A Wavelet-Based Learning Model Enhances Molecular Prognosis in Pancreatic Adenocarcinoma

Abstract

Genome-wide omics technology boosts deep interrogation into the clinical prognosis and inherent mechanism of pancreatic oncology. Classic LASSO methods coequally treat all candidates, ignoring individual characteristics, thus frequently deteriorating performance with comparatively more predictors. Here, we propose a wavelet-based deep learning method in variable selection and prognosis formulation for PAAD with small samples and multisource information. With the genomic, epigenomic, and clinical cohort information from The Cancer Genome Atlas, the constructed five-molecule model is validated via Kaplan-Meier survival estimate, rendering significant prognosis capability on high- and low-risk subcohorts ( p value < 0.0001), together with three predictors manifesting the individual prognosis significance ( p value: 0.0012~0.024). Moreover, the performance of the prognosis model has been benchmarked against the traditional LASSO and wavelet-based methods in the 3- and 5-year prediction AUC items, respectively. Specifically, the proposed model with discrete stationary wavelet base (bior1.5) overwhelmingly outperformed traditional LASSO and wavelet-based methods (AUC: 0.787 vs. 0.782 and 0.721 for the 3-year case; AUC: 0.937 vs. 0.802 and 0.859 for the 5-year case). Thus, the proposed model provides a more accurate perspective, but with less predictor burden for clinical prognosis in the pancreatic carcinoma study.

Machine learning in the identification of prognostic DNA methylation biomarkers among patients with cancer: a systematic review of epigenome-wide studies

“…In particular, one study (82) applied one-dimensional discrete wavelet transform to pre-selected key genes, and the transformed results were used as the input for the downward convolutional neural network for feature extraction. Afterwards, the top 200 genes were further refined by univariable Cox regression analysis, which were finally used to construct the prognostic model by multivariable Cox regression analysis.…”

“…A few identified studies performed comparative analysis of the autoencoder framework with other methods (49, 52, 65, 76), and results mostly favored the autoencoder approach. Besides, one study showed that wavelet-based deep learning model outperform traditional LASSO and other wavelet-based approaches (82). However, we did not find benchmarking studies comparing the three types of workflows identified by this review.…”

Artificial intelligence in pancreatic cancer

“…These facts make it challenging to predict the prognosis of PC. Due to its excellent computational power, AI was used to analyze PC prognoses, including survival time [204][205][206][207][208][209][210][211][212][213][214][215][216][217][218][219][220][221], recurrence risk [78,[221][222][223][224], metastasis [225][226][227][228][229][230], therapy response [79][80][81][231][232][233][234][235][236][237][238][239][240], etc.…”

“…A wavelet-based DL method was proposed by Tang et al to select variables and predict prognosis for PC by training with multi-omics data (genomic, epigenomic, and clinical cohort information). This method predicts prognosis better than the traditional LASSO model (AUC: 0.937 vs. 0.802) [220]. Beak et al used multi-omics data to analyze survival and recurrence in PC, with data sources including whole-exome sequencing, RNA sequencing, microRNA sequencing, DNA methylation data, and other clinical data.…”

Application of artificial intelligence to pancreatic adenocarcinoma

“…Integrating mRNA profiling, DNA methylation, and corresponding clinical information together, Tang et al (89) established CNN models to predict the 5-year survival rates of PC patients, and their best algorithm achieved an AUC of 0.937.…”