Accurate early-stage colorectal cancer detection through analysis of cell-free circulating tumor DNA (ctDNA) methylation patterns.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 3606-3606
Author(s):  
James M. Kinross ◽  
Pol Canal-Noguer ◽  
Marko Chersicola ◽  
Primož Knap ◽  
Marko Bitenc ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Machine Learning ◽  
Cancer Detection ◽  
Learning Algorithm ◽  
Early Stage ◽  
Country Of Origin ◽  
Stage I ◽  
Stage Iii ◽  
Machine Learning Algorithm ◽  
Crc Screening

3606 Background: Colorectal cancer (CRC) screening programs suffer from poor uptake and biomarkers have limited diagnostic accuracy. The measurement of the methylation status of tumor-derived cell-free DNA in plasma may address these challenges. We used a targeted methylation panel, tumor-derived signal deduction and machine learning algorithm to refine a blood test for the detection of early-stage CRC. Methods: This was a prospective, international multicenter observational cohort study. Plasma samples were collected either prior to a scheduled colonoscopy as part of standard colorectal cancer screening or prior to colonic surgery for primary CRC. Differentially methylated regions (DMRs) were initially selected by analyzing CRC and control tissue samples with whole genome bisulfite sequencing. A targeted sequencing assay was designed to capture these DMRs in plasma ctDNA. Individual sequencing reads were evaluated for cancer-specific methylation signal and scores calculated for each DMR in a sample. A panel of methylation scores originating from 203 DMRs was used in a prediction model building and validated in a test cohort of patients. Results: Calculated scores were used to train a machine learning model on 68 ctDNA samples from 18 early stage (I-II) and 16 late-stage (III-IV) CRC patients and 34 age, BMI, gender and country of origin matched neoplasia-free controls (median age 63 [50-74], mean BMI 27 [19.5-37], female 50%, Spanish and Ukrainian population, distal cancers 50%). This model was then applied to an independent set of subjects from Spanish, Ukraine and Germany, including 36 stage I-IV cancer patients (median age 61.5 [55-82], BMI 28 [16-39], female 47%, 42% of the tumors were distal) and 159 age and sex matched controls. 87 of the control patients had a negative colonoscopy finding (cNEG), 19 had hyperplastic polyps (HP), 37 had small non-advanced adenomas (NAA) and 16 were diagnosed with other benign gastrointestinal diseases (GID). The model correctly classified 92% (33/36) of CRC patients. Sensitivity per cancer stage ranged from 83% (5/6) for stage I, 92% (11/12) for stage II, 92% (12/13) for stage III to 100% (5/5) for stage IV. Specificity of the model was 97% (154/159), with 100% (37/37) NAA, 94% (15/16) GID, 95% (18/19) HP and 97% cNEG patients correctly identified. Lesion location, gender, BMI, age and country of origin were not significantly correlated to prediction outcome. Conclusions: Methylation sequencing data analyzed using read-wise scoring approach combined with a machine-learning algorithm is highly diagnostic for early-stage (I-II) CRCs (89% sensitivity at 97% specificity). This method could serve as the basis for a highly accurate and minimally invasive blood-based CRC screening test with significant implications for the clinical utility of ctDNA in early-stage cancer detection.

scholarly journals Dementia Prognostication using Machine Learning

2020 ◽  
Vol 9 (4) ◽  
pp. 1199-1203
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neurological Disease ◽  
Learning Algorithm ◽  
Early Stage ◽  
Machine Learning Algorithms ◽  
Machine Learning Algorithm ◽  
Treatment Analysis ◽  
Disease Analysis ◽  
Correct Implementation

Since the introduction of Machine Learning in the field of disease analysis and diagnosis, it has been revolutionized the industry by a big margin. And as a result, many frameworks for disease prognostics have been developed. This paperfocuses on the analysis of three different machine learning algorithms – Neural network, Naïve bayes and SVM on dementia. While the paper focuses more on comparison of the three algorithms, we also try to find out about the important features and causes related to dementia prognostication. Dementia is a severe neurological disease which renders a person unable to use memory and logic if not treated at the early stage so a correct implementation of fast machine learning algorithm may increase the chances of successful treatment. Analysis of the three algorithms will provide algorithm pathway to do further research and create a more complex system for disease prognostication.

Multimodal circulating tumor DNA (ctDNA) colorectal neoplasia detection assay for asymptomatic and early-stage colorectal cancer (CRC).

