Implementing and evaluating a fully functional AI-enabled model for chronic eye disease screening in a real clinical environment.

BACKGROUND: Artificial intelligence (AI) has the potential to increase the affordability and accessibility of eye disease screening, especially with the recent approval of AI-based diabetic retinopathy (DR) screening programs in several countries. METHODS: This study investigated the performance, feasibility, and user experience of a seamless hardware and software solution for screening chronic eye diseases in a real-world clinical environment in Germany. The solution integrated AI grading for DR, age-related macular degeneration (AMD), and glaucoma, along with specialist auditing and patient referral decision. The study comprised several components: (1) evaluating the entire system solution from recruitment to eye image capture and AI grading for DR, AMD, and glaucoma; (2) comparing specialist's grading results with AI grading results; (3) gathering user feedback on the solution. RESULTS: A total of 231 patients were recruited, and their consent forms were obtained. The sensitivity, specificity, and area under the curve for DR grading were 100.00%, 80.10%, and 90.00%, respectively. For AMD grading, the values were 90.91%, 78.79%, and 85.00%, and for glaucoma grading, the values were 93.26%, 76.76%, and 85.00%. The analysis of all false positive cases across the three diseases and their comparison with the final referral decisions revealed that only 17 patients were falsely referred among the 231 patients. The efficacy analysis of the system demonstrated the effectiveness of the AI grading process in the study's testing environment. Clinical staff involved in using the system provided positive feedback on the disease screening process, particularly praising the seamless workflow from patient registration to image transmission and obtaining the final result. Results from a questionnaire completed by 12 participants indicated that most found the system easy, quick, and highly satisfactory. The study also revealed room for improvement in the AMD model, suggesting the need to enhance its training data. Furthermore, the performance of the glaucoma model grading could be improved by incorporating additional measures such as intraocular pressure. CONCLUSIONS: The implementation of the AI-based approach for screening three chronic eye diseases proved effective in real-world settings, earning positive feedback on the usability of the integrated platform from both the screening staff and auditors. The auditing function has proven valuable for obtaining efficient second opinions from experts, pointing to its potential for enhancing remote screening capabilities. TRIAL REGISTRATION: Institutional Review Board of the Hamburg Medical Chamber (Ethik-Kommission der Ärztekammer Hamburg): 2021-10574-BO-ff.

Awareness of Diagnosis in Persons with Early-Stage Alzheimer's Disease: An Observational Study in Spain.

INTRODUCTION: Limited information is available on people's experiences of living with Alzheimer's disease (AD) at earlier stages. This study assessed awareness of diagnosis among people with early-stage AD and its impact on different person-centered outcome measures. METHODS: We conducted an observational, cross-sectional study in 21 memory clinics in Spain. Persons aged 50-90 years, diagnosed with prodromal or mild AD (NIA/AA criteria), a Mini Mental State Examination (MMSE) score ≥ 22, and a Clinical Dementia Rating-Global score (CDR-GS) of 0.5 or 1.0 were recruited. The Representations and Adjustment to Dementia Index (RADIX) was used to assess participants' beliefs about their condition and its consequences. RESULTS: A total of 149 persons with early-stage AD were studied. Mean (SD) age was 72.3 (7.0) years and 50.3% were female. Mean duration of AD was 1.4 (1.8) years. Mean MMSE score was 24.6 (2.1) and 87.2% had a CDR-GS score of 0.5. Most participants (n = 84, 57.5%) used a descriptive term related to specific AD symptoms (e.g., memory difficulties) when asked what they called their condition. Participants aware of their diagnosis using the term AD (n = 66, 45.2%) were younger, had more depressive symptoms, and poorer life satisfaction and quality of life compared to those without awareness of their specific diagnosis. Practical and emotional consequences RADIX scores showed a significant negative correlation with Quality of Life in Alzheimer's Disease score (rho = - 0.389 and - 0.413, respectively; p < 0.0001). Years of education was the only predictor of awareness of AD diagnosis [OR = 1.04 (95% CI 1.00-1.08); p = 0.029]. CONCLUSIONS: Awareness of diagnosis was a common phenomenon in persons with early-stage AD negatively impacting their quality of life. Understanding illness representations in earlier stages may facilitate implementing optimized care that supports improved quality of life and well-being.

Plasma miR-34a-5p and miR-545-3p as Early Biomarkers of Alzheimer's Disease: Potential and Limitations.

Plasma microRNAs (miRNAs) have been proposed as potential biomarkers in Alzheimer's disease (AD). Here, we explored their use as early sensors of the preclinical phase of the disease, when brain pathology is being developed and no cognitive loss is detected. For this purpose, we analyzed a set of ten mature plasma miRNAs in symptomatic patients with AD from a cohort that also included healthy controls (HC) and patients with preclinical Alzheimer's disease (PAD) (cohort 1). Plasmas from subjects with Parkinson's disease (PD) were used to control for disease specificity. We found that miR-15b-5p, miR-34a-5p, miR-142-3p, and miR-545-3p levels significantly distinguished AD from PD and HC subjects. We next examined the expression of these four miRNAs in plasma from subjects with PAD. Among these, miR-34a-5p and miR-545-3p presented good diagnostic accuracy to distinguish both AD and PAD from HC subjects, according to the receiver operating characteristic (ROC) curve analysis. Both miRNAs also demonstrated a significant positive correlation with Aß1-42 levels in cerebrospinal fluid (CSF). Taking into account the clinical potential of these findings, we decided to validate the diagnostic accuracy of miR-34a-5p and miR-545-3p in plasma samples from an independent cohort (cohort 2), in which we did not observe the alterations described by us and others in AD and PAD samples. Although miR-34a-5p and miR-545-3p might be promising early biomarker candidates for AD, our study highlights possible sources of variability in miRNA analysis across hospitals, which currently prevents their use as reliable clinical tools.

Genetic variation in APOE cluster region and Alzheimer's disease risk.

We report the fine mapping/sequencing results of promoter and regulatory regions of APOE cluster genes (APOE, APOC1, APOC4, APOC2, and TOMM40) in Alzheimer's disease (AD) risk as well as in the progression from mild cognitive impairment (MCI) to AD. Long-range sequencing in 29 MCI subjects who progressed to dementia revealed 7 novel variants. Two potentially relevant novel variants and 34 single nucleotide polymorphisms (SNPs) were genotyped in a large sample of AD, MCI, and control subjects (n = 1453). Globally, very little association signal was observed in our sample in the absence of APOE ε4. Rs5158 (APOC4 intron 1) and rs10413089 (3' to APOC2) showed a trend toward an increase in AD risk independently from APOE ε4 associated risk though it did not survive multiple test correction (uncorrected p = 0.0099 and 0.01, respectively). Interestingly, rs10413089 showed a similar effect in an independent series. The analysis of the discovery sample showed an association of TOMM40 single nucleotide polymorphisms with progression from MCI stage to AD (rs59007384 and rs11556510), as well as with a shorter time to progression from MCI status to AD (rs10119), though these results could not be replicated in independent series. Further studies are needed to investigate the role of APOE cluster variants in AD risk.