AI models predicting breast cancer distant metastasis using LightGBM with clinical blood markers and ultrasound maximum diameter
Ontology highlight
ABSTRACT:
SUBMITTER: Tan Y
PROVIDER: S-EPMC11226620 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Metastasis of cancer is directly related to death in almost all cases, however a lot is yet to be understood about this process. Despite advancements in the available radiological investigation techniques, not all cases of Distant Metastasis (DM) are diagnosed at initial clinical presentation. Also, there are currently no standard biomarkers of metastasis. Early, accurate diagnosis of DM is however crucial for clinical decision making, and planning of appropriate management strategies. Previous works have achieved little success in attempts to predict DM from either clinical, genomic, radiology, or histopathology data. In this work we attempt a multimodal approach to predict the presence of DM in cancer patients by combining gene expression data, clinical data and histopathology images. We tested a novel combination of Random Forest (RF) algorithm with an optimization technique for gene selection, and investigated if gene expression pattern in the primary tissues of three cancer types (Bladder Carcinoma, Pancreatic Adenocarcinoma, and Head and Neck Squamous Carcinoma) with DM are similar or different. Gene expression biomarkers of DM identified by our proposed method outperformed Differentially Expressed Genes (DEGs) identified by the DESeq2 software package in the task of predicting presence or absence of DM. Genes involved in DM tend to be more cancer type specific rather than general across all cancers. Our results also indicate that multimodal data is more predictive of metastasis than either of the three unimodal data tested, and genomic data provides the highest contribution by a wide margin. The results re-emphasize the importance for availability of sufficient image data when a weakly supervised training technique is used. Code is made available at: https://github.com/rit-cui-lab/Multimodal-AI-for-Prediction-of-Distant-Metastasis-in-Carcinoma-Patients.
| S-EPMC10203594 | biostudies-literature
Project description:PurposePatients with cancer often present with a hypercoagulable state, which is closely associated with tumor progression. The purpose of this study was to assess the diagnostic efficacy of D-dimer in predicting distant metastasis in colorectal cancer (CRC).MethodsThis study included 529 patients diagnosed with CRC at our hospital between January 2020 and December 2022. Plasma coagulation indicators and tumor markers were collected prior to treatment and their diagnostic efficacy for predicting CRC metastasis was assessed by receiver operating characteristic (ROC) curves. Independent risk factors for evaluating tumor metastasis were obtained by multivariate logistic regression analysis.ResultsThe level of D-dimer in the metastatic group was significantly higher than that in the non-metastatic group (P<0.001). The results of the multiple logistic regression analysis indicated that lower level of prealbumin and platelet, and higher level of glucose, CEA and D-dimer were independent risk factors for distant metastasis in patients with CRC (P<0.05, respectively). The combination of prealbumin, glucose, D-dimer, platelet and tumor markers (PRE2) was found to be significantly more effective in predicting metastasis of CRC when compared to the combination of tumor marker alone (PRE1, P<0.001).ConclusionPlasma D-dimer may be a novel tumor marker for screening metastases of CRC.
| S-EPMC11244829 | biostudies-literature
Project description:Distant metastasis (DM) is the main cause of treatment failure in locally advanced rectal cancer. Adjuvant chemotherapy is usually used for distant control. However, not all patients can benefit from adjuvant chemotherapy, and particularly, some patients may even get worse outcomes after the treatment. We develop and validate an MRI-based radiomic signature (RS) for prediction of DM within a multicenter dataset. The RS is proved to be an independent prognostic factor as it not only demonstrates good accuracy for discriminating patients into high and low risk of DM in all the four cohorts, but also outperforms clinical models. Within the stratified analysis, good chemotherapy efficacy is observed for patients with pN2 disease and low RS, whereas poor chemotherapy efficacy is detected in patients with pT1-2 or pN0 disease and high RS. The RS may help individualized treatment planning to select patients who may benefit from adjuvant chemotherapy for distant control.
| S-EPMC7452897 | biostudies-literature
Project description:We aimed to evaluate whether radiomics analysis based on gray-scale ultrasound (US) can predict distant metastasis of follicular thyroid cancer (FTC). We retrospectively included 35 consecutive FTCs with distant metastases and 134 FTCs without distant metastasis. We extracted a total of 60 radiomics features derived from the first order, shape, gray-level cooccurrence matrix, and gray-level size zone matrix features using US imaging. A radiomics signature was generated using the least absolute shrinkage and selection operator and was used to train a support vector machine (SVM) classifier in five-fold cross-validation. The SVM classifier showed an area under the curve (AUC) of 0.90 on average on the test folds. Age, size, widely invasive histology, extrathyroidal extension, lymph node metastases on pathology, nodule-in-nodule appearance, marked hypoechogenicity, and rim calcification on the US were significantly more frequent among FTCs with distant metastasis compared to those without metastasis (p < 0.05). Radiomics signature and widely invasive histology were significantly associated with distant metastasis on multivariate analysis (p < 0.01 and p = 0.003). The classifier using the results of the multivariate analysis showed an AUC of 0.93. The radiomics signature from thyroid ultrasound is an independent biomarker for noninvasively predicting distant metastasis of FTC.
