The Innovation Medicine最新文献

Artificial Intelligence (AI) has transformed how we live and how we think, and it will change how we practice medicine. With multimodal big data, we can develop large medical models that enables what used to unimaginable, such as early cancer detection several years in advance and effective control of virus outbreaks without imposing social burdens. The future is promising, and we are witnessing the advancement. That said, there are challenges that cannot be overlooked. For example, data generated is often isolated and difficult to integrate from both perspectives of data ownership and fusion algorithms. Additionally, existing AI models are often treated as black boxes, resulting in vague interpretation of the results. Patients also exhibit a lack of trust to AI applications, and there are insufficient regulations to protect patients�� privacy and rights. However, with the advancement of AI technologies, such as more sophisticated multimodal algorithms and federated learning, we may overcome the barriers posed by data silos. Deeper understanding of human brain and network structures can also help to unravel the mysteries of neural networks and construct more transparent yet more powerful AI models. It has become something of a trend that an increasing number of clinicians and patients will implement AI in their life and medical practice, which in turn can generate more data and improve the performance of models and networks. Last but not the least, it is crucial to monitor the practice of AI in medicine and ensure its equity, security, and responsibility.

Anterior chamber angles in primary angle closure suspects (PACS) can continue to narrow after laser peripheral iridotomy (LPI). The aim of this study is to identify risk factors and develop prediction models for the progression in LPI-treated eyes during a 14-year follow-up. From 2008 to 2010, 889 Chinese participants aged 50-70 years with bilateral PACS were enrolled in the Zhongshan Angle Closure Prevention (ZAP) trial and received LPI in one randomly selected eye. Examinations before LPI included Goldmann tonometry, ultrasound A-scan biometry, both light-room and dark-room anterior-segment optical coherence tomography (AS-OCT). Logistic regression models were built to predict the 14-year risk of progression in PACS eyes after LPI (peripheral anterior synechiae, intraocular pressure [IOP] ��24mmHg, or acute angle closure). Within 370 eligible PACS eyes, 26 progressed to PAC during 14 years after LPI. For both light-room and dark-room AS-OCT metrics before LPI, the narrowing of anterior chamber angle was identified as risk factor for the 14-year risk of progression in LPI-treated PACS eyes. In addition, change in IOP after dark-room prone provocative test and change in lens vault from light to dark before LPI were found to be negatively associated with the risk of progression during 14 years after LPI. Based on aforementioned predictors, multivariable logistic models provided good performance in the prediction for long-term risk of progression after LPI (area under the curve = 0.80-0.84). This study suggested that closer monitoring is still required for PACS eyes at high risk of progression even after prophylactic LPI.

Parkinson��s disease (PD) induces functional connectivity (FC) changes during its course. However, the impact of PD progression on the temporal properties of FC remains ambiguous. In the current study, we aimed to uncover longitudinal shifts in dynamic FC (DFC) temporal properties of brain networks during PD progression, proposing a novel biomarker for PD progression evaluation. We conducted a longitudinal study on 45 PD patients from the Parkinson��s Progression Markers Initiative database. Patients underwent dual-timepoint neurological assessments and resting-state fMRI scans at baseline and 1-4 years of subsequent follow-up. The sliding-window technique and k-means clustering were employed to scrutinize DFC patterns of the entire brain network, including individual cortical subnetworks and subcortical nuclei (SN) at every timepoint. From this analysis, DFC analyses revealed two predominant states: a high-frequency sparse FC state and a low-frequency intense FC state. For the entire brain network, the mean dwell time (MDT) in the sparse FC state diminished with PD progression, and this decrease was closely tied to motor deterioration. Concerning cortical subnetworks and SN, MDTs in the sparse FC state reduced at the second timepoint in both visual (VN) and limbic networks (LN) linked with the SN. The MDT reduction in LN-SN positively correlated with cognitive decline, while the MDT reduction in VN-SN showed a strong link with motor degradation. These results emphasize that DFC might offer insights into the evolving brain dynamics in PD patients over the disease's course, underscoring its prospective utility as a progression biomarker.

Lung cancer (LC) is one of the major causes of cancer deaths in China. Death burden and mortality of LC vary according to sexes and regions. We aimed to comprehensively evaluate the geographical and sexual disparities in LC mortality trends in China, and a further age-period-cohort analysis to explore underlying factors. LC mortality data during 2004-2021 were extracted from the Disease Surveillance Points system. Annual age-standardized mortality rates (ASMR) were calculated for 36 sub-populations by sex, urban-rural status and geographical regions. The age-period-cohort model was applied to investigate age, period and cohort effects on mortality trends. Time trends of ASMR for LC overall did not show statistical significance during 2004-2021, but contrasting patterns were observed between cities and countryside, with annual average percent changes of -1.58% (95%CI, -2.11%- -1.05%) and 0.57% (95%CI, 0.07%- 1.07%), respectively. ASMR of LC decreased in eastern and central regions and increased markedly in western region. Cohort effects illustrated a downward trend in cities, but an inverted U-shape curve peaking around the 1950s appeared in the countryside, and the decreasing trends were slower in the western region. There are substantial geographical and sexual disparities in LC mortality trends in China, notably with unfavorable trends in the western countryside. The variation in cohort effects on the mortality trends implies the importance of taking region- and population-specific primary prevention strategies to reduce the disease burden of LC in China.