scholarly journals Application and Performance of Artificial Intelligence Technology in Oral Cancer Diagnosis and Prediction of Prognosis: A Systematic Review

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1004
Author(s):  
Sanjeev B. Khanagar ◽  
Sachin Naik ◽  
Abdulaziz Abdullah Al Kheraif ◽  
Satish Vishwanathaiah ◽  
Prabhadevi C. Maganur ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Oral Cancer ◽  
Cox Regression ◽  
Eligibility Criteria ◽  
Cox Regression Analysis ◽  
Electronic Search ◽  
Clinical Strategies ◽  
Artificial Intelligence Technology ◽  
And Performance ◽  
Prediction Of Prognosis

Oral cancer (OC) is a deadly disease with a high mortality and complex etiology. Artificial intelligence (AI) is one of the outstanding innovations in technology used in dental science. This paper intends to report on the application and performance of AI in diagnosis and predicting the occurrence of OC. In this study, we carried out data search through an electronic search in several renowned databases, which mainly included PubMed, Google Scholar, Scopus, Embase, Cochrane, Web of Science, and the Saudi Digital Library for articles that were published between January 2000 to March 2021. We included 16 articles that met the eligibility criteria and were critically analyzed using QUADAS-2. AI can precisely analyze an enormous dataset of images (fluorescent, hyperspectral, cytology, CT images, etc.) to diagnose OC. AI can accurately predict the occurrence of OC, as compared to conventional methods, by analyzing predisposing factors like age, gender, tobacco habits, and bio-markers. The precision and accuracy of AI in diagnosis as well as predicting the occurrence are higher than the current, existing clinical strategies, as well as conventional statistics like cox regression analysis and logistic regression.

ORGANISATIONAL SLACK AND NEW PRODUCT TIME TO MARKET PERFORMANCE

2018 ◽  
Vol 22 (04) ◽  
pp. 1850034 ◽  
Author(s):  
GREGORY STOCK ◽  
NOEL GREIS ◽  
WILLIAM FISCHER
Keyword(s):  
Video Game ◽  
Cox Regression ◽  
Market Performance ◽  
New Product ◽  
Exact Nature ◽  
Time To Market ◽  
Cox Regression Analysis ◽  
And Performance ◽  
Using Data ◽  
The Relationship

Using archival data from two different industries, this paper examines the relationship between organisational slack and new product time to market performance. Prior research has shown that there is a relationship between slack and performance, but this prior research has primarily considered slack as it relates to financial performance or the innovativeness of a firm or its products. In this paper, using data from the computer modem and video game industries across more than 40 years, we test the hypotheses relating organisational slack time to market performance for new products. Cox regression analysis in general supports the hypothesised relationships, although there are some differences in the exact nature of the relationship across the two industries. We conclude by discussing the implications of these results for research and practice.

scholarly journals Effect of extending the original eligibility criteria for the “CROSS” neoadjuvant chemoradiotherapy on toxicity and survival in esophageal cancer.

2017 ◽  
Vol 35 (4_suppl) ◽  
pp. 187-187
Author(s):  
Jan-Binne Hulshoff ◽  
Ellen C. de Heer ◽  
Daphne H. Klerk ◽  
Derk Jan De Groot ◽  
John Theodorus Plukker ◽  
...  
Keyword(s):  
Esophageal Cancer ◽  
Cox Regression ◽  
Locally Advanced ◽  
Neoadjuvant Chemoradiotherapy ◽  
Postoperative Mortality ◽  
Hematologic Toxicity ◽  
Eligibility Criteria ◽  
Cox Regression Analysis ◽  
Group I ◽  
The Cross

187 Background: Patients with curable esophageal cancer (EC) which proceed beyond the original CROSS eligibility criteria are also treated with neoadjuvant chemoradiotherapy (nCRT). This study assessed the effect of extending the CROSS eligibility criteria for nCRT on treatment related toxicity and overall survival (OS) in EC. Methods: Included were 161 patients with locally advanced EC (T1N1-3/T2-4aN0-3/M0), treated with the CROSS schedule followed by esophagectomy. Group 1 (N = 90) consisted of patients which met the CROSS criteria and patients in group 2 (N = 71) met the extended eligibility criteria, i.e. including a tumor length of > 8 cm (N = 23), > 10% weight loss (N = 35), > 2 – 4 cm extension in the stomach (N = 21), celiac lymph node metastasis (N = 13), and/or age > 75 years (N = 2). We assessed the differences in hematologic toxicity (≥ grade 3) and 90-day postoperative mortality. Moreover, we assessed the prognostic value on OS with multivariate Cox regression analysis. Results: No difference was found in hematologic toxicity and 90-day mortality. The OS differed significantly (P = 0.003), with a median of 37.3 (95% CI 10.56 – 64.0) and 17.2 (95% CI 13.8 – 20.6) months in group I and II, respectively. Pathological N-stage (P = 0.024), ypT-stage (P = 0.044), and group II (P = 0.006) were independent prognostic factors for OS. Conclusions: Extension of the CROSS study eligibility criteria for nCRT did not affect hematologic toxicity and postoperative mortality, but was prognostic for OS.

