A Study on Improvement of Accuracy of Assistive Artificial Intelligence for Colonoscopy CADe: Study on Improvement of Accuracy of EndoBRAIN-EYE
Ontology highlight
ABSTRACT:
DISEASE(S): Colorectal Tumor
PROVIDER: 103658 | ecrin-mdr-crc |
REPOSITORIES: ECRIN MDR
Similar Datasets
Project description:Primary outcome(s): Diagnostic ability (sensitivity, specificity, accuracy, positive predictive value, and negative predictive value) for lymph node metastasis
| 2724955 | ecrin-mdr-crc
Project description:Interventions: Gold Standard:Pathological test;Index test:1. Endoscopy;
2. Artificial intelligence real-time diagnosis system.
Primary outcome(s): Diagnostic accuracy;Sensitivity;Specificity;Positive predictive value;Negative predictive value
Study Design: Sequential
| 2725610 | ecrin-mdr-crc
Project description:Contemporary analyses focused on a limited number of clinical and molecular features have been unable to accurately predict clinical outcomes in pancreatic ductal adenocarcinoma (PDAC). Here we describe a novel, conceptual approach and use it to analyze clinical, computational pathology, and molecular (DNA, RNA, protein, and lipid) analyte data from 74 patients with resectable PDAC. Multiple, independent, machine learning models were developed and tested on curated singleand multi-omic feature/analyte panels to determine their ability to predict clinical outcomes in patients. The multi-omic models predicted recurrence with an accuracy and positive predictive value (PPV) of 0.90, 0.91, and survival of 0.85, 0.87, respectively, outperforming every singleomic model. In predicting survival, we defined a parsimonious model with only 589 multi-omic analytes that had an accuracy and PPV of 0.85. Our approach enables discovery of parsimonious biomarker panels with similar predictive performance to that of larger and resource consuming panels and thereby has a significant potential to democratize precision cancer medicine worldwide.
2024-01-23 | PXD037038 | Pride
Project description:Contemporary analyses focused on a limited number of clinical and molecular features have been unable to accurately predict clinical outcomes in pancreatic ductal adenocarcinoma (PDAC). Here we describe a novel, conceptual approach and use it to analyze clinical, computational pathology, and molecular (DNA, RNA, protein, and lipid) analyte data from 74 patients with resectable PDAC. Multiple, independent, machine learning models were developed and tested on curated single and multi-omic feature/analyte panels to determine their ability to predict clinical outcomes in patients. The multi-omic models predicted recurrence with an accuracy and positive predictive value (PPV) of 0.90, 0.91, and survival of 0.85, 0.87, respectively, outperforming every single-omic model. In predicting survival, we defined a parsimonious model with only 589 multi-omic analytes that had an accuracy and PPV of 0.85. Our approach enables discovery of parsimonious biomarker panels with similar predictive performance to that of larger and resource consuming panels and thereby has a significant potential to democratize precision cancer medicine worldwide.
2023-10-15 | MSV000093118 | MassIVE
Project description:Primary outcome(s): Predictive value (sensitivity, specificity, accuracy, AUC)
| 2653493 | ecrin-mdr-crc
Project description:PurposeClinical evaluation of eye versions plays an important role in the diagnosis of special strabismus. Despite the importance of versions, they are not standardized in clinical practice because they are subjective. Assuming that objectivity confers accuracy, this research aims to create an artificial intelligence app that can classify the eye versions into nine positions of gaze.MethodsWe analyzed photos of 110 strabismus patients from an outpatient clinic of a tertiary hospital at nine gazes. For each photo, the gaze was identified, and the corresponding version was rated by the same examiner during patient evaluation.ResultsThe images were standardized by using the OpenCV library in Python language, so that the patient's eyes were located and sent to a multilabel model through the Keras framework regardless of the photo orientation. Then, the model was trained for each combination of the following groupings: eyes (left, right), gaze (1 to 9), and version (-4 to 4). Resnet50 was used as the neural network architecture, and the Data Augmentation technique was applied. For quick inference via web browser, the SteamLit app framework was employed. For use in Mobiles, the finished model was exported for use in through the Tensorflow Lite converter.ConclusionsThe results showed that the mobile app might be applied to complement evaluation of ocular motility based on objective classification of ocular versions. However, further exploratory research and validations are required.Translational relevanceApart from the traditional clinical practice method, professionals will be able to envisage an easy-to-apply support app, to increase diagnostic accuracy.
| S-EPMC8212438 | biostudies-literature
Project description:Field Canals Improvement Projects is an important sustainable project to save fresh water in our world. Machine learning and artificial intelligence (AI) needs sufficient dataset size to model and predict the cost and duration of Field Canals Improvement Projects. Therefore, this data paper presents dataset includes the key parameters of such project to be used for analyzing and modelling project cost and duration. The data were acquired based on questionnaire survey and collecting historical cases of Field Canals Improvement Projects. The data consists of the following features: area served, total length of PVC pipe line, number of irrigation values, construction year, geographical zone, cost of FCIP, and duration of FCIP construction. The data can be applied to compare and evaluate the performance of machine learning algorithms for predicting cost and duration.
