Establishment and validation of multiclassification prediction models for pulmonary nodules based on machine learning.

BACKGROUND: Lung cancer is the leading cause of cancer-related death worldwide. This study aimed to establish novel multiclassification prediction models based on machine learning (ML) to predict the probability of malignancy in pulmonary nodules (PNs) and to compare with three published models. METHODS: Nine hundred fourteen patients with PNs were collected from four medical institutions (A, B, C and D), which were organized into tables containing clinical features, radiologic features and laboratory test features. Patients were divided into benign lesion (BL), precursor lesion (PL) and malignant lesion (ML) groups according to pathological diagnosis. Approximately 80% of patients in A (total/male: 632/269, age: 57.73 ± 11.06) were randomly selected as a training set; the remaining 20% were used as an internal test set; and the patients in B (total/male: 94/53, age: 60.04 ± 11.22), C (total/male: 94/47, age: 59.30 ± 9.86) and D (total/male: 94/61, age: 62.0 ± 11.09) were used as an external validation set. Logical regression (LR), decision tree (DT), random forest (RF) and support vector machine (SVM) were used to establish prediction models. Finally, the Mayo model, Peking University People's Hospital (PKUPH) model and Brock model were externally validated in our patients. RESULTS: The AUC values of RF model for MLs, PLs and BLs were 0.80 (95% CI: 0.73-0.88), 0.90 (95% CI: 0.82-0.99) and 0.75 (95% CI: 0.67-0.88), respectively. The weighted average AUC value of the RF model for the external validation set was 0.71 (95% CI: 0.67-0.73), and its AUC values for MLs, PLs and BLs were 0.71 (95% CI: 0.68-0.79), 0.98 (95% CI: 0.88-1.07) and 0.68 (95% CI: 0.61-0.74), respectively. The AUC values of the Mayo model, PKUPH model and Brock model were 0.68 (95% CI: 0.62-0.74), 0.64 (95% CI: 0.58-0.70) and 0.57 (95% CI: 0.49-0.65), respectively. CONCLUSIONS: The RF model performed best, and its predictive performance was better than that of the three published models, which may provide a new noninvasive method for the risk assessment of PNs.

Application of spectral CT in diagnosis, classification and prognostic monitoring of gastrointestinal cancers: progress, limitations and prospects.

Gastrointestinal (GI) cancer is the leading cause of cancer-related deaths worldwide. Computed tomography (CT) is an important auxiliary tool for the diagnosis, evaluation, and prognosis prediction of gastrointestinal tumors. Spectral CT is another major CT revolution after spiral CT and multidetector CT. Compared to traditional CT which only provides single-parameter anatomical diagnostic mode imaging, spectral CT can achieve multi-parameter imaging and provide a wealth of image information to optimize disease diagnosis. In recent years, with the rapid development and application of spectral CT, more and more studies on the application of spectral CT in the characterization of GI tumors have been published. For this review, we obtained a substantial volume of literature, focusing on spectral CT imaging of gastrointestinal cancers, including esophageal, stomach, colorectal, liver, and pancreatic cancers. We found that spectral CT can not only accurately stage gastrointestinal tumors before operation but also distinguish benign and malignant GI tumors with improved image quality, and effectively evaluate the therapeutic response and prognosis of the lesions. In addition, this paper also discusses the limitations and prospects of using spectral CT in GI cancer diagnosis and treatment.

Effects of low-carbohydrate diets versus low-fat diets on metabolic risk factors in overweight and obese adults: A meta-analysis of randomized controlled trials.

Background and aims: Low-carbohydrate diets (LCD) and low-fat diets (LFD) have shown beneficial effects on the management of obesity. Epidemiological studies were conducted to compare the effects of the two diets. However, the results were not always consistent. This study aimed to conduct a meta-analysis to compare the long-term effects of LCD and LFD on metabolic risk factors and weight loss in overweight and obese adults. Methods: We performed a systematic literature search up to 30 March, 2022 in PubMed, EMBASE, and Cochrane Library. The meta-analysis compared the effects of LCD (carbohydrate intake ≤ 40%) with LFD (fat intake < 30%) on metabolic risk factors and weight loss for ≥6 months. Subgroup analyses were performed based on participant characteristics, dietary energy intake, and the proportions of carbohydrates. Results: 33 studies involving a total of 3,939 participants were included. Compared with participants on LFD, participants on LCD had a greater reduction in triglycerides (-0.14 mmol/L; 95% CI, -0.18 to -0.10 mmol/L), diastolic blood pressure (-0.87 mmHg; 95% CI, -1.41 to -0.32 mmHg), weight loss (-1.33 kg; 95% CI, -1.79 to -0.87 kg), and a greater increase in high-density lipoprotein cholesterol (0.07 mmol/L; 95% CI, 0.06 to 0.09 mmol/L) in 6-23 months. However, the decrease of total cholesterol (0.14 mmol/L; 95% CI, 0.07 to 0.20 mmol/L) and low-density lipoprotein cholesterol (0.10 mmol/L; 95% CI, 0.06 to 0.14 mmol/L) was more conducive to LFD in 6-23 months. There was no difference in benefits between the two diets after 24 months. Subgroup analyses showed no significant difference in the reduction of total cholesterol, low-density lipoprotein cholesterol, and blood pressure between the two diets in participants with diabetes, hypertension, or hyperlipidemia. Conclusion: The results suggest that LCD and LFD may have specific effects on metabolic risk factors and weight loss in overweight and obese adults over 6 months. At 24 months, the effects on weight loss and improvement of metabolic risk factors were at least the same. These indicated that we might choose different diets to manage the overweight and obese subjects. However, the long-term clinical efficacy and effects of various sources of carbohydrates or fat in the two diets need to be studied in the future.