even at a low ctDNA, whereas WGS assess copy number alteration in ctDNA. A lower MAF is obtained with the digital PCR (dPCR) method, including microfluidic-based ddPCR and BEAMing ^[32] quantified with extreme sensitivity (0.001–0.05% MAF). The multiplexing capabilities are limited, as the primers or probes target specific mutations or loci.

For the purpose of MCED, cfDNA detects a tumor at an asymptomatic stage with a diameter of 5 mm. The ratio of tumor-derived cfDNA to normal cfDNA < 1–100,000 copies (MAF of 0.001%) corresponds to a tumor of 5 mm in diameter ^[33]. In blood, 1 mL of plasma contains approximately 3000 whole-genome equivalents ^[34], and in the total 3 L, plasma represents 9,000,000 copies. In the entire cfDNA population, only one cancer genome originates from a 1 mm diameter tumor, increasing the probability of extracting one tumor-derived cfDNA fragment from a 10 mL blood sample, which is very low. Hence, these available methods detect tumors with a diameter greater than 1 cm (0.5 cm³) ^[33]. Different from protein-based methods, tumor-derived cfDNA are DNA fragments released from dying cancer cells, and DNA copy numbers are limited in a cell. Thus, there is a limit of detection and a potential limit to how early detection can occur. Thus, if a cancer-associated MAF is detected, it is likely cancer. Protein biomarkers are released by cancer cells at a relatively high amount, so are easily detectable early ^[5]^[35]^[36], but lack specificity because protein biomarkers can be released by both cancer cells as well as normal cells.

The cost of cfDNA testing has significantly decreased in recent years, although it is still over five times the price of protein biomarker panels ^[37]. However, it can generally be achieved at a cost below USD 1000. The price reduction may lead to increased accessibility; however, there are still some inherent issues with cfDNA testing that remain unresolved. One critical concern is its short half-life, potentially as brief as a few minutes to hours ^[38]. Such a short half-life would result in an unstable cfDNA quantity in the specimen. Additionally, specimen preservation would pose a challenge, as the cfDNA could degrade within a few hours of in vitro storage. In contrast, protein biomarkers have a half-life lasting several days or even weeks ^[39]^[40]. These inherent issues may be the reasons why the effectiveness of cfDNA testing in MCED is not as promising as initially anticipated. In fact, a study suggests that combining cfDNA with protein biomarker testing does not yield better cancer efficacy than using protein biomarkers alone ^[41]. Further optimization is required for the use of cfDNA testing in MCED. The diagnostic performance of the cfDNA biomarkers is summarized in supplementary materials (Table S1).

2. Synergizing Artificial Intelligence Algorithms for Biomarker Analysis

2.1. Classical Machine-Learning Techniques in Biomarker Interpretation

Harnessing ML in interpreting clinical inputs for classification or prediction is becoming a mainstream application nowadays in the medical field. Several studies have indicated that ML algorithms analyzing clinical ^[42], genetic ^[43], or protein biomarker ^[44] results can provide diagnoses similar to or even better than those made by physicians. What is noteworthy is that ML algorithms demonstrate greater consistency in pattern recognition, reducing interindividual differences. In the medical domain, there exists a wide variety of ML algorithms, including logistic regression, decision trees, random forests, support vector machines, and more ^[45]^[46]. Despite differences in the underlying logic of these algorithms, their design aims to identify specific patterns and relationships between the data and the predicted targets.

In cancer screening or diagnosis studies, the effectiveness of ML algorithms was compared with physician interpretation of tests ^[44]^[47]. In these studies, human physicians used the reference range-based single-threshold method: predicting the probability of cancer occurrence within the next year if any test item exceeded the reference range. Conversely, if all test items fell within the reference ranges, the individuals were predicted not to be at risk of cancer. While this interpretation method is straightforward, the effectiveness of cancer screening is not as high as that achieved by machine-learning algorithms. This suggests that physicians may not be as sensitive to specific data patterns in laboratory test results as ML algorithms. The possible explanation is that ML algorithms detect the “face/pattern of a disease” rather than only a few test items.

