Delirium is a common cause and complication of hospitalization in the elderly and is associated with higher risk of future dementia and progression of existing dementia, of which 70% is Alzheimer's disease (AD). AD and delirium, which are known to be aggravated by one another, represent significant societal challenges, especially in light of the absence of effective treatments. The intricate biological mechanisms have led to numerous clinical trial setbacks and likely contribute to the limited efficacy of existing therapeutics. Artificial intelligence (AI) presents a promising avenue for overcoming these hurdles by deploying algorithms to uncover hidden patterns across diverse data types. This review explores the pivotal role of AI in revolutionizing drug discovery for AD and delirium from target identification to the development of small molecule and protein-based therapies. Recent advances in deep learning, particularly in accurate protein structure prediction, are facilitating novel approaches to drug design and expediting the discovery pipeline for biological and small molecule therapeutics. This review concludes with an appraisal of current achievements and limitations, and touches on prospects for the use of AI in advancing drug discovery in AD and delirium, emphasizing its transformative potential in addressing these two and possibly other neurodegenerative conditions.

Particle size and surface properties are crucial for lymphatic drainage (LN), dendritic cell (DC) uptake, DC maturation, and antigen cross-presentation induced by nanovaccine injection, which lead to an effective cell-mediated immune response. However, the manner in which the particle size and surface properties of vaccine carriers such as mesoporous silica nanoparticles (MSNs) affect this immune response is unknown. We prepared 50, 100, and 200 nm of MSNs that adsorbed ovalbumin antigen (OVA) while modifying β-glucan to enhance immunogenicity. The results revealed that these MSNs with different particle sizes were just as efficient in vitro, and MSNs with β-glucan modification demonstrated higher efficacy. However, the in vivo results indicated that MSNs with smaller particle sizes have stronger lymphatic targeting efficiency and a greater ability to promote the maturation of DCs. The results also indicate that β-glucan-modified MSN, with a particle size of ∼100 nm, has a great potential as a vaccine delivery vehicle and immune adjuvant and offers a novel approach for the delivery of multiple therapeutic agents that target other lymph-mediated diseases.

Objective To explore whether hypertonic saline would partake in regulating Notch signaling in microglia in experimentally induced cerebral ischemic rats.Methods Male SD rats were randomly divided into sham group, cerebral ischemia group, normal saline group ( NS group ) , 10%hypertonic saline group (10%HS group) , the model of cerebral ischemia were established in all rats except the sham group by using middle cerebral artery occlusion ( MCAO) .After 2 hours of MCAO, the rats were through reperfusion for 24 h.In addition, rats in the normal saline group and 10% HS group were respectively treated with a continuous intravenous injection of normal saline (0.3 mL/h) and 10%HS (0.3 mL/h) by tail vein for 24 h.Immunofluorescence methods, RT-PCR and Western blot were used to detect the expression of Notch1 and intracellular Notch receptor domain ( NICD) .All data was analyzed by one-way analysis of variance ( ANOVA) , The intergroup comparisons were analyzed by the least-significant-difference (LSD) tests.Differences were considered statistically significant if P<0.05.Results Immunofluorescence showed that the expression of Notch1 and NICD were significantly increased in the microglia around peri-ischemia area in cerebral ischemia group and normal saline group compared to sham group;the expression of Notch1 and NICD in the microglia around peri-ischemia area were significantly reduced in 10% HS group compared to ischemia group and NS group.RT-PCR showed that the mRNA expression of Notch1 was significantly increased in ischemia group and NS group compared to sham group ( sham group: 1.000 ± 0.076; ischemia group: 2.203 ±0.283; NS group: 1.616 ±0.185; P <0.01 ); however, it was significantly reduced in 10% HS group compared to ischemia group and NS group ( ischemia group:2.203 ±0.283; NS group: 1.616 ±0.185; 10%HS group: 1.202 ±0.177; P <0.05 ) .Western blot showed that the protein expression of Notch1 was significantly increased in ischemia group and NS group compared to sham group ( sham group: 0.290 ±0.079; ischemia group: 0.750 ±0.029; NS group:0.765 ±0.182;P<0.01);but was significantly reduced in 10%HS group compared to ischemia group and NS group ( ischemia group:0.750 ±0.029; NS group:0.765 ±0.182;10%HS group:0.390 ±0.195;P<0.05 ) .The protein expression of NICD was significantly increased in ischemia group and NS group compared to sham group ( sham group: 0.401 ±0.196; ischemia group: 0.906 ±0.359; NS group:0.847 ±0.153;P<0.01);but was significantly reduced in 10%HS group compared to ischemia group and NS group ( ischemia group:0.906 ±0.359; NS group:0.847 ±0.153;10%HS group:0.561 ±0.165;P<0.05 ) .Conclusion Our results suggest that HS markedly suppresses Notch signaling in microglia around the ischemia tissue area in experimental induced cerebral ischemic rats.

Objective To analyze the risk factors of pulmonary embolism in patients with negative Ddimer in serum in order to determine the need of pulmonary computed tomography angiograph (CTA) to confirm the final diagnosis in those patients for avoidance of misdiagnosis.Methods A retrospective analysis of 106 patients suspected to suffer from pulmonary embolism (PE) with serum negative D-dimer checked with pulmonary CTA was carried out.According to the results of CTA, the patients were divided into two groups, namely PE group (n =41) and non-PE group (n =65).The difference in clinic presentation, the time elapsed from onset to visit, N-terminal pro-brain natriuretic peptide (NT-proBNP), high risk factors (such as immobilization for 3 weeks, leg swelling and pain to palpation, history of deep vein thrombosis, malignancy) and Wells score (≥ 4 points indicates probability of PE).And logistic regression analysis was made to investigate the risk factors in PE with negative D-dimer.Results The analysis study showed that 38.6％ of total patients suspected to suffer from PE with serum negative D-dimer were checked by CTA to confirm the presence of PE.One important characteristics of the D-dimer negative PE patients was the longer time consumed from onset to visit [(9.51 ±2.01) d vs.(4.01 ±1.92) d, P＜ 0.05], and majority of the CTA positive patients suspected to suffer from PE with negative D-dimer had high risks of PE (P ＜0.01).Compared with the non-PE group, the Wells score ≥4 points and the level of serum NT-proBNP significantly increased in the PE group (P ＜ 0.01).Logistic regression analysis revealed that dyspnea, high NT-proBNP level and Wells sore ≥ 4 points were risk factors for D-dimer negative PE.Conclusion Delayed treatment was the main cause of misdiagnosis of D-dimer negative PE.Dyspnea, high NT-proBNP level and Wells sore ≥4 points were risk factors for suspected PE patients with negative D-dimer, and these patients should be confirmed by pulmonary CTA.On the contrary, PE could be excluded if patients with D-dimer negative had no these risk factors.