| S-EPMC7256293 | biostudies-literature
Project description:BACKGROUND:The mitotic count in breast carcinoma is an important prognostic marker. Unfortunately substantial inter- and intra-laboratory variation exists when pathologists manually count mitotic figures. Artificial intelligence (AI) coupled with whole slide imaging offers a potential solution to this problem. The aim of this study was to accordingly critique an AI tool developed to quantify mitotic figures in whole slide images of invasive breast ductal carcinoma. METHODS:A representative H&E slide from 320 breast invasive ductal carcinoma cases was scanned at 40x magnification. Ten expert pathologists from two academic medical centers labeled mitotic figures in whole slide images to train and validate an AI algorithm to detect and count mitoses. Thereafter, 24 readers of varying expertise were asked to count mitotic figures with and without AI support in 140 high-power fields derived from a separate dataset. Their accuracy and efficiency of performing these tasks were calculated and statistical comparisons performed. RESULTS:For each experience level the accuracy, precision and sensitivity of counting mitoses by users improved with AI support. There were 21 readers (87.5%) that identified more mitoses using AI support and 13 reviewers (54.2%) that decreased the quantity of falsely flagged mitoses with AI. More time was spent on this task for most participants when not provided with AI support. AI assistance resulted in an overall time savings of 27.8%. CONCLUSIONS:This study demonstrates that pathology end-users were more accurate and efficient at quantifying mitotic figures in digital images of invasive breast carcinoma with the aid of AI. Higher inter-pathologist agreement with AI assistance suggests that such algorithms can also help standardize practice. Not surprisingly, there is much enthusiasm in pathology regarding the prospect of using AI in routine practice to perform mundane tasks such as counting mitoses.
| S-EPMC7335442 | biostudies-literature
Project description:Background Although artificial intelligence (AI) shows promise across many aspects of radiology, the use of AI to create differential diagnoses for rare and common diseases at brain MRI has not been demonstrated. Purpose To evaluate an AI system for generation of differential diagnoses at brain MRI compared with radiologists. Materials and Methods This retrospective study tested performance of an AI system for probabilistic diagnosis in patients with 19 common and rare diagnoses at brain MRI acquired between January 2008 and January 2018. The AI system combines data-driven and domain-expertise methodologies, including deep learning and Bayesian networks. First, lesions were detected by using deep learning. Then, 18 quantitative imaging features were extracted by using atlas-based coregistration and segmentation. Third, these image features were combined with five clinical features by using Bayesian inference to develop probability-ranked differential diagnoses. Quantitative feature extraction algorithms and conditional probabilities were fine-tuned on a training set of 86 patients (mean age, 49 years ± 16 [standard deviation]; 53 women). Accuracy was compared with radiology residents, general radiologists, neuroradiology fellows, and academic neuroradiologists by using accuracy of top one, top two, and top three differential diagnoses in 92 independent test set patients (mean age, 47 years ± 18; 52 women). Results For accuracy of top three differential diagnoses, the AI system (91% correct) performed similarly to academic neuroradiologists (86% correct; P = .20), and better than radiology residents (56%; P < .001), general radiologists (57%; P < .001), and neuroradiology fellows (77%; P = .003). The performance of the AI system was not affected by disease prevalence (93% accuracy for common vs 85% for rare diseases; P = .26). Radiologists were more accurate at diagnosing common versus rare diagnoses (78% vs 47% across all radiologists; P < .001). Conclusion An artificial intelligence system for brain MRI approached overall top one, top two, and top three differential diagnoses accuracy of neuroradiologists and exceeded that of less-specialized radiologists. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Zaharchuk in this issue.
| S-EPMC7263320 | biostudies-literature
Project description:Rising cancer care costs impose financial burdens on health systems. Applying artificial intelligence to diagnostic algorithms may reduce testing costs and avoid wasteful therapy-related expenditures. To evaluate the financial and clinical impact of incorporating artificial intelligence-based determination of mismatch repair/microsatellite instability status into the first-line metastatic colorectal carcinoma setting, we developed a deterministic model to compare eight testing strategies: A) next-generation sequencing alone, B) high-sensitivity polymerase chain reaction or immunohistochemistry panel alone, C) high-specificity panel alone, D) high-specificity artificial intelligence alone, E) high-sensitivity artificial intelligence followed by next generation sequencing, F) high-specificity artificial intelligence followed by next-generation sequencing, G) high-sensitivity artificial intelligence and high-sensitivity panel, and H) high-sensitivity artificial intelligence and high-specificity panel. We used a hypothetical, nationally representative, population-based sample of individuals receiving first-line treatment for de novo metastatic colorectal cancer (N = 32,549) in the United States. Model inputs were derived from secondary research (peer-reviewed literature and Medicare data). We estimated the population-level diagnostic costs and clinical implications for each testing strategy. The testing strategy that resulted in the greatest project cost savings (including testing and first-line drug cost) compared to next-generation sequencing alone in newly-diagnosed metastatic colorectal cancer was using high-sensitivity artificial intelligence followed by confirmatory high-specificity polymerase chain reaction or immunohistochemistry panel for patients testing negative by artificial intelligence ($400 million, 12.9%). The high-specificity artificial intelligence-only strategy resulted in the most favorable clinical impact, with 97% diagnostic accuracy in guiding genotype-directed treatment and average time to treatment initiation of less than one day. Artificial intelligence has the potential to reduce both time to treatment initiation and costs in the metastatic colorectal cancer setting without meaningfully sacrificing diagnostic accuracy. We expect the artificial intelligence value proposition to improve in coming years, with increasing diagnostic accuracy and decreasing costs of processing power. To extract maximal value from the technology, health systems should evaluate integrating diagnostic histopathologic artificial intelligence into institutional protocols, perhaps in place of other genotyping methodologies.
| S-EPMC8217761 | biostudies-literature