While ML algorithms appear to generally outperform physicians in interpreting multiple test items, there does not seem to be a particular advantage among different ML algorithms for lab data-based classification problems in the medical field. Although in individual reports, various algorithms, like the support vector machine ^[47], random forest ^[48], and logistic regression ^[44], have been reported to outperform others. In a review study, it was also noted that other ML algorithms do not show a clear superiority over traditional logistic regression (also categorized as an ML algorithm) ^[49]. In fact, most MCED products still adopt logistic regression as the ML algorithm. Galleri, a cfDNA-based MCED artificial intelligence (AI), is composed of two logistic regression models, one for cancer detection and the other for predicting the tissue of origin ^[50]. Protein biomarker-based MCED products, such as OneTest ^[51] (20/20 GeneSystems) and CancerSEEK (Exact Sciences) ^[52], also revealed the utility of the classical ML algorithms. Overall, despite some ML algorithms seeming more prominent in these studies, their advantages are very limited. In fact, the nature of the laboratory data themselves determines whether such classification problems have good predictive performance. The data have already predetermined the predictive performance, and the choice of which ML algorithm to use does not play a significant role ^[53].

The reason why data predetermine the outcomes can be explained by the fact that the lab data-based AI models are based on lab data, and the lab tests typically have a good signal-to-noise ratio ^[49]. Moreover, these test items have undergone a series of rigorous validations from the development stage, and were implemented in clinical settings for years ^[54]. Thus, the lab test items fundamentally have a certain correlation with the predictive phenotypes or diseases. On top of that, tests like proteomic panels consisting of peptides and proteins would not suffice as biomarkers on their own; instead, acquiring an ML strategy for their interpretation renders good predictive performance ^[55]. On the basis that the data themselves are composed of such strong predictors, ML models built on either theoretical foundations can easily identify hidden patterns in the data. In summary, for medical AI models with lab data as the input, the importance of good data far outweighs the significance of the ML algorithm used.

2.2. Unveiling Deep Learning’s Potential in Biomarker Analysis

In recent years, deep-learning (DL) algorithms have achieved significant success in the field of computer vision. In the domain of medical imaging, DL algorithms are widely employed for the development of image-recognition models. Medical images, such as electrocardiograms, chest X-rays, and computed tomography scans, are particularly well-suited for the application of DL algorithms. In these areas, DL algorithms demonstrate excellent performance, often approaching the level of human experts ^[56]. One key distinction between DL algorithms and traditional ML algorithms lies in feature engineering. Typically, when dealing with high-dimensional data, traditional ML algorithms require the use of feature-extraction or feature-selection methods to reduce the data dimensions in order to improve the prediction accuracy. In contrast to traditional ML algorithms, DL does not necessitate upfront feature engineering ^[57]. Therefore, DL offers the convenience of not requiring these preprocessing steps over traditional ML and provides a distinct advantage in practice.

While DL algorithms have achieved significant success, it appears that they do not necessarily outperform conventional ML algorithms in the medical domain. For instance, the traditional ML–random forest method attained higher diagnostic performance than DL in ultrasound breast lesion classification ^[58]. In a study predicting postoperative patient conditions, DL algorithms did not demonstrate higher predictive capabilities compared to traditional logistic regression ^[59]. In another study predicting drug resistance based on mass spectrometry data, random forest or XGBoost algorithms exhibited higher predictive abilities than DL ^[54]. In the field of MCED, models using DL algorithms to analyze protein biomarker results did not show higher cancer prediction capabilities than traditional ML algorithms like logistic regression ^[15]. In certain data structures where the data themselves contain strong predictors, the need for feature engineering in DL algorithms is not as apparent as in traditional ML algorithms ^[54]. Thus, the performance comparison between DL and ML depends significantly on the data structure inherent to the specific application ^[58]. In situations where there is no advantage in predictive performance, the use of DL algorithms to analyze lab test results becomes debatable. Due to the complex computations within the model, DL algorithms require more processing time to generate classification or prediction results ^[54]. Beyond the longer processing time, DL algorithms also consume more energy compared to traditional ML algorithms to produce predictive outcomes ^[54]. In an era where AI algorithms are gradually becoming a part of daily life, energy-intensive methods pose a higher carbon footprint, eventually facing serious challenges. While there may not be a significant advantage in the predictive performance, certain DL algorithms can assist in addressing clinical challenges encountered in MCED in the real world. Taking the field of predicting cancer risk using protein biomarkers as an example, the test panel provided by each diagnostic institution may vary, with only partial overlap in the panels tested. Additionally, if the items tested for each case only partially overlap at different time points, comparing risk predictions becomes challenging. In this regard, long short-term memory networks, with their flexibility and tolerance for missing values, prove to be a suitable solution for addressing such clinical issues ^[15].

