Browse
Submit Data
Databases
API
Help

Dataset Information

32 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

IPMI: Machine Learning-Aided Identification of Parametrial Invasion in Women with Early-Stage Cervical Cancer.

ABSTRACT: Radical hysterectomy is a recommended treatment for early-stage cervical cancer. However, the procedure is associated with significant morbidities resulting from the removal of the parametrium. Parametrial cancer invasion (PMI) is found in a minority of patients but the efficient system used to predict it is lacking. In this study, we develop a novel machine learning (ML)-based predictive model based on a random forest model (called iPMI) for the practical identification of PMI in women. Data of 1112 stage IA-IIA cervical cancer patients who underwent primary surgery were collected and considered as the training dataset, while data from an independent cohort of 116 consecutive patients were used as the independent test dataset. Based on these datasets, iPMI-Econ was then developed by using basic clinicopathological data available prior to surgery, while iPMI-Power was also introduced by adding pelvic node metastasis and uterine corpus invasion to the iPMI-Econ. Both 10-fold cross-validations and independent test results showed that iPMI-Power outperformed other well-known ML classifiers (e.g., logistic regression, decision tree, k-nearest neighbor, multi-layer perceptron, naive Bayes, support vector machine, and extreme gradient boosting). Upon comparison, it was found that iPMI-Power was effective and had a superior performance to other well-known ML classifiers in predicting PMI. It is anticipated that the proposed iPMI may serve as a cost-effective and rapid approach to guide important clinical decision-making.

SUBMITTER: Charoenkwan P

PROVIDER: S-EPMC8391438 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Factors predicting parametrial invasion in patients with early-stage cervical carcinomas.

Project description:We aimed to identify factors predicting parametrial invasion in early-stage cervical cancer patients undergoing radical hysterectomy. We recruited women with invasive cervical cancer who underwent radical hysterectomy at a single medical institute from 2000-2011. The clinical and pathological characteristics and outcomes were retrospectively recorded, and the risk factors for parametrial invasion were analyzed. We enrolled 339 patients, including 7 with stage IA1 carcinomas, 10 with stage IA2, 266 with stage IB1, 39 with stage IB2, 14 with stage IIA1, and 3 with stage IIA2. The majority (237/339, 69.9%) had squamous cell carcinoma, while 32 (12.4%) had parametrial invasion. The 16 patients with stage IB1 tumors and parametrial invasion were older (55.9±9.5vs. 49.0±9.9 years, p = 0.005, Mann-Whitney U test), and had deeper cervical stromal invasion (9.59±4.87 vs. 7.47±5.48 mm, p = 0.048, Mann-Whitney U test), larger tumor size (2.32±1.15 vs. 1.74±1.14cm, p = 0.043, Mann-Whitney U test), higher incidences of lymphovascular space invasion (87.5% vs. 28.8%, p<0.001, chi-square test), and greater lymph node metastasis (68.8% vs. 10.8%, p<0.001, chi-square test) than the 260 patients without parametrial invasion. Among the patients with stage IB1 tumor size >2 cm,10% had parametrial invasion and 24.2% had lymph node metastasis compared with only 4% and 9.4% of stage IB1 patients with a tumor size <2 cm, respectively. Only one (0.9%) of the 109 patients aged less than 50 years had parametrial invasion compared with 6 (9.7%) of the 62 patients aged over 50 years. Patients with stage IA2 and IB1 tumors <2 cm may not need radical hysterectomy owing to the low incidence of parametrial invasion.

| S-EPMC6193633 | biostudies-literature

Identification of a low risk population for parametrial invasion in patients with early-stage cervical cancer.

Project description:BACKGROUND:Recent studies have challenged radical procedures for less extensive surgery in selected patients with early-stage cervical cancer at low risk of parametrial invasion. Our objective was to identify a subgroup of patients at low risk of parametrial invasion among women having undergone surgical treatment. METHODS:Data of 1447 patients with cervical cancer treated between 1996 and 2016 were extracted from maintained databases of 10 French University hospitals. Patients with early-stage (IA2-IIA) disease treated by radical surgery including hysterectomy and trachelectomy, were selected for further analysis. The Kaplan-Meier method was used to estimate the survival distribution. A Cox proportional hazards model including all the parameters statistically significant in univariate analysis, was used to account for the influence of multiple variables. RESULTS:Out of the 263 patients included for analysis, on final pathology analysis 28 (10.6%) had parametrial invasion and 235 (89.4%) did not. Factors significantly associated with parametrial invasion on multivariate analysis were: age?>?65 years, tumor?>?30 mm in diameter measured by MRI, lymphovascular space invasion (LVSI) on pathologic analysis. Among the 235 patients with negative pelvic lymph nodes, parametrial disease was seen in only 7.6% compared with 30.8% of those with positive pelvic nodes (p?<?0.001). In a subgroup of patients presenting tumors?<?30 mm, negative pelvic status and no LVSI, the risk of parametrial invasion fell to 0.6% (1/173 patients). CONCLUSION:Our analysis suggests that there is a subgroup of patients at very low risk of parametrial invasion, potentially eligible for less radical procedures.

