Treatment Response Prediction in Hepatitis C Patients using Machine Learning Techniques

The proper prognosis of treatment response is crucial in any medical therapy to reduce the effects of the disease and of the medication as well. The mortality rate due to hepatitis c virus (HCV) is high in Pakistan as well as all over the world. During the treatment of any disease, prediction of treatment response against any particular medicine is difficult. This paper focuses on predicting the treatment response of a drug: “L-ornithine L-Aspartate (LOLA)” in hepatitis c patients. We have used various machine learning techniques for the prediction of treatment response, including: “K Nearest Neighbor, kStar, Naive Bayes, Random Forest, Radial Basis Function, PART, Decision Tree, OneR, Support Vector Machine and Multi-Layer Perceptron”. Performance measures used to analyze the performance of used machine learning techniques include, “Accuracy, Recall, Precision, and F-Measure”.

Radiomics, deep learning and early diagnosis in oncology

Medical imaging, including X-ray, computed tomography (CT), and magnetic resonance imaging (MRI), plays a critical role in early detection, diagnosis, and treatment response prediction of cancer. To ease radiologists’ task and help with challenging cases, computer-aided diagnosis has been developing rapidly in the past decade, pioneered by radiomics early on, and more recently, driven by deep learning. In this mini-review, I use breast cancer as an example and review how medical imaging and its quantitative modeling, including radiomics and deep learning, have improved the early detection and treatment response prediction of breast cancer. I also outline what radiomics and deep learning share in common and how they differ in terms of modeling procedure, sample size requirement, and computational implementation. Finally, I discuss the challenges and efforts entailed to integrate deep learning models and software in clinical practice.

Delta radiomics analysis of Magnetic Resonance guided radiotherapy imaging data can enable treatment response prediction in pancreatic cancer

Background Magnetic Resonance Image guided Stereotactic body radiotherapy (MRgRT) is an emerging technology that is increasingly used in treatment of visceral cancers, such as pancreatic adenocarcinoma (PDAC). Given the variable response rates and short progression times of PDAC, there is an unmet clinical need for a method to assess early RT response that may allow better prescription personalization. We hypothesize that quantitative image feature analysis (radiomics) of the longitudinal MR scans acquired before and during MRgRT may be used to extract information related to early treatment response. Methods Histogram and texture radiomic features (n = 73) were extracted from the Gross Tumor Volume (GTV) in 0.35T MRgRT scans of 26 locally advanced and borderline resectable PDAC patients treated with 50 Gy RT in 5 fractions. Feature ratios between first (F1) and last (F5) fraction scan were correlated with progression free survival (PFS). Feature stability was assessed through region of interest (ROI) perturbation. Results Linear normalization of image intensity to median kidney value showed improved reproducibility of feature quantification. Histogram skewness change during treatment showed significant association with PFS (p = 0.005, HR = 2.75), offering a potential predictive biomarker of RT response. Stability analyses revealed a wide distribution of feature sensitivities to ROI delineation and was able to identify features that were robust to variability in contouring. Conclusions This study presents a proof-of-concept for the use of quantitative image analysis in MRgRT for treatment response prediction and providing an analysis pipeline that can be utilized in future MRgRT radiomic studies.

Simple Serum Pancreatic Ductal Adenocarcinoma (PDAC) Protein Biomarkers—Is There Anything in Sight?

A poor PDAC prognosis is due to a lack of effective treatment and late diagnosis. The early detection of PDAC could significantly decrease mortality and save lives. Idealbiomarkers for PDAC should be cost-effective, detectable in easily accessible biological material, and present in sufficient concentration in the earliest possible phase of the disease. This review addresses newly selected, simple protein biomarkers—new ones such as thrombospondin-2, insulin-linked binding protein 2, lysophosphatidic acid, and autotaxin and conventional ones such as Ca19-9, inflammatory factors, and coagulation factors. Their possible use in the early detection of PDAC, differentiation from benign diseases, prognosis, and treatment response prediction is discussed. We also address the usefulness of possible combinations of biomarkers in diagnostic panels.

Deep Learning for Human Disease Detection, Subtype Classification, and Treatment Response Prediction Using Epigenomic Data

Deep learning (DL) is a distinct class of machine learning that has achieved first-class performance in many fields of study. For epigenomics, the application of DL to assist physicians and scientists in human disease-relevant prediction tasks has been relatively unexplored until very recently. In this article, we critically review published studies that employed DL models to predict disease detection, subtype classification, and treatment responses, using epigenomic data. A comprehensive search on PubMed, Scopus, Web of Science, Google Scholar, and arXiv.org was performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Among 1140 initially identified publications, we included 22 articles in our review. DNA methylation and RNA-sequencing data are most frequently used to train the predictive models. The reviewed models achieved a high accuracy ranged from 88.3% to 100.0% for disease detection tasks, from 69.5% to 97.8% for subtype classification tasks, and from 80.0% to 93.0% for treatment response prediction tasks. We generated a workflow to develop a predictive model that encompasses all steps from first defining human disease-related tasks to finally evaluating model performance. DL holds promise for transforming epigenomic big data into valuable knowledge that will enhance the development of translational epigenomics.

