Development of a prediction model for pancreatic cancer in patients with type 2 diabetes using logistic regression and artificial neural network models

Hsieh, Meng Hsuen; Sun, Li‐Min; Lin, Cheng‐Li; Hsieh, Meng-Ju; Hsu, Chung Y.; Kao, Chia‐Hung

doi:10.2147/cmar.s180791

Cited by 48 publications

(57 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another study, Wang et al (2007) predicted familial PC risk through a Mendelian model (i.e., PancPRO) that was built by extending the Bayesian modeling framework. The AUCs achieved by these models were 0.72 (Cai et al, 2011), 0.73 (Hsieh et al, 2018), and 0.75 (Wang et al, 2007), respectively. With lower AUCs as compared to the current study and being designed for specific conditions, these studies may not be widely used for the general public.…”

Section: Discussionmentioning

confidence: 98%

Pancreatic Cancer Prediction Through an Artificial Neural Network

Muhammad

Hart

Nartowt

et al. 2019

Front. Artif. Intell.

116

View full text Add to dashboard Cite

Early detection of pancreatic cancer is challenging because cancer-specific symptoms occur only at an advanced stage, and a reliable screening tool to identify high-risk patients is lacking. To address this challenge, an artificial neural network (ANN) was developed, trained, and tested using the health data of 800,114 respondents captured in the National Health Interview Survey (NHIS) and Pancreatic, Lung, Colorectal, and Ovarian cancer (PLCO) datasets, together containing 898 patients diagnosed with pancreatic cancer. Prediction of pancreatic cancer risk was assessed at an individual level by incorporating 18 features into the neural network. The established ANN model achieved a sensitivity of 87.3 and 80.7%, a specificity of 80.8 and 80.7%, and an area under the receiver operating characteristic curve of 0.86 and 0.85 for the training and testing cohorts, respectively. These results indicate that our ANN can be used to predict pancreatic cancer risk with high discriminatory power and may provide a novel approach to identify patients at higher risk for pancreatic cancer who may benefit from more tailored screening and intervention.

show abstract

Section: Discussionmentioning

confidence: 98%

Pancreatic Cancer Prediction Through an Artificial Neural Network

Muhammad

Hart

Nartowt

et al. 2019

Front. Artif. Intell.

116

View full text Add to dashboard Cite

show abstract

“…The application of these studies would improve the classification of the samples in tumor diagnosis and subtyping [18][19][20]. The studies using automatic technics to predict risk/diagnosis had demonstrated a high classification performance, presenting sensitivity > 90% [21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

“…The AI has been used to predict risk/diagnosis using pancreatic image and personal health features [27]. The prediction of pancreatic cancer risk in patients with type 2 diabetes was compared using logistic regression and ANN, again using personal health features and presenting the performance of models predicting the cancer risk factor [24]. There are also AI models to diagnose pancreatic cancer-based in four plasma proteins selected in mass spectra, showing the potential of AI in predicting the status of a sample based on biological markers with high sensitivity (90.9%) and specificity (91.1%) [22].…”

Section: Introductionmentioning

confidence: 99%

PDAC-ANN: an artificial neural network to predict pancreatic ductal adenocarcinoma based on gene expression

2020

View full text Add to dashboard Cite

Background: Although the pancreatic ductal adenocarcinoma (PDAC) presents high mortality and metastatic potential, there is a lack of effective therapies and a low survival rate for this disease. This PDAC scenario urges new strategies for diagnosis, drug targets, and treatment. Methods: We performed a gene expression microarray meta-analysis of the tumor against normal tissues in order to identify differentially expressed genes (DEG) shared among all datasets, named core-genes (CG). We confirmed the CG protein expression in pancreatic tissue through The Human Protein Atlas. It was selected five genes with the highest area under the curve (AUC) among these proteins with expression confirmed in the tumor group to train an artificial neural network (ANN) to classify samples. Results: This microarray included 461 tumor and 187 normal samples. We identified a CG composed of 40 genes, 39 upregulated, and one downregulated. The upregulated CG included proteins and extracellular matrix receptors linked to actin cytoskeleton reorganization. With the Human Protein Atlas, we verified that fourteen genes of the CG are translated, with high or medium expression in most of the pancreatic tumor samples. To train our ANN, we selected the best genes (AHNAK2, KRT19, LAMB3, LAMC2, and S100P) to classify the samples based on AUC using mRNA expression. The network classified tumor samples with an f1-score of 0.83 for the normal samples and 0.88 for the PDAC samples, with an average of 0.86. The PDAC-ANN could classify the test samples with a sensitivity of 87.6 and specificity of 83.1. Conclusion: The gene expression meta-analysis and confirmation of the protein expression allow us to select five genes highly expressed PDAC samples. We could build a python script to classify the samples based on RNA expression. This software can be useful in the PDAC diagnosis.