scholarly journals Post-chemotherapy miR-146a expression and its prognostic potential in oral cancer patients

2021 ◽  
Vol 20 (10) ◽  
pp. 2205-2211
Author(s):  
Yuanyuan Sun ◽  
Leilei Li ◽  
Wensong Hao
Keyword(s):  
Oral Cancer ◽  
Cancer Patients ◽  
Cox Regression ◽  
Expression Level ◽  
Individual Risk ◽  
Cox Regression Analysis ◽  
Oral Cancer Patients ◽  
Risk Parameters ◽  
Individual Risk Factors

Purpose: To determine miR-146a expression level after chemotherapy in oral cancer patients, and itsprognostic value.Methods: Quantitative reverse transcription polymerase chain reaction (qRT-PCR) was used for the determination of miR-146 expression levels. Based on the results, the analysis of the miR-146a expression in oral cancer patients was performed by drawing ROC curve to provide information on the prognostic value of miR-146a. The survival of the patients was monitored over a period of 5 years. The patients were categorized into high- and low-expression groups, and multivariate Cox regression analysis method was adopted to provide a more comprehensive analysis of individual risk factors influencing the prognosis of oral cancer.Results: The miR-146a expression level in patients after chemotherapy was lower than that in patients before they received chemotherapy (p < 0.05). The specificity of using miR-146a to predict oral cancer was 76.83 %, the sensitivity 69.44 %, and the area between the curve and x-axis 0.78. In contrast, the survival level was significantly greater in high-expression patients (p < 0.05).Conclusion: The independent risk parameters for buccal carcinoma are drinking, smoking, chronic leukoplakia, and miR-146a.

scholarly journals NDRG2 combined with EGFR improved its prognostic value for lung adenocarcinoma

2019 ◽  
Author(s):  
Bo Yang ◽  
Xiao-Ping Li ◽  
Hong-Gang Zhou ◽  
Tao Jiang ◽  
Ting Xiao ◽  
...  
Keyword(s):  
Lung Adenocarcinoma ◽  
Cox Regression ◽  
Growth Factor Receptor ◽  
Prognostic Indicators ◽  
Clinicopathological Parameters ◽  
Clinical Value ◽  
Cox Regression Analysis ◽  
Egfr Expression ◽  
Serum Carcinoembryonic Antigen ◽  
Prediction Of Prognosis

Abstract Background N-Myc downstream-regulated gene2 (NDRG2) plays an important role in lung adenocarcinoma (LUAD). Epidermal growth factor receptor (EGFR) mutation has significantly improved prognosis in patients with adenocarcinoma. We aimed to elucidate the clinical value of NDRG2/EGFR as a prediction of prognosis in patients with lung adenocarcinoma.Materials and Methods Immunohistochemistry and western blot analysis were conducted to detect the expression of NDRG2 protein. Association between NDRG2/EGFR expression and clinicopathological parameters of the patients were examined. Serum Carcinoembryonic antigen (CEA) level was examined prior to treatment in patients with LUAD. Patients’ survival rate was assessed by Kaplan–Meier. Candidates for independent prognostic biomarkers were analyzed using a COX proportional hazard model.Results NDRG2 levels were significantly decreased in patients with lung adenocarcinoma. NDRG2 levels were positively correlated with CEA and EGFR. Advanced stages were significantly associated with low expression of NDRG2. Patients with NDRG2-high combined with EGFR-positive expression had the best prognosis during the 5-year follow-up period. Meanwhile, COX regression analysis showed that the conjoined expressions of NDRG2-low/EGFR-positive, NDRG2-high/EGFR-positive and vascular invasion were independent prognostic indicators for lung adenocarcinoma.Conclusion NDRG2 is of more prognosis value as the biomarker for lung adenocarcinoma when analyzed combined with the EGFR expression.