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 3536-3536
Author(s):  
Jeeyun Lee ◽  
Hee C Kim ◽  
Seung Tae Kim ◽  
Yupeng He ◽  
Paul Sample ◽  
...  
Keyword(s):  
Early Stage ◽  
Colorectal Neoplasia ◽  
High Sensitivity ◽  
High Specificity ◽  
Stage I ◽  
Stage Iii ◽  
Average Risk ◽  
Crc Screening ◽  
Large Patient ◽  
Detection Assay

3536 Background: To improve average risk CRC screening compliance, additional options are needed, especially options that address patient and provider reported barriers such as time and convenience. LUNAR-2 is a multimodal blood-based colorectal neoplasia detection assay incorporating ctDNA assessment of somatic mutations and tumor derived methylation and fragmentomic patterns, aimed to maximize sensitivity for early stage CRC detection. We evaluated this test in a large patient cohort with newly diagnosed CRC. Methods: Individuals diagnosed with CRC between 2013-2016 consented to provide blood samples prior to surgical resection. Those treated with neoadjuvant chemotherapy were excluded. Isolated plasma samples (median 3mL from EDTA) from 434 individuals were analyzed with LUNAR-2 (Guardant Health, USA) and included in the analysis. Median age at CRC diagnosis was 63 years (range 28 - 89) and 41% were female. Control samples were from 271 age-matched cancer free individuals. “ctDNA detected” and “ctDNA not detected” results were generated by a model trained on a separate sample set (N=614) from both cancer free individuals and those with CRC. Calling threshold was determined based on this held-out set to target 90% specificity. ctDNA results and clinical characteristics were correlated. Results: Overall CRC sensitivity was 91% (393/434), with high sensitivity across all stages; 88% Stage I/II, 93% Stage III (Table). Specificity was 94% (255/271). There was no difference in sensitivity when excluding those with early (<45 years) or late (>84 years) onset CRC (90% sensitivity; 388/429; p=0.95; 88% Stage I/II, 93% Stage III). There were no differences in sensitivity for asymptomatic CRC (88%) compared to symptomatic CRC (91%; p=0.4; Table). However, higher cell-free DNA tumor fractions were observed in the symptomatic cohort. Sensitivity for detection of right-sided and left-sided CRC was similar (93% vs. 90%; p=0.5; Table). Conclusions: In this large early-stage CRC cohort, multimodal ctDNA assessment has high sensitivity for CRC detection with high specificity. Equivalent sensitivity in the asymptomatic cohort suggests this test will have clinically meaningful performance in an average risk screening population. A prospective registrational study is ongoing to evaluate the test in an average risk CRC screening cohort.[Table: see text]

Machine Learning Algorithms to Detect Subclinical Keratoconus: Systematic Review (Preprint)

2021 ◽  
Author(s):  
Howard Maile ◽  
Ji-Peng Olivia Li ◽  
Daniel Gore ◽  
Marcello Leucci ◽  
Padraig Mulholland ◽  
...  
Keyword(s):  
Machine Learning ◽  
Disease Progression ◽  
Learning Algorithm ◽  
Early Stage ◽  
Demographic Data ◽  
Learning Algorithms ◽  
Detailed Comparison ◽  
Machine Learning Algorithms ◽  
Machine Learning Algorithm ◽  
Clinical Measures

BACKGROUND Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage corneal collagen cross linking can prevent disease progression and further visual loss. Whilst advanced forms are easily detected, reliably identifying subclinical disease can be problematic. A number of different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of single or multiple clinical measures such as corneal imaging, aberrometry, or biomechanical measurements. OBJECTIVE To survey and critically evaluate the literature on algorithmic detection of subclinical keratoconus and equivalent definitions. METHODS We performed a structured search of the following databases: Medical Literature Analysis and Retrieval System Online (MEDLINE), Excerpta Medica Database (EMBASE), Web of Science and Cochrane from Jan 1, 2010 to Oct 31, 2020. We included all full text studies that have used algorithms for the detection of subclinical keratoconus. We excluded studies that did not perform validation. RESULTS We compared the parameters measured and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm and key results are reported in this study. CONCLUSIONS Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Presently there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early intervention to prevent disease progression. CLINICALTRIAL N/A

Vitamin D levels and its relationship with successful completion of adjuvant chemotherapy and improved survival in early stage colorectal cancer patients.

2017 ◽  
Vol 35 (4_suppl) ◽  
pp. 549-549
Author(s):  
Khurram Bilal Tariq ◽  
Aaron Gopal ◽  
Asha Nayak-Kapoor
Keyword(s):  
Colorectal Cancer ◽  
Vitamin D ◽  
Overall Survival ◽  
Cancer Survival ◽  
Early Stage ◽  
Neoadjuvant Treatment ◽  
Stage I ◽  
Stage Iii ◽  
Vitamin D Levels ◽  
Sufficient Vitamin