References

Tseng, Y.J.; Huang, C.E.; Wen, C.N.; Lai, P.Y.; Wu, M.H.; Sun, Y.C.; Wang, H.Y.; Lu, J.J. Predicting breast cancer metastasis by using serum biomarkers and clinicopathological data with machine learning technologies. Int. J. Med. Inf. 2019, 128, 79–86.
Bodaghi, A.; Fattahi, N.; Ramazani, A. Biomarkers: Promising and valuable tools towards diagnosis, prognosis and treatment of Covid-19 and other diseases. Heliyon 2023, 9, e13323.
Hartl, J.; Kurth, F.; Kappert, K.; Horst, D.; Mülleder, M.; Hartmann, G.; Ralser, M. Quantitative protein biomarker panels: A path to improved clinical practice through proteomics. EMBO Mol. Med. 2023, 15, e16061.
Messner, C.B.; Demichev, V.; Wendisch, D.; Michalick, L.; White, M.; Freiwald, A.; Textoris-Taube, K.; Vernardis, S.I.; Egger, A.S.; Kreidl, M. Ultra-High-Throughput Clinical Proteomics Reveals Classifiers of COVID-19 Infection. Cell Syst. 2020, 11, 11–24.e4.
Landegren, U.; Hammond, M. Cancer diagnostics based on plasma protein biomarkers: Hard times but great expectations. Mol. Oncol. 2021, 15, 1715–1726.
Vignoli, A.; Tenori, L.; Morsiani, C.; Turano, P.; Capri, M.; Luchinat, C. Serum or Plasma (and Which Plasma), That Is the Question. J. Proteome Res. 2022, 21, 1061–1072.
Rai, A.J.; Gelfand, C.A.; Haywood, B.C.; Warunek, D.J.; Yi, J.; Schuchard, M.D.; Mehigh, R.J.; Cockrill, S.L.; Scott, G.B.; Tammen, H. HUPO Plasma Proteome Project specimen collection and handling: Towards the standardization of parameters for plasma proteome samples. Proteomics 2005, 5, 3262–3277.
Wong, Y.L.; Ramanathan, A.; Yuen, K.M.; Mustafa, W.M.W.; Abraham, M.T.; Tay, K.K.; Rahman, Z.A.A.; Chen, Y. Comparative sera proteomics analysis of differentially expressed proteins in oral squamous cell carcinoma. PeerJ 2021, 9, e11548.
Bader, J.M.; Albrecht, V.; Mann, M. MS-Based Proteomics of Body Fluids: The End of the Beginning. Mol. Cell Proteom. MCP 2023, 22, 100577.
Fu, Q.; Kowalski, M.P.; Mastali, M.; Parker, S.J.; Sobhani, K.; van den Broek, I.; Hunter, C.L.; Van Eyk, J.E. Highly Reproducible Automated Proteomics Sample Preparation Workflow for Quantitative Mass Spectrometry. J. Proteome Res. 2018, 17, 420–428.
Wang, Z.; Tober-Lau, P.; Farztdinov, V.; Lemke, O.; Schwecke, T.; Steinbrecher, S.; Muenzner, J.; Kriedemann, H.; Sander, L.E.; Hartl, J. The human host response to monkeypox infection: A proteomic case series study. EMBO Mol. Med. 2022, 14, e16643.
Percy, A.J.; Yang, J.; Chambers, A.G.; Mohammed, Y.; Miliotis, T.; Borchers, C.H. Protocol for Standardizing High-to-Moderate Abundance Protein Biomarker Assessments Through an MRM-with-Standard-Peptides Quantitative Approach. Adv. Exp. Med. Biol. 2016, 919, 515–530.
Füzéry, A.K.; Levin, J.; Chan, M.M.; Chan, D.W. Translation of proteomic biomarkers into FDA approved cancer diagnostics: Issues and challenges. Clin. Proteom. 2013, 10, 13.
Van Gorp, T.; Cadron, I.; Despierre, E.; Daemen, A.; Leunen, K.; Amant, F.; Timmerman, D.; De Moor, B.; Vergote, I. HE4 and CA125 as a diagnostic test in ovarian cancer: Prospective validation of the Risk of Ovarian Malignancy Algorithm. Br. J. Cancer 2011, 104, 863–870.
Wu, X.; Wang, H.Y.; Shi, P.; Sun, R.; Wang, X.; Luo, Z.; Zeng, F.; Lebowitz, M.S.; Lin, W.Y.; Lu, J.J. Long short-term memory model—A deep learning approach for medical data with irregularity in cancer predication with tumor markers. Comput. Biol. Med. 2022, 144, 105362.