scholarly journals The use and performance of artificial intelligence applications in dental and maxillofacial radiology: A systematic review

2020 ◽  
Vol 49 (1) ◽  
pp. 20190107 ◽  
Author(s):  
Kuofeng Hung ◽  
Carla Montalvao ◽  
Ray Tanaka ◽  
Taisuke Kawai ◽  
Michael M. Bornstein
Keyword(s):  
Artificial Intelligence ◽  
Systematic Review ◽  
Clinical Practice ◽  
Diagnostic Performance ◽  
Clinical Applications ◽  
Quality Analysis ◽  
Maxillofacial Radiology ◽  
Diagnosis Of Osteoporosis ◽  
Electronic Search ◽  
And Performance

Objectives: To investigate the current clinical applications and diagnostic performance of artificial intelligence (AI) in dental and maxillofacial radiology (DMFR). Methods: Studies using applications related to DMFR to develop or implement AI models were sought by searching five electronic databases and four selected core journals in the field of DMFR. The customized assessment criteria based on QUADAS-2 were adapted for quality analysis of the studies included. Results: The initial electronic search yielded 1862 titles, and 50 studies were eventually included. Most studies focused on AI applications for an automated localization of cephalometric landmarks, diagnosis of osteoporosis, classification/segmentation of maxillofacial cysts and/or tumors, and identification of periodontitis/periapical disease. The performance of AI models varies among different algorithms. Conclusion: The AI models proposed in the studies included exhibited wide clinical applications in DMFR. Nevertheless, it is still necessary to further verify the reliability and applicability of the AI models prior to transferring these models into clinical practice.

Predictive Value of Gene Expression with Respect to IgVH Mutational Status and Survival in Chronic Lymphocytic Leukemia.

Blood ◽  
2004 ◽  
Vol 104 (11) ◽  
pp. 1913-1913
Author(s):  
Mars B. Van’t Veer ◽  
Anne Brooymans ◽  
Anton W. Langerak ◽  
Wilfried J. Graveland ◽  
Kirsten Van Lom ◽  
...  
Keyword(s):  
Chronic Lymphocytic Leukemia ◽  
Predictive Value ◽  
Cox Regression ◽  
Lymphocytic Leukemia ◽  
P Value ◽  
Mrna Levels ◽  
Cox Regression Analysis ◽  
Mutational Status ◽  
Igvh Mutational Status ◽  
Prediction Of Prognosis

Abstract Background: Chronic Lymphocytic Leukemia (CLL) has a variable clinical course, of which IgVH mutational status of the malignant B cells is a strong independent predictor for outcome. Objective: We studied the expression of 5 different genes for their value to predict IgVH mutational status and overall survival (OS). Methods: mRNA levels were quantified by real time PCR in lymphoprep separated but unsorted blood samples from 110 morphologically and fenotypically characterised CLL patients for the following genes: ZAP70, lipoprotein lipase (LPL), ADAM29, KIAA0610 and nRIP1. Expression levels were compared wih respect to IgVH mutational status (mutation = % germline < 98%), using logistic regression and with respect to OS (= time from day of laboratory tests to death due to any cause), using Cox regression analysis. Results: The predictive value of the expression of these 5 genes for IgVH mutational status is shown in table 1. Each of these genes showed to be an independent marker for the prediction of IgVH mutational status. LPL as a single marker was the best predictor for mutation. These factors taken together had a high predictive value towards mutational IgVH status (area under ROC curve = 0.93). table 1 N Odds ratio P value ZAP70 no 85 1 (>5.2) yes 25 0.098 0.002 LPL no 73 1 (>0.04) yes 37 0.029 <0.001 ADAM29 no 73 1 (>30) yes 37 6.61 0.012 KIAA0610 no 81 1 (>0.25) yes 29 0.19 0.045 NRIP1 no 88 1 (>10) yes 22 48.73 0.008 The predictive value of IgVH mutation and the expression of these 5 genes for OS is shown in table 2. From the six parameters tested, IgVH mutational status and LPL were predictors for OS at a significant level of 5%, while ZAP70 was of borderline significance. table 2 Conclusion: measured in unsorted CLL samples, all genes, and especially LPL, had predictive value towards the presence of IgVH mutation. Expression of LPL and absence of mutation were adverse prognostic factors for survival. Thus, the replacement of the assessment of both IgVH mutational status and ZAP70 by assessment of LPL levels for the prediction of prognosis in CLL patients may be considered. N survival at 24months P value mutation no 36 70% yes 44 93% 0.041 ZAP70 no 66 87% yes 18 70% 0.078 LPL no 55 94% yes 29 66% 0.001 ADAM29 no 57 84% yes 27 84% 0.486 KIAA0610 no 63 88% yes 21 71% 0.133 NRIP no 71 81% yes 13 100% 0.167

scholarly journals Overexpression of Keratin17 is Associated With Prognosis of Oral Cancer in the Chinese Population

