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.

Acute Pancreatitis Complicated by Thrombosis in the Right Brachiocephalic Veins and Superior Vena Cava: A Case Report

BACKGROUND: Acute pancreatitis (AP) is one of the most common digestive emergencies, and vascular complication is one of the primary reasons for death, with splanchnic venous thrombosis being the most common. Although extra-splanchnic venous thrombosis is rare, it carries the risk of life-threatening secondary pulmonary embolism. CASE PRESENTATION: We have, herein, reported a case of AP complicated by rare brachiocephalic vein thrombosis and superior vena cava thrombosis. A 40 years old woman was diagnosed with severe AP for abdominal pain 21 days ago. The patient received symptomatic treatment, including acid suppression, enzyme suppression, lipid-lowering, fluid infusion, anti-infection, and continuous renal replacement therapy. The patient was discharged after symptomatic relief. Recently, the patient was admitted again for middle-upper abdominal pain and discomfort. On admission, her blood platelet, DDimer, fibrin degradation products (FDP), and triglyceride levels have been found to be increased; abdominal enhanced CT showed pancreatic necrosis and an accumulation of peripancreatic necrosis and fluid, while chest enhanced CT suggested thrombosis in the right brachiocephalic vein and superior vena cava. The patient, however, improved and was discharged after anticoagulation combined with insulin and trypsin inhibitors. CONCLUSION: In diagnosing and treating AP, dynamic monitoring of D-dimer levels is necessary for the timely detection of the development of thrombotic complications.

Mitochondrion-Targeted NIR Therapeutic Agent Suppresses Melanoma by Inducing Apoptosis and Cell Cycle Arrest via E2F/Cyclin/CDK Pathway.

Malignant melanoma is the most fatal form of skin cancer worldwide, and earlier diagnosis and more effective therapies are required to improve prognosis. As a possible solution, near-infrared fluorescent heptamethine cyanine dyes have been shown to be useful for tumor diagnosis and treatment. Here, we synthesized a novel theranostic agent, IR-817, a multifunctional bioactive small-molecule that has near-infrared emission, targets mitochondria in cancer cells, and has selective anti-cancer effects. In in vitro experiments, IR-817 preferentially accumulated in melanoma cells through organic anion transporting polypeptide transporters but also selectively inhibited the growth of tumor cells by inducing mitochondrial-dependent intrinsic apoptosis. Mechanistically, IR-817 caused G0/G1 cell cycle arrest by targeting the E2F/Cyclin/CDK pathway. Finally, IR-817 significantly suppressed the growth of xenograft tumors in zebrafish and mice. Immunohistochemical staining and hematoxylin and eosin staining revealed that IR-817 induced apoptosis and inhibited tumor cell proliferation without notable side effects. Therefore, mitochondrial-targeting theranostic agent IR-817 may be promising for accurate tumor diagnosis, real-time monitoring, and safe anti-cancer treatments.

Using a machine learning-based risk prediction model to analyze the coronary artery calcification score and predict coronary heart disease and risk assessment.

OBJECTIVES: To calculate the coronary artery calcification score (CACS) obtained from coronary artery computed tomography angiography (CCTA) examination and combine it with the influencing factors of coronary artery calcification (CAC), which is then analyzed by machine learning (ML) to predict the probability of coronary heart disease(CHD). METHODS: All patients who were admitted to the Affiliated Hospital of Traditional Chinese Medicine of Southwest Medical University from January 2019 to March 2022, suspected of CHD, and underwent CCTA inspection were retrospectively selected. The degree of CAC was quantified based on the Agatston score. To compare the correlation between the CACS and clinical-related factors, we collected 31 variables, including hypertension, diabetes, smoking, hyperlipidemia, among others. ML models containing the random forest (RF), radial basis function neural network (RBFNN),support vector machine (SVM),K-Nearest Neighbor algorithm (KNN) and kernel ridge regression (KRR) were used to assess the risk of CHD based on CACS and clinical-related factors. RESULTS: Among the five ML models, RF achieves the best performance about accuracy (ACC) (78.96%), sensitivity (SN) (93.86%), specificity(Spe) (51.13%), and Matthew's correlation coefficient (MCC) (0.5192).It also has the best area under the receiver operator characteristic curve (ROC) (0.8375), which is far superior to the other four ML models. CONCLUSION: Computer ML model analysis confirmed the importance of CACS in predicting the occurrence of CHD, especially the outstanding RF model, making it another advancement of the ML model in the field of medical analysis.

Value of multi-slice spiral computerized tomography for diagnosis of synchronous colorectal carcinoma: a retrospective study.

OBJECTIVE: To compare the accuracy of multi-slice spiral computerized tomography (MSCT) with colonoscopy for diagnosing synchronous colorectal carcinoma (SCC). METHODS: We retrospectively analyzed all consecutive patients admitted to our institution with colorectal carcinoma between 19 September 2014 and 31 January 2020. Data on SCC patients who had undergone MSCT and colonoscopy were analyzed. Information on tumor location, tumor size, missed diagnosis by MSCT or colonoscopy, T stage, pathological type, and reasons for missed diagnosis was recorded and used to assess the diagnostic accuracies of MSCT and colonoscopy. RESULTS: Twenty-three cases met the inclusion criteria. MSCT plus colonoscopy had a significantly higher diagnostic accuracy (93.5%) than colonoscopy alone. There were significant differences in missed diagnosis rates of proximal cancer (34.8%) and distal cancer (4.3%) by colonoscopy. For MSCT, the missed diagnosis rate for tumors with a median long diameter of 1.25 cm (interquartile range 0.80, 1.50) was significantly lower than that for larger tumors (long diameter 4.00 cm; 3.00, 6.00). CONCLUSIONS: MSCT is a valuable diagnostic tool for SCC that can effectively minimize the missed diagnosis rate of primary tumors when combined with colonoscopy.