Wen, Y.H.; Chang, P.Y.; Hsu, C.M.; Wang, H.Y.; Chiu, C.T.; Lu, J.J. Cancer screening through a multi-analyte serum biomarker panel during health check-up examinations: Results from a 12-year experience. Clin. Chim. Acta Int. J. Clin. Chem. 2015, 450, 273–276.
Kim, Y.S.; Kang, K.N.; Shin, Y.S.; Lee, J.E.; Jang, J.Y.; Kim, C.W. Diagnostic value of combining tumor and inflammatory biomarkers in detecting common cancers in Korea. Clin. Chim. Acta 2021, 516, 169–178.
Schrag, D.; Beer, T.M.; McDonnell, C.H.; Nadauld, L.; Dilaveri, C.A.; Reid, R.; Marinac, C.R.; Chung, K.C.; Lopatin, M.; Fung, E.T. Blood-based tests for multicancer early detection (PATHFINDER): A prospective cohort study. Lancet 2023, 402, 1251–1260.
Salvi, S.; Gurioli, G.; De Giorgi, U.; Conteduca, V.; Tedaldi, G.; Calistri, D.; Casadio, V. Cell-free DNA as a diagnostic marker for cancer: Current insights. OncoTargets Ther. 2016, 9, 6549–6559.
De Mattos-Arruda, L.; Caldas, C. Cell-free circulating tumour DNA as a liquid biopsy in breast cancer. Mol. Oncol. 2016, 10, 464–474.
Gao, Q.; Zeng, Q.; Wang, Z.; Li, C.; Xu, Y.; Cui, P.; Zhu, X.; Lu, H.; Wang, G.; Cai, S. Circulating cell-free DNA for cancer early detection. Innovation 2022, 3, 100259.
Bronkhorst, A.J.; Ungerer, V.; Holdenrieder, S. The emerging role of cell-free DNA as a molecular marker for cancer management. Biomol. Detect. Quantif. 2019, 17, 100087.
Kalendar, R.; Shustov, A.V.; Akhmetollayev, I.; Kairov, U. Designing Allele-Specific Competitive-Extension PCR-Based Assays for High-Throughput Genotyping and Gene Characterization. Front. Mol. Biosci. 2022, 9, 773956.
Ahmad, E.; Ali, A.; Nimisha; Kumar Sharma, A.; Ahmed, F.; Mehdi Dar, G.; Mohan Singh, A.; Apurva Kumar, A.; Athar, A.; Parveen, F. Molecular approaches in cancer. Clin. Chim. Acta Int. J. Clin. Chem. 2022, 537, 60–73.
Ito, K.; Suzuki, Y.; Saiki, H.; Sakaguchi, T.; Hayashi, K.; Nishii, Y.; Watanabe, F.; Hataji, O. Utility of Liquid Biopsy by Improved PNA-LNA PCR Clamp Method for Detecting EGFR Mutation at Initial Diagnosis of Non-Small-Cell Lung Cancer: Observational Study of 190 Consecutive Cases in Clinical Practice. Clin. Lung Cancer 2018, 19, 181–190.
Heitzer, E.; Haque, I.S.; Roberts, C.E.S.; Speicher, M.R. Current and future perspectives of liquid biopsies in genomics-driven oncology. Nat. Rev. Genet. 2019, 20, 71–88.
Zhai, J.; Arikit, S.; Simon, S.A.; Kingham, B.F.; Meyers, B.C. Rapid construction of parallel analysis of RNA end (PARE) libraries for Illumina sequencing. Methods 2014, 67, 84–90.
Belic, J.; Koch, M.; Ulz, P.; Auer, M.; Gerhalter, T.; Mohan, S.; Fischereder, K.; Petru, E.; Bauernhofer, T.; Geigl, J.B. Rapid Identification of Plasma DNA Samples with Increased ctDNA Levels by a Modified FAST-SeqS Approach. Clin. Chem. 2015, 61, 838–849.
Murtaza, M.; Dawson, S.J.; Tsui, D.W.Y.; Gale, D.; Forshew, T.; Piskorz, A.M.; Parkinson, C.; Chin, S.F.; Kingsbury, Z.; Wong, A.S. Non-invasive analysis of acquired resistance to cancer therapy by sequencing of plasma DNA. Nature 2013, 497, 108–112.
Newman, A.M.; Lovejoy, A.F.; Klass, D.M.; Kurtz, D.M.; Chabon, J.J.; Scherer, F.; Stehr, H.; Liu, C.L.; Bratman, S.V.; Say, C. Integrated digital error suppression for improved detection of circulating tumor DNA. Nat. Biotechnol. 2016, 34, 547–555.