show abstract

“…The application of these studies would improve the classification of the samples in tumors diagnosis and subtyping [18][19][20]. The studies using automatic technics to predict risk/diagnosis had demonstrated a high classification performance, presenting sensitivity >90% [21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

“…The AI has been used to predict risk/diagnosis using pancreatic image and personal health features [27]. The prediction of pancreatic cancer risk in patients with type 2 diabetes was compared using logistic regression and artificial neural network (ANN), again using personal health features and presenting the performance of models predicting the cancer risk factor [24] . There are also AI models to diagnosis pancreatic cancer-based in four plasma protein selected in mass spectra, showing the potential of AI in predicting the status of the sample based in biological markers with high sensitivity (90.9%) and specificity (91.1%) [22].…”

Section: Introductionmentioning

confidence: 99%

PDAC-ANN: an artificial neural network to predict Pancreatic Ductal Adenocarcinoma based on gene expression

Almeida

Cardoso

Freitas

2019

Preprint

View full text Add to dashboard Cite

Background: Although the pancreatic ductal adenocarcinoma (PDAC) presents high mortality and metastatic potential, there is a lack of effective therapies and a low survival rate for this disease. This PDAC scenario urges new strategies for diagnosis, drug targets, and treatment. Methods:We performed a gene expression microarray meta-analysis of the tumor against healthy tissues in order to identify differentially expressed genes shared among all datasets, named core-genes (CG). We confirmed the pancreatic expressed proteins of the CG through The Human Protein Atlas. The five most expressed proteins in the tumor group were selected to train an artificial neural network to classify samples. 2 Results: This microarray included 110 tumor and 77 healthy samples. We identified a CG composed of 60 genes, 58 upregulated and two downregulated. The upregulated CG included proteins and extracellular matrix receptors linked to actin cytoskeleton reorganization. With the Human Protein Atlas, we verified that thirteen genes of the CG are translated, with high or medium expression in most of the pancreatic tumor samples. To train our artificial neural network, we used the five most expressed genes (KRT19, LAMC2, MELK, MET, TOP2A). The artificial neural network model (PDAC-ANN) classified the train samples with sensitivity of 0.95, specificity of 0.9, and f1-score of 0.93. The PDAC-ANN could classify the test samples with a sensitivity of 0.97, specificity of 0.88, and f1-score 0.94. Conclusion:The gene expression meta-analysis and confirmation of the protein expression allow us to select five genes highly expressed PDAC samples. We could build a python script to classify the samples based on mRNA expression. This software can be useful in the PDAC diagnosis.1 5 migration, and metastasis. The PDAC-ANN trained using gene expression information could classify the samples in normal and PDAC with an f1-score of 0.94 and sensitivity = 0.97. The PDAC-ANN tool can only be used when the gene expression information from KRT19, LAMC2, MELK, MET, and TOP2A are available, in addition to min-max gene expression values rescaling. The PDAC-ANN is a free tool (Additional file 4) that can support in the pancreatic ductal adenocarcinoma diagnosis.

show abstract

Development of a prediction model for pancreatic cancer in patients with type 2 diabetes using logistic regression and artificial neural network models

Cited by 48 publications

References 25 publications

Pancreatic Cancer Prediction Through an Artificial Neural Network

Pancreatic Cancer Prediction Through an Artificial Neural Network

PDAC-ANN: an artificial neural network to predict pancreatic ductal adenocarcinoma based on gene expression

PDAC-ANN: an artificial neural network to predict Pancreatic Ductal Adenocarcinoma based on gene expression

Contact Info

Product

Resources

About