Evaluation of isolated abdominal visceral artery dissection with multi-scale spiral computed tomography: a retrospective case series.

BACKGROUND: To evaluate the role of multi-slice spiral computed tomography (MSCT) angiography in the diagnosis of spontaneous isolated visceral artery dissection (SIVAD). METHODS: Twenty-seven patients with abdominal SIVAD were included in the study. The MSCT scans of the patients were subjected to various post-processing techniques to visualize the visceral artery wall. Clinical features including arterial dissection, thrombosis, dissection length, true/false lumen, and complications were recorded. RESULTS: Type I, IIa, and IIb SIVADs were observed in 11, 6, and 10 patients, respectively. Superior mesenteric artery (SMA) dissection was the most common (n = 16), followed by abdominal aortic dissection (n = 6), splenic artery dissection (n = 2), renal artery dissection (n = 2), and splenic artery dissection (n = 1). One patient with SMA dissection suffered small intestine ischemia, 1 with splenic artery dissection had splenic infarction, and 1 patient with left renal artery dissection experienced renal infarction. The false lumen was bigger than the true lumen in 20 patients, with 9 patients having thrombus. The true lumen was bigger than the false lumen in 7 patients. CONCLUSIONS: MSCT angiography is a valuable technique in the diagnosis and treatment of patients with SIVAD. Patients with abdominal pain suspected due to SIVAD should be examined with MSCT angiography for early detection of SIVAD.

Multislice Computed Tomographic Manifestation of Transient Hepatic Attenuation Difference in the Left Lobe of the Liver: A Retrospective Study.

INTRODUCTION: Transient hepatic attenuation differences (THAD) are areas of high parenchymal enhancement observed during the hepatic arterial phase on computed tomography (CT). THAD in the left lobe of the liver can lead to surgical complications. METHODS: A retrospective study was conducted on patients who underwent multislice computed tomography (MSCT) examination of the upper abdomen to understand the morphology, distribution, and causes of THAD and their correlation with hepatic artery variation. RESULTS: Among 179 cases, 65 and 114 belonged to diseased and normal groups, respectively. THAD as observed in MSCT demonstrated various shapes: lobe/segment (127 cases; 70.9%), irregular sheet (31; 17.3%), strip shape (9; 5.02%), arc/semicircle (7; 3.9%), and segment + flaky (5; 2.79%). THAD were found to be caused by liver tumor (32.3%), hepatic inflammatory lesions (6.15%), biliary tract diseases (13.8%), perihepatic disease compression (9.23%), portal vein obstructive disease (1.53%), and lesion in left hepatic lobe with hepatic artery variation (29.2%). THAD exhibited variation in distribution in the left lobe of the liver. Among 114 cases, THAD in 18 (15.7%) cases were observed in the S2 segment, six (5.26%) in the S3 segment, and 90 (78.9%) in multiple segments of the liver, that is, 50 cases in S2 and S3 segments and 40 cases in S2, S3, and S4 segments. The hepatic artery of 179 cases was of various types based on Hiatt classification: 57 cases of Hiatt I (31%), 65 cases of Hiatt II (37%), 11 cases of Hiatt III (6%), 17 cases of Hiatt IV (10%), 7 cases of Hiatt V (4%), 12 cases of large left hepatic artery (7%), 6 cases of right hepatic artery originating from the celiac trunk (3%), and 4 cases (2%) of superior mesenteric artery originating from the celiac trunk. CONCLUSION: THAD can occur as a result of specific pathological causes and hence should be considered as a diagnostic sign in liver pathologies.

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.

Implications of Classification of Os Trigonum: A Study Based on Computed Tomography Three-Dimensional Imaging.

BACKGROUND The os trigonum is an accessory bone that is not fully fused with the talus during secondary ossification, and is one of the risk factors of posterior malleolus impact syndrome. The purpose of this study was to classify the os trigonum and to guide the diagnosis and treatment of related clinical diseases. MATERIAL AND METHODS Ankle computed tomography (CT) scans of 586 Chinese patients between October 2014 and October 2018 were reviewed. CT images of 1011 ankle joints were reconstructed to evaluate the classification of the os trigonum and the measurement of anatomical parameters. RESULTS The incidences of os trigonum in 3 groups were determined as type I (1.9%), type II (10.5%), and type III (14.7%). The macro-axis of type II (0.89±0.31) cm was significantly larger than with type I (0.65±0.24 cm) and type III (0.74±0.23 cm) (p<0.05).The minor axis of similar of type I (0.41±0.23 cm) was significantly shorter than that of type II (0.58±0.32 cm) and type III (0.55±0.16 cm) (p<0.05).The distance from os trigonum to calcaneal tubercle was significantly different than that of type I (1.33±0.52 cm), type II (1.67±0.55 cm), and type III (1.84±0.45 cm) (p<0.05). CONCLUSIONS This study showed that os trigonum has a high incidence. Type I was the least common, the volume of type II was larger, and type III was more common. The anatomical parameters of each type may improve treatment of related diseases and the further development of ankle arthroscopic surgery.