Lanman, R.B.; Mortimer, S.A.; Zill, O.A.; Sebisanovic, D.; Lopez, R.; Blau, S.; Collisson, E.A.; Divers, S.G.; Hoon, D.S.; Kopetz, E.S. Analytical and Clinical Validation of a Digital Sequencing Panel for Quantitative, Highly Accurate Evaluation of Cell-Free Circulating Tumor DNA. PLoS ONE 2015, 10, e0140712.
García-Foncillas, J.; Alba, E.; Aranda, E.; Díaz-Rubio, E.; López-López, R.; Tabernero, J.; Vivancos, A. Incorporating BEAMing technology as a liquid biopsy into clinical practice for the management of colorectal cancer patients: An expert taskforce review. Ann. Oncol. Off. J. Eur. Soc. Med. Oncol. 2017, 28, 2943–2949.
Fiala, C.; Diamandis, E.P. Utility of circulating tumor DNA in cancer diagnostics with emphasis on early detection. BMC Med. 2018, 16, 166.
Manokhina, I.; Singh, T.K.; Peñaherrera, M.S.; Robinson, W.P. Quantification of cell-free DNA in normal and complicated pregnancies: Overcoming biological and technical issues. PLoS ONE 2014, 9, e101500.
Davies, M.P.A.; Sato, T.; Ashoor, H.; Hou, L.; Liloglou, T.; Yang, R.; Field, J.K. Plasma protein biomarkers for early prediction of lung cancer. eBioMedicine 2023, 93, 104686.
Trinidad, C.V.; Pathak, H.B.; Cheng, S.; Tzeng, S.C.; Madan, R.; Sardiu, M.E.; Bantis, L.E.; Deighan, C.; Jewell, A.; Rayamajhi, S. Lineage specific extracellular vesicle-associated protein biomarkers for the early detection of high grade serous ovarian cancer. Sci. Rep. 2023, 13, 18341.
Guerra, C.E.; Sharma, P.V.; Castillo, B.S. Multi-Cancesr Early Detection: The New Frontier in Cancer Early Detection. Annu. Rev. Med. 2024, 75, 67–81.
Tivey, A.; Church, M.; Rothwell, D.; Dive, C.; Cook, N. Circulating tumour DNA—Looking beyond the blood. Nat. Rev. Clin. Oncol. 2022, 19, 600–612.
Han, S.J.; Yoo, S.; Choi, S.H.; Hwang, E.H. Actual half-life of alpha-fetoprotein as a prognostic tool in pediatric malignant tumors. Pediatr. Surg. Int. 1997, 12, 599–602.
Riedinger, J.M.; Wafflart, J.; Ricolleau, G.; Eche, N.; Larbre, H.; Basuyau, J.P.; Dalifard, I.; Hacene, K.; Pichon, M.F. CA 125 half-life and CA 125 nadir during induction chemotherapy are independent predictors of epithelial ovarian cancer outcome: Results of a French multicentric study. Ann. Oncol. Off. J. Eur. Soc. Med. Oncol. 2006, 17, 1234–1238.
Halner, A.; Hankey, L.; Liang, Z.; Pozzetti, F.; Szulc, D.A.; Mi, E.; Liu, G.; Kessler, B.M.; Syed, J.; Liu, P.J. DEcancer: Machine learning framework tailored to liquid biopsy based cancer detection and biomarker signature selection. iScience 2023, 26, 106610.
Lin, W.Y.; Chen, C.H.; Tseng, Y.J.; Tsai, Y.T.; Chang, C.Y.; Wang, H.Y.; Chen, C.K. Predicting post-stroke activities of daily living through a machine learning-based approach on initiating rehabilitation. Int. J. Med. Inf. 2018, 111, 159–164.
Tseng, Y.J.; Wang, H.Y.; Lin, T.W.; Lu, J.J.; Hsieh, C.H.; Liao, C.T. Development of a Machine Learning Model for Survival Risk Stratification of Patients with Advanced Oral Cancer. JAMA Netw. Open 2020, 3, e2011768.
Wang, H.Y.; Hsieh, C.H.; Wen, C.N.; Wen, Y.H.; Chen, C.H.; Lu, J.J. Cancers Screening in an Asymptomatic Population by Using Multiple Tumour Markers. PLoS ONE 2016, 11, e0158285.
Uddin, S.; Khan, A.; Hossain, M.E.; Moni, M.A. Comparing different supervised machine learning algorithms for disease prediction. BMC Med. Inform. Decis. Mak. 2019, 19, 281.