| S-EPMC7408789 | biostudies-literature
Project description:BackgroundThe purpose of this study was to investigate the predictive accuracy of erythrocyte count and maximum tumor diameter to maximum kidney diameter ratio (TKR) in patients with renal cell carcinoma (RCC).MethodsWe retrospectively analyzed the clinicopathological epidemiological characteristics of patients with RCC in the First Hospital of Shanxi Medical University from 2010 to 2014. Among them, 295 cases with complete follow-up data at the time of visit were selected. We collected data including erythrocyte counts and length of each diameter line of the tumor and kidney. To predict the prognosis of RCC, receiver operating characteristic (ROC) curve analysis was used to calculate the cutoff value of each parameter.ResultsOf the 295 included patients, 199 (67.5%) were male, 96 (32.5%) were female, and the mean (± SD) age was 56.45±11.03 years. The area under the curve (AUC) of the erythrocyte count and the TKR for predicting the prognosis of RCC were 0.672 (SD 0.031; P<0.001) and 0.800 (SD 0.030; P<0.001), respectively. When the cutoff value of the erythrocyte count and TKR count were 3.975 and 0.452, the highest Youden index values were 0.309 and 0.685, and the corresponding sensitivity and specificity were 0.826 and 0.685, and 0.483 and 1.000, respectively.ConclusionsAn erythrocyte count <3.975×1012/L and a TKR >0.452 were found to be risk factors for poor prognosis in patients with RCC.
| S-EPMC9360514 | biostudies-literature
Project description:This study aimed to establish and validate prognostic nomogram models for patients who underwent 131I therapy for thyroid cancer with distant metastases. The cohort was divided into training (70%) and validation (30%) sets for nomogram development. Univariate and multivariate Cox regression analyses were used to identify independent predictors for overall survival (OS) and progression-free survival (PFS). Nomograms were developed based on these predictors, and Kaplan-Meier curves were constructed for validation. Among 451 patients who were screened, 412 met the inclusion criteria and were followed-up for a median duration of 65.2 months. The training and validation sets included 288 and 124 patients, respectively. Pathological type, first 131I administrated activity, and lesion 131I uptake in lesions were independent predictors for PFS. For OS, predictors included gender, age, metastasis site, first 131I administrated activity, 131I uptake, pulmonary lesion size, and stimulated thyroglobulin levels. These predictors were used to construct nomograms for predicting PFS and OS. Low-risk patients had significantly longer PFS and OS compared to high-risk patients, with 10-year PFS rates of 81.1% vs. 51.9% and 10-year OS rates of 86.2% vs. 37.4%. These may aid individualized prognostic assessment and clinical decision-making, especially in determining the prescribed activity for the first 131I treatment.
| S-EPMC11747094 | biostudies-literature
Project description:Distant metastasis (DM) is relatively uncommon in T1 stage gastric cancer (GC). The aim of this study was to develop and validate a predictive model for DM in stage T1 GC using machine learning (ML) algorithms. Patients with stage T1 GC from 2010 to 2017 were screened from the public Surveillance, Epidemiology and End Results (SEER) database. Meanwhile, we collected patients with stage T1 GC admitted to the Department of Gastrointestinal Surgery of the Second Affiliated Hospital of Nanchang University from 2015 to 2017. We applied seven ML algorithms: logistic regression, random forest (RF), LASSO, support vector machine, k-Nearest Neighbor, Naive Bayesian Model, Artificial Neural Network. Finally, a RF model for DM of T1 GC was developed. The AUC, sensitivity, specificity, F1-score and accuracy were used to evaluate and compare the predictive performance of the RF model with other models. Finally, we performed a prognostic analysis of patients who developed distant metastases. Independent risk factors for prognosis were analysed by univariate and multifactorial regression. K-M curves were used to express differences in survival prognosis for each variable and subvariable. A total of 2698 cases were included in the SEER dataset, 314 with DM, and 107 hospital patients were included, 14 with DM. Age, T-stage, N-stage, tumour size, grade and tumour location were independent risk factors for the development of DM in stage T1 GC. A combined analysis of seven ML algorithms in the training and test sets found that the RF prediction model had the best prediction performance (AUC: 0.941, Accuracy: 0.917, Recall: 0.841, Specificity: 0.927, F1-score: 0.877). The external validation set ROCAUC was 0.750. Meanwhile, survival prognostic analysis showed that surgery (HR = 3.620, 95% CI 2.164-6.065) and adjuvant chemotherapy (HR = 2.637, 95% CI 2.067-3.365) were independent risk factors for survival prognosis in patients with DM from stage T1 GC. Age, T-stage, N-stage, tumour size, grade and tumour location were independent risk factors for the development of DM in stage T1 GC. ML algorithms had shown that RF prediction models had the best predictive efficacy to accurately screen at-risk populations for further clinical screening for metastases. At the same time, aggressive surgery and adjuvant chemotherapy can improve the survival rate of patients with DM.
