Infectious diseases have always been a major threat to the survival of humanity. Additionally, they bring an enormous economic burden to society. The conventional methods for bacteria identification are expensive, time-consuming and laborious. Therefore, it is of great importance to automatically rapidly identify pathogenic bacteria in a short time. Here, we constructed an AI-assisted system for automating rapid bacteria genus identification, combining the hyperspectral microscopic technology and a deep-learning-based algorithm Buffer Net. After being trained and validated in the self-built dataset, which consists of 11 genera with over 130,000 hyperspectral images, the accuracy of the algorithm could achieve 94.9%, which outperformed 1D-CNN, 2D-CNN and 3D-ResNet. The AI-assisted system we developed has great potential in assisting clinicians in identifying pathogenic bacteria at the single-cell level with high accuracy in a cheap, rapid and automatic way. Since the AI-assisted system can identify the pathogenic genus rapidly (about 30 s per hyperspectral microscopic image) at the single-cell level, it can shorten the time or even eliminate the demand for cultivating. Additionally, the system is user-friendly for novices.

Background: Physical activity may help prevent dementia in people with hearing loss, but evidence on long‐term behavioural heterogeneity is limited. This study examined dose–response associations between physical activity and cognitive impairment and explored heterogeneity in long‐term physical activity trajectories and their associations with cognitive function among adults with self‐reported hearing loss. Methods: Data were from the China Health and Retirement Longitudinal Study (2011–2020), including 2055 adults aged ≥ 45 years with hearing difficulties and normal cognition at baseline. Physical activity, assessed biennially using the International Physical Activity Questionnaire, was expressed as metabolic equivalent minutes per week. Cognitive function in 2020 was measured by validated tests of episodic memory and mental status (range 0–21). Multiple linear regression examined associations between activity trajectories and cognition. Results: Physical activity showed an L‐shaped relationship with cognitive impairment. Three trajectories were identified: slight decline (70.61%), sharp drop (15.28%), and rise‐then‐fall (14.11%). Compared with the slight‐decline group, the rise‐then‐fall group had lower global cognition ( β = −0.621, 95% CI −1.022–−0.219) and mental status scores ( β = −0.449, 95% CI –0.648–−0.249). This trajectory was more common among men, younger rural residents, frequent drinkers, non‐nappers, and those with depressive symptoms. Conclusions: Among adults with self‐reported hearing loss, physical activity showed an L‐shaped association with cognitive impairment, and participants following an unstable rise‐then‐fall activity pattern had lower cognitive function. These findings highlight heterogeneity in physical activity patterns within this population and support the need for strategies that help sustain long‐term physical activity engagement. Trial registration: Not applicable.