| S-EPMC6001133 | biostudies-literature

Predictors for pathological parametrial invasion in clinical stage IIB cervical cancer.

Project description:ObjectiveTo examine predictors of pathological parametrial invasion in clinical stage IIB cervical cancer, and to examine prognostic factors in pathological stage IIB disease.MethodsThis study is an ancillary analysis of a nation-wide retrospective cohort examining 6,003 clinical stage IB-IIB cervical cancers. Women with clinical stage IIB disease who underwent primary radical hysterectomy with lymphadenectomy were examined (n = 714). Multivariate analysis was performed to identify independent clinico-pathological factors for pathological parametrial invasion and to identify independent prognostic factors in pathological stage IIB disease.ResultsParametrial invasion was identified on the surgical specimen in 400 cases (56.0%, 95% confidence interval 52.4-59.7). On multivariate analysis, deep stromal invasion (DSI, adjusted-OR 3.922), multiple pelvic nodal metastases (adjusted-OR 3.266), lympho-vascular space invasion (adjusted-OR 2.333), and uterine corpus invasion (adjusted-OR 1.656) remained independent tumor factors for pathological parametrial invasion. In classification-tree models, tumors with DSI and multiple pelvic nodal metastases had the highest incidence of pathological parametrial invasion (75.0-87.7%); contrary, tumors without DSI had the lowest incidence (21.9%). Among patients with pathological stage IIB disease, the absolute difference in 5-year disease-free survival rates was 57.2%, ranging between 80.9% in those with squamous histology with none/single pelvic nodal metastasis and 23.7% in those with non-squamous histology with multiple pelvic nodal metastases.ConclusionIn clinical stage IIB cervical cancer, accuracy for pathological parametrial invasion is low-modest. With absence of DSI, only one in five clinical stage IIB diseases has pathological stage IIB disease. Survival of pathological stage IIB varies widely and is largely dependent on nodal factors.

| S-EPMC7523386 | biostudies-literature

What are the determinants of parametrial invasion in patients with early stage cervical cancer: A cross sectional study.

Project description:IntroductionThere was an increase in number of patients presented with early-stage cervical cancer (CC). Tumors with favorable pathological features might be candidates for less radical surgery.MethodsWe retrospectively reviewed 700 patients with histologically confirmed CC between January 2011 and March 2020. Chi-square, Fisher's exact tests and multivariate logistic regression analysis were used to assess relations between parametrial involvement (PI) and clinic-pathological variables.ResultsTotal number of 132 patients with stage IA to IIA were eligible to participate. Squamous cell carcinoma was reported in 100 (75.8%) patients, adenocarcinoma and other tumor pathologies were found in 24(18.2%) and 8(6.1%), respectively. Considering the 2018 FIGO stage, 11 (8.4%) patients had IA, 111 (83%%) IB and 10 (7.6%) IIA. Nine patients (6.8%) had PI on permanent pathologic report. Univariate analysis demonstrated that following variables were statistically different between patients with and without PI: age ≥50, tumor size ≥ 3 cm, lower segment involvement, poorly differentiated pathology, deep stromal invasion, pelvic lymph node, lympho-vascular involvement and positive surgical margin (all p values < 0.05). Among these variables only tumor size ≥3 cm (OR: 2.1, 95% CI: 1.11-4.16, p value: 0.02), deep stromal invasion (OR: 2.2, 95% CI: 1.9-7.43, p value: 0.02) and positive surgical margin (OR: 5.1, 95% CI: 3.97-11.15, p value: 0.008) were independent risk factor of PI in multivariate analysis.ConclusionsEarly stage CC might be surgically approached in a more conservative manner if patients have tumor size <3 cm and do not have deep stromal invasion in conization.

| S-EPMC9289433 | biostudies-literature

Parametrial involvement and decreased survival of women with FIGO stage IIIC1 cervical cancer.