| S-EPMC10082185 | biostudies-literature
Project description:Distant metastasis is the major cause of death in colorectal cancer (CRC). Patients at high risk of developing distant metastasis could benefit from appropriate adjuvant and follow-up treatments if stratified accurately at an early stage of the disease. Studies have increasingly recognized the role of diverse cellular components within the tumor microenvironment in the development and progression of CRC tumors. In this paper, we show that automated analysis of digitized images from locally advanced colorectal cancer tissue slides can provide estimate of risk of distant metastasis on the basis of novel tissue phenotypic signatures of the tumor microenvironment. Specifically, we determine what cell types are found in the vicinity of other cell types, and in what numbers, rather than concentrating exclusively on the cancerous cells. We then extract novel tissue phenotypic signatures using statistical measurements about tissue composition. Such signatures can underpin clinical decisions about the advisability of various types of adjuvant therapy.
| S-EPMC6135776 | biostudies-literature
Project description:The aim of the study is to demonstrate the relationship between clinicopathological variables and organ sites of metastasis in resected lung adenocarcinoma. The clinicopathological characteristics of 748 patients of resected lung adenocarcinoma at Taipei Veterans General Hospital between 2004 and 2012 were retrospectively reviewed. The prognostic value of clinicopathological variables for specific organ site metastasis-free survival was demonstrated. Among the 182 patients with distant metastasis, 93 (51.1%) patients developed contralateral lung metastasis, 81 (44.5%) had brain metastasis, 71 (39.0%) had bone metastasis, and 18 (8.9%) had liver metastasis during follow-up. Acinar predominant (Hazard ratio [HR], 0.468; 95% confidence interval [CI]: 0.250 to 0.877; P = 0.018) was significantly associated with less contralateral lung metastasis in multivariate analysis. Micropapillary predominant (HR, 2.686; 95% CI, 1.270 to 5.683; P = 0.010) was significantly associated with brain metastasis. Acinar predominant (HR, 0.461; 95% CI, 0.216 to 0.986; P = 0.046) was a significant prognostic factor for better contralateral lung metastasis-free survival in multivariate analysis. Micropapillary predominant (HR, 2.186; 95% CI, 1.148 to 4.163; P = 0.017) and solid predominant (HR, 4.093; 95% CI, 1.340 to 12.504; P = 0.013) were significant prognostic factors for worse brain metastasis-free survival and liver metastasis free-survival, respectively. There are significant differences in metastatic behavior between predominant pathological subtypes of lung adenocarcinoma. This information is important for patient follow-up strategy and identification of organ-specific distant metastasis. Prospective multi-institutional studies are mandatory for further validation.
| S-EPMC5295429 | biostudies-literature
Project description:ObjectiveThis retrospective study aimed to establish ultrasound radiomics models to predict central lymph node metastasis (CLNM) based on preoperative multimodal ultrasound imaging features fusion of primary papillary thyroid carcinoma (PTC).MethodsIn total, 498 cases of unifocal PTC were randomly divided into two sets which comprised 348 cases (training set) and 150 cases (validition set). In addition, the testing set contained 120 cases of PTC at different times. Post-operative histopathology was the gold standard for CLNM. The following steps were used to build models: the regions of interest were segmented in PTC ultrasound images, multimodal ultrasound image features were then extracted by the deep learning residual neural network with 50-layer network, followed by feature selection and fusion; subsequently, classification was performed using three classical classifiers-adaptive boosting (AB), linear discriminant analysis (LDA), and support vector machine (SVM). The performances of the unimodal models (Unimodal-AB, Unimodal-LDA, and Unimodal-SVM) and the multimodal models (Multimodal-AB, Multimodal-LDA, and Multimodal-SVM) were evaluated and compared.ResultsThe Multimodal-SVM model achieved the best predictive performance than the other models (P < 0.05). For the Multimodal-SVM model validation and testing sets, the areas under the receiver operating characteristic curves (AUCs) were 0.910 (95% CI, 0.894-0.926) and 0.851 (95% CI, 0.833-0.869), respectively. The AUCs of the Multimodal-SVM model were 0.920 (95% CI, 0.881-0.959) in the cN0 subgroup-1 cases and 0.828 (95% CI, 0.769-0.887) in the cN0 subgroup-2 cases.ConclusionThe ultrasound radiomics model only based on the PTC multimodal ultrasound image have high clinical value in predicting CLNM and can provide a reference for treatment decisions.
| S-EPMC10643192 | biostudies-literature