Early Bone Marrow Assessment after 7+3 Induction Chemotherapy Is Predictable of Outcome in AML with Adverse Cytogenetics

Introduction Although many new therapeutic agents have been introduced in the field of AML, the most important intensive induction regimen of AML patients is still 7+3 chemotherapy based on cytarabine and anthracycline. Currently, major guidelines recommend to exam bone marrow (BM) assessment in 14-21 days after the initiation of induction to determine whether to proceed with intensification chemotherapy. However, there is no solid evidence that these timings are most optimal. If the evaluation at an earlier time point is prognostic for response, earlier intensification could be considered. In this regard, we investigated if the BM blast rate at the 7th day after the start of 7+3 chemotherapy (D7 BM blast) was useful in predicting the treatment response of induction chemotherapy. Methods We retrospectively collected the data of patients who were newly diagnosed with AML from February 2002 to February 2021, received induction chemotherapy by 7+3, had a D7 BM examination without any intensification. A total of 665 patients were enrolled and we analyzed the prognostic significance of the D7 BM blast for the induction treatment response (complete remission or complete remission with incomplete hematologic recovery (CR/CRi)). In addition, we analyzed whether the predictive significance of the D7 BM blast varies by the patient's cytogenetic features by Medical Research Council classification (MRC risk). Then, we evaluated the diagnostic ability of the D7 BM blast by the receiver operating characteristic (ROC) curve for treatment response prediction. To find an optimal D7 BM blast cut-off value, the value that maximizes Youden's index was investigated. Results Among 665 AML patients who underwent 7+3 without intensification, the proportion of patients who acquired CR/CRi after single induction was 68.3%. A significant decrease in the CR/CRi rate was observed in the intermediate/adverse MRC group according to the increase of the D7 BM blast (tests for the trends in the intermediate and adverse group, p<0.001 and p=0.008, respectively; Figure 1). In univariable/multivariable (using covariates of age, sex, etiology, and MRC risk) logistic regression models, the D7 BM blast showed a significant correlation with the CR/CRi rate in the intermediate/adverse cytogenetic group (Table 1). To evaluate the usability of the D7 BM blast as a predictive tool, the ROC curve for the treatment response prediction was plotted (Figure 2) and the D7 BM blast was significantly predictable only in the adverse MRC risk group (Area under the curve: 0.7007, Mann-Whitney test statistics p=0.002). The D7 blast cut-off in the adverse MRC risk group which maximizes Youden's index was 4-4.9%, near to 5%, which is the cut-off used to evaluate the treatment response. The sensitivity and specificity for treatment response prediction according to D7 BM blast <5% or not were 82.8% and 61.1%, respectively. Conclusion The BM assessment performed at 7 days after 7+3 chemotherapy was available to predict the treatment response in intermediate and adverse cytogenetic risk patients. In particular, it can be practically used in patients with adverse cytogenetics, and a value of around BM blast 5% can be used as cut-off for response prediction. Early intensification in these patients could be considered, which would be beneficial in various aspects such as shorter nadir period or hospital stay and possibly better treatment response compared with the current strategies of later intensification or second induction. Figure 1 Figure 1. Disclosures Kim: Novartis: Research Funding; BMS: Research Funding; Pfizer: Research Funding; ILYANG: Research Funding; Takeda: Research Funding. Lee: Alexion, AstraZeneca Rare Disease: Honoraria, Membership on an entity's Board of Directors or advisory committees. Kim: AbbVie: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; AIMS Biosciense: Consultancy, Honoraria; Amgen: Consultancy, Honoraria; AML-Hub: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; Astellas: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; BL & H: Research Funding; BMS & Celgene: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; Boryung Pharm Co.: Consultancy; Daiichi Sankyo: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; Janssen: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; Handok: Consultancy, Honoraria; LG Chem: Consultancy, Honoraria; Novartis: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; Pfizer: Consultancy, Honoraria; Pintherapeutics: Consultancy, Membership on an entity's Board of Directors or advisory committees; Sanofi Genzyme: Honoraria, Speakers Bureau; SL VaxiGen: Consultancy, Honoraria; VigenCell: Consultancy, Honoraria.

Design of InnoPrimers-Duplex Real-Time PCR for Detection and Treatment Response Prediction of EBV-Associated Nasopharyngeal Carcinoma Circulating Genetic Biomarker

Nasopharyngeal carcinoma (NPC) is an epithelial tumor with high prevalence in southern China and Southeast Asia. NPC is well associated with the Epstein-Barr virus (EBV) latent membrane protein 1 (LMP1) 30 bp deletion by having its vital role in increased tumorigenicity and decreased immune recognition of EBV-related tumors. This study developed an InnoPrimers-duplex qPCR for detection of NPC blood circulating LMP1 30 bp deletion genetic biomarker for early diagnosis and treatment response prediction of NPC patients. The analytical and diagnostic evaluation and treatment response prediction were conducted using NPC patients’ whole blood (WB) and tissue samples and non-NPC cancer patients and healthy individuals’ WB samples. The assay was able to detect as low as 20 ag DNA per reaction (equivalent to 173 copies) with high specificity against broad reference microorganisms and archive NPC biopsy tissue and FNA samples. The diagnostic sensitivity and specificity were 83.3% and 100%, respectively. The 30 bp deletion genetic biomarker was found to be a good prognostic biomarker associated with overall clinical outcome of NPC WHO type III patients. This sensitive and specific assay can help clinicians in early diagnosis and treatment response prediction of NPC patients, which will enhance treatment outcome and lead to better life-saving.