Project description:ObjectiveTo evaluate the effect of parametrial status on FIGO stage IIIC1 cervical cancer.MethodsA retrospective study was conducted from June 1, 2009, to December 31, 2018.Patients with stage IIIC1 cervical cancer were included and stratified into two groups based on the status of parametrial involvement. Patients with IIIA or IIIB were selected as control. The primary outcomes are overall survival (OS) and progression-free survival (PFS).ResultsOf 586 patients included, 377 patients were stage IIIC1 (group A) and 209 patients were stage IIIA/IIIB (group B). Compared control, stage IIIC1 was not associated with worse 5-year OS or PFS. Of the stage IIIC1 patients, 58.1% without parametrial involvement (group A1) and 41.9% with parametrial involvement (group A2). Patients of group A1 showed a better prognosis than group A2 both in 5-year rates of OS (79.09% vs. 59.43%, p<0.001) and PFS (73.27% vs. 56.95%, p=0.0002). However, patients of group A1 showed a better prognosis than group B both in OS and PFS. Also, patients of group A2 showed a comparable prognosis to group B both in OS and PFS.ConclusionReclassification of stage IIIC1 cervical cancer without parametrial into a new stage is more appropriate and improves discriminatory ability.

| S-EPMC10323298 | biostudies-literature

A machine learning-based prediction model of pelvic lymph node metastasis in women with early-stage cervical cancer.

Project description:ObjectiveTo develop a novel machine learning-based preoperative prediction model for pelvic lymph node metastasis (PLNM) in early-stage cervical cancer by combining the clinical findings and preoperative computerized tomography (CT) of the whole abdomen and pelvis.MethodsPatients diagnosed with International Federation of Gynecology and Obstetrics stage IA2-IIA1 squamous cell carcinoma, adenocarcinoma, and adenosquamous carcinoma of the cervix who had primary radical surgery with bilateral pelvic lymphadenectomy from January 1, 2003 to December 31, 2020, were included. Seven supervised machine learning algorithms, including logistic regression, random forest, support vector machine, adaptive boosting, gradient boosting, extreme gradient boosting, and category boosting, were used to evaluate the risk of PLNM.ResultsPLNM was found in 199 (23.9%) of 832 patients included. Younger age, larger tumor size, higher stage, no prior conization, tumor appearance, adenosquamous histology, and vaginal metastasis as well as the CT findings of larger tumor size, parametrial metastasis, pelvic lymph node enlargement, and vaginal metastasis, were significantly associated with PLNM. The models' predictive performance, including accuracy (89.1%-90.6%), area under the receiver operating characteristics curve (86.9%-91.0%), sensitivity (77.4%-82.4%), specificity (92.1%-94.3%), positive predictive value (77.0%-81.7%), and negative predictive value (93.0%-94.4%), appeared satisfactory and comparable among all the algorithms. After optimizing the model's decision threshold to enhance the sensitivity to at least 95%, the 'highly sensitive' model was obtained with a 2.5%-4.4% false-negative rate of PLNM prediction.ConclusionWe developed prediction models for PLNM in early-stage cervical cancer with promising prediction performance in our setting. Further external validation in other populations is needed with potential clinical applications.

| S-EPMC10948976 | biostudies-literature

Nomogram Predicting the Likelihood of Parametrial Involvement in Early-Stage Cervical Cancer: Avoiding Unjustified Radical Hysterectomies.

Project description:BACKGROUND:We aimed to establish a tool predicting parametrial involvement (PI) in patients with early-stage cervical cancer and select a sub-group of patients who would most benefit from a less radical surgery. METHODS:We retrospectively reviewed patients from two prospective multicentric databases-SENTICOL I and II-from 2005 to 2012. Patients with early-stage cervical cancer (FIGO 2018 IA with lympho-vascular involvement to IIA1), undergoing radical surgery (hysterectomy or trachelectomy) with bilateral sentinel lymph node (SLN) mapping with no metastatic node or PI on pre-operative imaging, were included. RESULTS:In total, 5.2% patients (11/211) presented a histologic PI. After univariate analysis, SLN status, lympho-vascular space invasion, deep stromal invasion and tumor size were significantly associated with PI and were included in our nomogram. Our predictive model had an AUC of 0.92 (IC95% = 0.86-0.98) and presented a good calibration. A low risk group, defined according to the optimal sensitivity and specificity, presented a predicted probability of PI of 2%. CONCLUSION:Patients could benefit from a two-step approach. Final surgery (i.e. radical surgery and/or lymphadenectomy) would depend on the SLN status and the probability PI calculated after an initial conization with bilateral SLN mapping.

| S-EPMC7408823 | biostudies-literature

Machine learning-aided protein identification from multidimensional signatures.