2020 ◽  
Author(s):  
Lili Wang ◽  
Hongguang Song ◽  
Shiming Yang
Keyword(s):  
Oral Cancer ◽  
Prognostic Value ◽  
Cox Regression ◽  
Prognostic Biomarker ◽  
Human Cancer ◽  
Clinical Stage ◽  
Cancer Tissue ◽  
Cox Regression Analysis ◽  
Kaplan Meier ◽  
Cancer Tissues

Abstract Background: Oral cancer represents an common cancer among head and neck malignancies. The early metastasis contributes the poor prognosis of this disease. Keratin (KRT) family has ever been found to be involved in some crucial biological processes in normal cells and human cancer cells. As a member of this family, keratin 17 (KRT17) has been studied in some different cancers. In the present study, we aimed at assess the prognostic value of KRT17 in patients with oral cancer.Methods: Expression of KRT17 in 135 paired oral cancer tissues and noncancerous tissues was estimated by using quantitative Real-Time RT-PCR (qRT-PCR). The prognostic value of KRT17 was assessed with Kaplan-Meier survival analysis and multivariate Cox regression analysis.Results: Upregulated expression of KRT17 was detected in oral cancer tissues compared with the matched normal tissues (P<0.001). The expression of KRT17 was found associated with lymph node metastasis (P=0.025) and clinical stage (P=0.005). The Kaplan-Meier survival curves showed that the patients with high KRT17 expression possessed worse overall survival than those with low level cases (log-rank P=0.000). From the data of Cox analysis, we considered the KRT17 expression was an independent prognostic biomarker in oral cancer patients with HR of 2.489, 95% CI of 1.333-4.648 and P of 0.004.Conclusion: In summary, the expression of KRT17 was found upregulated in oral cancer tissue specimens and it was proved to serve as an independent prognostic biomarker in patients with oral cancer.

scholarly journals Relationship of Common Variants in miR-27a-3p Gene with Susceptibility and Prognosis of Oral Cancer

2020 ◽  
Author(s):  
Lili Wang ◽  
Hongguang Song ◽  
Shiming Yang
Keyword(s):  
Regression Analysis ◽  
Oral Cancer ◽  
Cancer Patients ◽  
Prognostic Value ◽  
Cox Regression ◽  
Poor Overall Survival ◽  
Cox Regression Analysis ◽  
Kaplan Meier ◽  
Oral Cancer Patients ◽  
Cancer Tissues

Abstract Background: miR-27a-3p has been found dysexpressed in various cancers. The aim of the present study was to clarify the prognostic value of miR-27a-3p in patients with oral cancer.Methods: We used quantitative real-time polymerase chain reaction (qRT-PCR) assay to detect the expression of miR-27a-3p in the tissue of oral cancer and adjacent normal specimens. The association of miR-27a-3p with clinicopathological characteristics was analyzed via the Chi-square test. Kaplan-Meier survival and Cox regression analysis were performed to evaluate the prognostic value of miR-27a-3p in oral cancer patients.Results: The down-regulated expression of miR-27a-3p was found in oral cancer tissues compared with the matched noncancerous samples (P<0.05). And its expression was influenced by TNM stage (P=0.032), T stage (P=0.014) and lymph node metastasis (P=0.025). Kaplan–Meier analysis result showed that the decreased level of miR-27a-3p expression was associated with a poor overall survival of oral cancer patients. Additionally, multivariate cox regression analysis revealed that the low expression of miR-27a-3p was an independent prognostic maker in oral cancer patients (HR=0.462, 95% CI=0.223-0.957, P=0.038).Conclusions: Taken together, the expression pattern of miR-27a-3p was decreased in oral cancer tissues. The decreased expression of miR-27a-3p was a potential prognostic biomarker in patients with oral cancer.

Sign in / Sign up

Export Citation Format

Share Document