Mathematical Modelling of Cervical Precancerous Lesion Grade Risk Scores: Linear Regression Analysis of Cellular Protein Biomarkers and Human Papillomavirus E6/E7 RNA Staining Patterns

A Prospective Study on the Progression, Recurrence, and Regression of Cervical Lesions: Assessing Various Screening Approaches

(1) Background: The prediction of cervical lesion evolution is a challenge for clinicians. This prospective study aimed to determine and compare the predictive accuracy of cytology, HPV genotyping, and p16/Ki67 dual staining alone or in combination with personal risk factors in the prediction of progression, regression, or persistence of cervical lesions in human papillomavirus (HPV)-infected patients; (2) Methods: This prospective study included HPV-positive patients with or without cervical lesions who underwent follow-up in a private clinic. We calculated the predictive performance of individual tests (cervical cytology, HPV genotyping, CINtecPlus results, and clinical risk factors) or their combination in the prediction of cervical lesion progression, regression, and persistence; (3) Results: The highest predictive performance for the progression of cervical lesions was achieved by a model comprising a Pap smear suggestive of high-grade squamous intraepithelial lesion (HSIL), the presence of 16/18 HPV strains, a positive p16/Ki67 dual staining result along with the presence of at least three clinical risk factors, which had a sensitivity (Se) of 74.42%, a specificity of 97.92%, an area under the receiver operating curve (AUC) of 0.961, and an accuracy of 90.65%. The prediction of cervical lesion regression or persistence was modest when using individual or combined tests; (4) Conclusions: Multiple testing or new biomarkers should be used to improve HPV-positive patient surveillance, especially for cervical lesion regression or persistence prediction.

Utility of four machine learning approaches for identifying ulcerative colitis and Crohn's disease

Objective

Peripheral blood routine parameters (PBRPs) are simple and easily acquired markers to identify ulcerative colitis (UC) and Crohn's disease (CD) and reveal the severity, whereas the diagnostic performance of individual PBRP is limited. We, therefore used four machine learning (ML) models to evaluate the diagnostic and predictive values of PBRPs for UC and CD.

Methods

A retrospective study was conducted by collecting the PBRPs of 414 inflammatory bowel disease (IBD) patients, 423 healthy controls (HCs), and 344 non-IBD intestinal diseases (non-IBD) patients. We used approximately 70 % of the PBRPs data from both patients and HCs for training, 30 % for testing, and another group for external verification. The area under the receiver operating characteristic curve (AUC) was used to evaluate the diagnosis and prediction performance of these four ML models.

Results

Multi-layer perceptron artificial neural network model (MLP-ANN) yielded the highest diagnostic performance than the other three models in six subgroups in the training set, which is helpful for discriminating IBD and HCs, UC and CD, active CD and remissive CD, active UC and remissive UC, non-IBD and HCs, and IBD and non-IBD with the AUC of 1.00, 0.988, 0.942, 1.00, 0.986, and 0.97 in the testing set, as well as the AUC of 1.00, 1.00, 0.773, 0.904, 1.00 and 0.992 in the external validation set.

Conclusion

PBRPs-based MLP-ANN model exhibited good performance in discriminating between UC and CD and revealing the disease activity; however, a larger sample size and more models need to be considered for further research.

Stochastic dynamics of human papillomavirus delineates cervical cancer progression

Starting from a deterministic model, we propose and study a stochastic model for human papillomavirus infection and cervical cancer progression. Our analysis shows that the chronic infection state as random variables which have the ergodic invariant probability measure is necessary for progression from infected cell population to cervical cancer cells. It is shown that small progression rate from infected cells to precancerous cells and small microenvironmental noises associated with the progression rate and viral infection help to establish such chronic infection states. It implicates that large environmental noises associated with viral infection and the progression rate in vivo can reduce chronic infection. We further show that there will be a cervical cancer if the noise associated with precancerous cell growth is large enough. In addition, comparable numerical studies for the deterministic model and stochastic model, together with Hopf bifurcations in both deterministic and stochastic systems, highlight our analytical results.