Project description:The ability to determine the identity of specific proteins is a critical challenge in many areas of cellular and molecular biology, and in medical diagnostics. Here, we present a macine learning aided microfluidic protein characterisation strategy that within a few minutes generates a three-dimensional fingerprint of a protein sample indicative of its amino acid composition and size and, thereby, creates a unique signature for the protein. By acquiring such multidimensional fingerprints for a set of ten proteins and using machine learning approaches to classify the fingerprints, we demonstrate that this strategy allows proteins to be classified at a high accuracy, even though classification using a single dimension is not possible. Moreover, we show that the acquired fingerprints correlate with the amino acid content of the samples, which makes it is possible to identify proteins directly from their sequence without requiring any prior knowledge about the fingerprints. These findings suggest that such a multidimensional profiling strategy can lead to the development of a novel method for protein identification in a microfluidic format.

| S-EPMC8314522 | biostudies-literature

Nanoscale light element identification using machine learning aided STEM-EDS.

Project description:Light element identification is necessary in materials research to obtain detailed insight into various material properties. However, reported techniques, such as scanning transmission electron microscopy (STEM)-energy dispersive X-ray spectroscopy (EDS) have inadequate detection limits, which impairs identification. In this study, we achieved light element identification with nanoscale spatial resolution in a multi-component metal alloy through unsupervised machine learning algorithms of singular value decomposition (SVD) and independent component analysis (ICA). Improvement of the signal-to-noise ratio (SNR) in the STEM-EDS spectrum images was achieved by combining SVD and ICA, leading to the identification of a nanoscale N-depleted region that was not observed in as-measured STEM-EDS. Additionally, the formation of the nanoscale N-depleted region was validated using STEM-electron energy loss spectroscopy and multicomponent diffusional transformation simulation. The enhancement of SNR in STEM-EDS spectrum images by machine learning algorithms can provide an efficient, economical chemical analysis method to identify light elements at the nanoscale.

| S-EPMC7426414 | biostudies-literature

Significance of uterine corpus tumor invasion in early-stage cervical cancer.

Project description:ObjectiveTo examine characteristics and survival outcomes of women with surgically-treated cervical cancer exhibiting uterine corpus tumor invasion.MethodsWe utilized The Surveillance, Epidemiology, and End Results Program to identify cervical cancer patients who underwent hysterectomy between 1973 and 2003. Logistic regression models were used to identify risk factors for uterine corpus tumor invasion on multivariable analysis. Association of uterine corpus tumor invasion and cause-specific survival (CSS) from cervical cancer was examined with Cox proportional hazard regression models on multivariable analysis.ResultsWe identified 837 (4.9%) cases of uterine corpus invasion and 16,237 (95.1%) cases of non-invasion. Median follow-up time was 14.0 years. There were 1642 deaths due to cervical cancer. Uterine corpus invasion was independently associated with older age, non-squamous histology, high-grade tumors, large tumor size, and nodal metastasis on multivariable analysis (all, P < 0.001). On univariable analysis, uterine corpus tumor invasion was significantly associated with decreased CSS compared to the non-invasion (5-year rates, 79.0% versus 94.5%, P < 0.001). After controlling for other significant prognostic factors, uterine corpus tumor invasion remained an independent prognostic factor for decreased CSS (adjusted-hazard ratio 1.45, 95% confidence interval 1.21-1.74). Among stage T1b cases (n = 6730), uterine corpus tumor invasion remained an independent prognostic factor for decreased CSS (adjusted-hazard ratio 1.95, 95%CI 1.47-2.60). Uterine corpus tumor invasion was significantly associated with decreased CSS in stage T1b1 disease (74.5% versus 90.7%, P < 0.001) and in stage T1b2 disease (67.0% versus 79.5%, P = 0.01).ConclusionUterine corpus tumor invasion is an independent prognostic factor for decreased survival of women with early-stage cervical cancer.

| S-EPMC7521086 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data