Prediction of viral pneumonia based on machine learning models analyzing pulmonary inflammation index scores.

OBJECT: To obtain Pulmonary Inflammation Index scores from imaging chest CT and combine it with clinical correlates of viral pneumonia to predict the risk and severity of viral pneumonia using a computer learning model. METHODS: All patients with suspected viral pneumonia on CT examination admitted to The Affiliated Traditional Chinese Medicine Hospital of Southwest Medical University from December 2022 to March 2023 were retrospectively selected. The respiratory viruses were monitored by RT-PCR and categorized into patients with viral pneumonia and those with non-viral pneumonia. The extent of lung inflammation was quantified according to the Pulmonary Inflammation Index score (PII). Information on patient demographics, comorbidities, laboratory tests, pathogenetic testing, and radiological data were collected. Five machine learning models containing Random Forest(RF), Radial Basis Function Neural Network (RBFNN), Support Vector Machine (SVM), K Nearest Neighbour Algorithm (KNN), and Kernel Ridge Regression (KRR) were used to predict the risk of onset and severity of viral pneumonia based on the clinically relevant factors or PII. RESULTS: Among the five models, the SVM model performed best in ACC (76.75 %), SN (73.99 %), and F1 (72.42 %) and achieved a better area under the receiver operating characteristic curve (ROC) (0.8409) when predicting the risk of developing viral pneumonia. RF had the best overall classification accuracy in predicting the severity of viral pneumonia, especially in predicting pneumonia with a PII classification of grade I, the RF model achieved an accuracy of 98.89%. CONCLUSION: Machine learning models are valuable in assessing the risk of viral pneumonia. Meanwhile, machine learning models confirm the importance in predicting the severity of viral pneumonia through PII. The establishment of machine learning models for predicting the risk and severity of viral pneumonia promotes the further development of machine learning in the medical field.

Correlation analysis of multi-slice computed tomography (MSCT) findings, clinicopathological factors, and prognosis of gastric gastrointestinal stromal tumors.

BACKGROUND: Computed tomography (CT) findings and clinicopathological characteristics of gastric gastrointestinal stromal tumors (GISTs) have been reported in the past, however, studies on their association with prognosis are limited. We aimed to evaluate the correlation between multi-slice computed tomography (MSCT) findings and clinicopathological characteristics for the prognosis of gastric GISTs. Multiple independent factors influencing the prognostic assessment of gastric GISTs were recognized. METHODS: The CT images and clinicopathological data of 155 patients with gastric GISTs were retrospectively analyzed. Progression-free survival of patients was obtained using the Kaplan-Meier method and compared using the log-rank test. Univariate and multivariate analyses were performed to evaluate the prognostic significance of CT imaging and clinicopathological factors. RESULTS: Univariate analysis revealed that patient prognosis was associated with the size, shape, necrosis or cystic degeneration, margin, growth pattern, enhancement pattern, mitotic rate, and Ki-67 index of the tumor. Further, multivariate analysis indicated that tumor size and necrosis or cystic degeneration were significant independent prognostic factors for gastric GISTs. CONCLUSIONS: Tumor shape, necrosis or cystic degeneration, growth pattern, enhancement pattern, and mitotic rate were non-negligible criteria for improving the prognostic accuracy for GISTs, whereas tumor size, margin, and Ki-67 index were significant independent predictors identifying high-risk patients, facilitating personalized treatment to improve the prognosis of gastric GISTs patients. Thus, a combination of MSCT findings and clinicopathological features may be a valuable tool for assessing the prognosis of patients with gastric GISTs.