Prediction of prognosis and survival of patients with gastric cancer by a weighted improved random forest model: an application of machine learning in medicine

Development and validation of an inflammatory biomarkers model to predict gastric cancer prognosis: a multi-center cohort study in China

BACKGROUND

Inflammatory factors have increasingly become a more cost-effective prognostic indicator for gastric cancer (GC). The goal of this study was to develop a prognostic score system for gastric cancer patients based on inflammatory indicators.

METHODS

Patients' baseline characteristics and anthropometric measures were used as predictors, and independently screened by multiple machine learning(ML) algorithms. We constructed risk scores to predict overall survival in the training cohort and tested risk scores in the validation. The predictors selected by the model were used in multivariate Cox regression analysis and developed a nomogram to predict the individual survival of GC patients.

RESULTS

A 13-variable adaptive boost machine (ADA) model mainly comprising tumor stage and inflammation indices was selected in a wide variety of machine learning models. The ADA model performed well in predicting survival in the validation set (AUC = 0.751; 95% CI: 0.698, 0.803). Patients in the study were split into two sets - "high-risk" and "low-risk" based on 0.42, the cut-off value of the risk score. We plotted the survival curves using Kaplan-Meier analysis.

CONCLUSION

The proposed model performed well in predicting the prognosis of GC patients and could help clinicians apply management strategies for better prognostic outcomes for patients.

A novel CT-based radiomics model for predicting response and prognosis of chemoradiotherapy in esophageal squamous cell carcinoma

No clinically relevant biomarker has been identified for predicting the response of esophageal squamous cell carcinoma (ESCC) to chemoradiotherapy (CRT). Herein, we established a CT-based radiomics model with artificial intelligence (AI) to predict the response and prognosis of CRT in ESCC. A total of 44 ESCC patients (stage I-IV) were enrolled in this study; training (n = 27) and validation (n = 17) cohorts. First, we extracted a total of 476 radiomics features from three-dimensional CT images of cancer lesions in training cohort, selected 110 features associated with the CRT response by ROC analysis (AUC ≥ 0.7) and identified 12 independent features, excluding correlated features by Pearson's correlation analysis (r ≥ 0.7). Based on the 12 features, we constructed 5 prediction models of different machine learning algorithms (Random Forest (RF), Ridge Regression, Naive Bayes, Support Vector Machine, and Artificial Neural Network models). Among those, the RF model showed the highest AUC in the training cohort (0.99 [95%CI 0.86-1.00]) as well as in the validation cohort (0.92 [95%CI 0.71-0.99]) to predict the CRT response. Additionally, Kaplan-Meyer analysis of the validation cohort and all the patient data showed significantly longer progression-free and overall survival in the high-prediction score group compared with the low-prediction score group in the RF model. Univariate and multivariate analyses revealed that the radiomics prediction score and lymph node metastasis were independent prognostic biomarkers for CRT of ESCC. In conclusion, we have developed a CT-based radiomics model using AI, which may have the potential to predict the CRT response as well as the prognosis for ESCC patients with non-invasiveness and cost-effectiveness.

Gut mycobiome as a potential non-invasive tool in early detection of lung adenocarcinoma: a cross-sectional study

BACKGROUND

The gut mycobiome of patients with lung adenocarcinoma (LUAD) remains unexplored. This study aimed to characterize the gut mycobiome in patients with LUAD and evaluate the potential of gut fungi as non-invasive biomarkers for early diagnosis.

METHODS

In total, 299 fecal samples from Beijing, Suzhou, and Hainan were collected prospectively. Using internal transcribed spacer 2 sequencing, we profiled the gut mycobiome. Five supervised machine learning algorithms were trained on fungal signatures to build an optimized prediction model for LUAD in a discovery cohort comprising 105 patients with LUAD and 61 healthy controls (HCs) from Beijing. Validation cohorts from Beijing, Suzhou, and Hainan comprising 44, 17, and 15 patients with LUAD and 26, 19, and 12 HCs, respectively, were used to evaluate efficacy.

RESULTS

Fungal biodiversity and richness increased in patients with LUAD. At the phylum level, the abundance of Ascomycota decreased, while that of Basidiomycota increased in patients with LUAD. Candida and Saccharomyces were the dominant genera, with a reduction in Candida and an increase in Saccharomyces, Aspergillus, and Apiotrichum in patients with LUAD. Nineteen operational taxonomic unit markers were selected, and excellent performance in predicting LUAD was achieved (area under the curve (AUC) = 0.9350) using a random forest model with outcomes superior to those of four other algorithms. The AUCs of the Beijing, Suzhou, and Hainan validation cohorts were 0.9538, 0.9628, and 0.8833, respectively.

CONCLUSIONS

For the first time, the gut fungal profiles of patients with LUAD were shown to represent potential non-invasive biomarkers for early-stage diagnosis.