549 Background: Vitamin D deficiency is associated with increased colorectal cancer (CRC) risk and decreased colorectal cancer survival. The purpose of this study was to determine the effect of colorectal cancer adjuvant treatment on the vitamin D status in CRC. Methods: 102 patients at the GCC with Stage I-III CRC were selected between 2009 -2011. A retrospective analyses of baseline vitamin D in these patients was made to determine if vitamin D level predicts survival. Those patients who have received neoadjuvant treatment were excluded. Only patients who had a baseline vitamin D level drawn at baseline were included. Vitamin D sufficiency was defined as serum level of 30ng/ml or greater, insufficiency as 20 to 29ng/ml and deficiency as less than 20ng/ml. Results: Mean age of the patients was 76.4 years. 45 % were Stage I , 35% comprised Stage II and 25% were Stage III. 25OHD Level was insufficient in 85% and deficient in 10% and sufficient in only 5% of the patients. In the patients who received chemotherapy (45% ), those with sufficient vitamin D levels had a statistically longer survival than those with deficient levels (p<0.002). Also the patients with sufficient levels, they were more likely to complete the 6 months of chemotherapy than those with deficient levels (p<0.006). The median Vitamin D level for all 102 patients was 22.8ng/ml. Patients with sufficient vitamin D levels were more likely to have lower body mass index (p<0.01). There was no correlation between race and level of vitamin D. Patients with a sufficient vitamin D Level (25 patients), had a survival which was significantly more than those with deficient levels (p<0.001). Patients with sufficient vitamin D levels were more likely to have stage I and II disease than stage III ( p <0.04). For each stage of CRC, patients with sufficient vitaminD levels had a better overall survival than those with deficient vitamin D level(p<0.01). Conclusions: Patients with sufficient levels of vitamin D are associated with better overall survival in early stage CRC. Whether aggressive vitamin D repletion would improve the outcome in vitamin D deficient CRC patients remains unknown.

Machine learning algorithm for characterizing risks of hypertension, at an early stage in Bangladesh

2021 ◽  
Vol 15 (3) ◽  
pp. 877-884
Author(s):  
Md. Merajul Islam ◽  
Md. Jahanur Rahman ◽  
Dulal Chandra Roy ◽  
Most. Tawabunnahar ◽  
Rubaiyat Jahan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Early Stage ◽  
Machine Learning Algorithm

An automated lung cancer detection system based on machine learning algorithm

2021 ◽  
Vol 40 (4) ◽  
pp. 6355-6364
Author(s):  
S. Lalitha
Keyword(s):  
Machine Learning ◽  
Lung Cancer ◽  
Cancer Detection ◽  
Learning Algorithm ◽  
Detection System ◽  
Imaging Techniques ◽  
Medical Science ◽  
Lung Cancer Mortality ◽  
Machine Learning Algorithm ◽  
Lung Cancer Detection

Cancer has been one of the most serious health challenges to the human kind for a long period of time. Lung cancer is the most prevalent type of cancer which shows higher death rates. However, lung cancer mortality rates can be tracked by periodic screening. With the advanced medical science, the society has reaped numerous benefits with respect to screening equipments. Computed Tomography (CT) is one of the popular imaging techniques and this work utilizes the CT images for lung cancer detection. An early detection of lung cancer could prolong the lifetime of the patient and is made effortless by the latest screening technology. Additionally, the accuracy of disease detection can be enhanced with the help of the automated systems, which could support the healthcare experts in effective diagnosis. This article presents an automated lung cancer detection system equipped with machine learning algorithm, which can differentiate between the benign, malignant and normal classes of lung cancer. The accuracy of the proposed lung cancer detection method is around 98.7%, which is superior to the compared approaches.

scholarly journals Acute Diseases Prognosis using Chatbot

2021 ◽  
Vol 9 (VII) ◽  
Author(s):  
Shivanand Tiwari
Keyword(s):  
Machine Learning ◽  
Healthcare Professionals ◽  
Learning Algorithm ◽  
Early Stage ◽  
Machine Learning Algorithm ◽  
Patient Needs ◽  
Healthcare Organizations ◽  
Physician Time ◽  
Consultant Doctor

The role of chatbots in healthcare is to help free-up valuable physician-time by reducing or eliminating unnecessary doctor’s appointments. As the increase in cost, various healthcare organizations are looking for different ways to manage cost while improving the user’s experience. As we know there is shortage of healthcare professionals that makes it increasingly necessary for us to augment technology with health facilities in order to allow doctors to focus on more critical patient needs. Keeping this in Mind we are aiming to develop a Project that will basically ask for Symptoms from the Patient and perform the Prognosis on the basis of already developed dataset. The Machine Learning Algorithm will work on that dataset of symptoms and their prognosis to tell exactly what has happened to the Patient and will help to Reach the Desired Consultant/Doctor with respect to the Prognosis. It will also help the Patients to get Useful Information regarding different diseases that may help to deal with some Chronic Diseases at an early Stage!’

Sign in / Sign up

Export Citation Format

Share Document