Cruz, J.A.; Wishart, D.S. Applications of machine learning in cancer prediction and prognosis. Cancer Inform. 2007, 2, 59–77.
Wang, H.; Huang, G. Application of support vector machine in cancer diagnosis. Med. Oncol. Northwood Lond. Engl. 2011, 28 (Suppl. 1), S613–S618.
Wang, H.Y.; Chung, C.R.; Chen, C.J.; Lu, K.P.; Tseng, Y.J.; Chang, T.H.; Wu, M.H.; Huang, W.T.; Lin, T.W.; Liu, T.P.; et al. Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin. Microbiol. Spectr. 2021, 9, e0091321.
Christodoulou, E.; Ma, J.; Collins, G.S.; Steyerberg, E.W.; Verbakel, J.Y.; Van Calster, B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J. Clin. Epidemiol. 2019, 110, 12–22.
Liu, M.C.; Oxnard, G.R.; Klein, E.A.; Swanton, C.; Seiden, M.V.; CCGA Consortium. Sensitive and specific multi-cancer detection and localization using methylation signatures in cell-free DNA. Ann. Oncol. Off. J. Eur. Soc. Med. Oncol. 2020, 31, 745–759.
Wang, H.Y.; Chen, C.H.; Shi, S.; Chung, C.R.; Wen, Y.H.; Wu, M.H.; Lebowitz, M.S.; Zhou, J.; Lu, J.J. Improving Multi-Tumor Biomarker Health Check-Up Tests with Machine Learning Algorithms. Cancers 2020, 12, 1442.
Cohen, J.D.; Li, L.; Wang, Y.; Thoburn, C.; Afsari, B.; Danilova, L.; Douville, C.; Javed, A.A.; Wong, F.; Mattox, A. Detection and localization of surgically resectable cancers with a multi-analyte blood test. Science 2018, 359, 926–930.
Cebekhulu, E.; Onumanyi, A.J.; Isaac, S.J. Performance Analysis of Machine Learning Algorithms for Energy Demand–Supply Prediction in Smart Grids. Sustainability 2022, 14, 2546.
Yu, J.R.; Chen, C.H.; Huang, T.W.; Lu, J.J.; Chung, C.R.; Lin, T.W.; Wu, M.H.; Tseng, Y.J.; Wang, H.Y. Energy Efficiency of Inference Algorithms for Clinical Laboratory Data Sets: Green Artificial Intelligence Study. J. Med. Internet Res. 2022, 24, e28036.
Kelly, C.J.; Karthikesalingam, A.; Suleyman, M.; Corrado, G.; King, D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019, 17, 195.
Liu, X.; Faes, L.; Kale, A.U.; Wagner, S.K.; Fu, D.J.; Bruynseels, A.; Mahendiran, T.; Moraes, G.; Shamdas, M.; Kern, C.; et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: A systematic review and meta-analysis. Lancet Digit. Health 2019, 1, e271–e297.
Yang, S.; Zhu, F.; Ling, X.; Liu, Q.; Zhao, P. Intelligent Health Care: Applications of Deep Learning in Computational Medicine. Front. Genet. 2021, 12, 607471.
Wan, K.W.; Wong, C.H.; Ip, H.F.; Fan, D.; Yuen, P.L.; Fong, H.Y.; Ying, M. Evaluation of the performance of traditional machine learning algorithms, convolutional neural network and AutoML Vision in ultrasound breast lesions classification: A comparative study. Quant. Imaging Med. Surg. 2021, 11, 1381–1393.
Rodrigues, A.J.; Schonfeld, E.; Varshneya, K.; Stienen, M.N.; Staartjes, V.E.; Jin, M.C.; Veeravagu, A. Comparison of Deep Learning and Classical Machine Learning Algorithms to Predict Postoperative Outcomes for Anterior Cervical Discectomy and Fusion Procedures with State-of-the-art Performance. Spine 2022, 47, 1637–1644.

© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.

Upload a video for this entry

Information

Subjects: Health Care Sciences & Services

Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to https://encyclopedia.pub/register :

Hsin-Yao Wang

Wan-Ying Lin

Chenfei Zhou

Zih-Ang Yang

Sriram Kalpana

Michael S. Lebowitz

View Times: 69

Update Date: 29 Feb 2024

Table of Contents

Video Upload Options

Confirm