Artificial intelligence-based prognostic model accurately predicts the survival of patients with diffuse large B-cell lymphomas: analysis of a large cohort in China.

BACKGROUND: Diffuse large B-cell lymphomas (DLBCLs) display high molecular heterogeneity, but the International Prognostic Index (IPI) considers only clinical indicators and has not been updated to include molecular data. Therefore, we developed a widely applicable novel scoring system with molecular indicators screened by artificial intelligence (AI) that achieves accurate prognostic stratification and promotes individualized treatments. METHODS: We retrospectively enrolled a cohort of 401 patients with DLBCL from our hospital, covering the period from January 2015 to January 2019. We included 22 variables in our analysis and assigned them weights using the random survival forest method to establish a new predictive model combining bidirectional long-short term memory (Bi-LSTM) and logistic hazard techniques. We compared the predictive performance of our "molecular-contained prognostic model" (McPM) and the IPI. In addition, we developed a simplified version of the McPM (sMcPM) to enhance its practical applicability in clinical settings. We also demonstrated the improved risk stratification capabilities of the sMcPM. RESULTS: Our McPM showed superior predictive accuracy, as indicated by its high C-index and low integrated Brier score (IBS), for both overall survival (OS) and progression-free survival (PFS). The overall performance of the McPM was also better than that of the IPI based on receiver operating characteristic (ROC) curve fitting. We selected five key indicators, including extranodal involvement sites, lactate dehydrogenase (LDH), MYC gene status, absolute monocyte count (AMC), and platelet count (PLT) to establish the sMcPM, which is more suitable for clinical applications. The sMcPM showed similar OS results (P < 0.0001 for both) to the IPI and significantly better PFS stratification results (P < 0.0001 for sMcPM vs. P = 0.44 for IPI). CONCLUSIONS: Our new McPM, including both clinical and molecular variables, showed superior overall stratification performance to the IPI, rendering it more suitable for the molecular era. Moreover, our sMcPM may become a widely used and effective stratification tool to guide individual precision treatments and drive new drug development.

Maternal obesity inhibits placental angiogenesis by down-regulating the SIRT1/PGC-1α pathway.

Background: To explore whether maternal obesity inhibits placental angiogenesis through down-regulation of Sirtuin 1/Peroxisome proliferator-activated receptor-γ coactivator-1α (SIRT1/PGC-1α) signaling pathway. Methods: In a rat model of pre-pregnancy obesity, rats were sacrificed at embryonic day (E)18.5. Maternal characteristics were measured. Placentas were collected to observe the pathological changes and angiogenesis using hematoxylin-eosin (HE) staining and platelet endothelial cell adhesion molecule-1 [PECAM-1/CD31 (CD31)] immunohistochemical (IHC) staining, and the expression of the SIRT1/PGC-1α signaling pathway was also analyzed using western blotting and quantitative real-time polymerase chain reaction (qPCR). In in vitro experiments, human umbilical vein endothelial cells (HUVECs) were incubated under high fat conditions. We activated and inhibited the SIRT1/PGC-1α signaling pathway to determine the proliferation, angiogenic tube formation, and migration capacity of endothelial cells. Cell counting kit-8 (CCK-8) assays, tubule formation assays, and scratch wound-healing migration assays were also performed. Results: In vivo results showed that compared with the control group, the high-fat diet (HFD) group were heavier and their plasma triglyceride and total cholesterol contents were higher. The ratio of fetal weight to placental weight was reduced in the HFD group compared to the control group. In the HFD group, placental angiogenesis was decreased, and the SIRT1/PGC-1α signaling pathway was down-regulated compared with that in the control group. The results of in vitro experiments showed that SRT1720 reduced SIRT1/PGC-1α and vascular endothelial growth factor (VEGFA) expression inhibition induced by high fat stress, while EX-527 increased SIRT1/PGC-1α and VEGFA expression inhibition. Compared with the control group, maternal obesity impaired placental angiogenesis and reduced the proliferation and migration of HUVECs. Conclusions: The results suggest that maternal obesity impairs placental angiogenesis. They also provide experimental evidence that activation of the SIRT1/PGC-1α signaling pathway improves angiogenesis in vitro.

[Effects of paeoniflorin on expressions of CTGF, PDGF and TNF-alpha in mice with hepatic fibrosis due to Schistosoma japonicum infection].

OBJECTIVE: To observe the effects of paeoniflorin on the expressions of CTGF and PDGF in liver tissue of fibrosis and the serum level of TNF-alpha in mice infected with Schistosoma japonicum, and to explore the protective effect and its mechanisms of paeoniflorin on liver fibrosis. METHODS: Kunming mice were divided randomly into 5 groups, namely normal control group (Group A), paeoniflorin groups (Group B, C, D) and infected control group (Group E). The mice in Group B-E were infected with cercariae of Schistosoma japonicum, and then they were treated with praziquantel (400 mg/kg per day) for 2 days after 6 weeks. After that, the mice in Group B, C, D were given paeoniflorin with a dose of 30, 60, 120 mg/(kg x d), respectively. After 8 weeks of paeoniflorin treatment, all the mice were killed, and their livers and serum were obtained. Hematoxylin and eosin stain and Masson stain were used to observe the degree of hepatic fibrosis. Immunohistochemical staining was performed to detect the expressions of CTGF and PDGF in liver tissue. The serum level of TNF-alpha was detected by ELISA. RESULTS: The expression levels of CTGF and PDGF proteins in liver tissue and the serum level of TNF-alpha of the mice in the high dosage paeoniflorin treatment group (Group D) were significantly lower than those in the infected control group (P < 0.05). CONCLUSIONS: The effects of paeoniflorin on hepatic fibrosis induced by Schistosoma japonicum infection depends on its dosage. Paeoniflorin may exert its effects by inhibiting the serum level of TNF-alpha and down regulating the expression of CTGF and PDGF proteins.