The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible. While AI models for glaucoma screening from CFPs have shown promising results in laboratory settings, their performance decreases significantly in real-world scenarios due to the presence of out-of-distribution and low-quality images. To address this issue, we propose the Artificial Intelligence for Robust Glaucoma Screening (AIROGS) challenge. This challenge includes a large dataset of around 113,000 images from about 60,000 patients and 500 different screening centers, and encourages the development of algorithms that are robust to ungradable and unexpected input data. We evaluated solutions from 14 teams in this paper and found that the best teams performed similarly to a set of 20 expert ophthalmologists and optometrists. The highest-scoring team achieved an area under the receiver operating characteristic curve of 0.99 (95% CI: 0.98-0.99) for detecting ungradable images on-the-fly. Additionally, many of the algorithms showed robust performance when tested on three other publicly available datasets. These results demonstrate the feasibility of robust AI-enabled glaucoma screening.

Colorectal cancer (CRC) has attracted the attention of scientific communities as one of the leading causes of death in humans

Background: Pancreatic cancer (PC) has an extremely poor prognosis and is growing worldwide. In Kazakhstan, it is among the five leading causes of cancer death. However, local epidemiological studies of PC are scarce. A retrospective population-based study was conducted to investigate the PC incidence, mortality, and survival in Kazakhstan, using data from the Electronic Registry of Oncological Patients for the period 2014–2023. Methods: Incidence, prevalence, and crude mortality rates were calculated per 100,000 population. The all-cause mortality rate per 1000 person-years (PY) was obtained based on socio-demographic and medical characteristics and for different regions. Survival analysis was performed using the Kaplan–Meier method and Cox regression models. Results: A total of 11,934 cases were analyzed. The annual incidence rate significantly increased from 5.9 to 6.9 per 100,000. The mortality rate per 100,000 also increased from 4 to 6. The highest incidence was observed in the 60–74 age group (49.2%), with an equal sex distribution. The mortality rate was the highest in patients aged 75 and older. Northern and central regions had the highest incidence rates as of 2023. Atyrau, West Kazakhstan, Pavlodar, and Abay had the highest mortality rates per 1000 PY. The five-year survival rate was 10.9%. An older age, a male sex, advanced cancer stages, and a Russian ethnicity significantly increased the risk of death. Conclusions: PC represents a significant healthcare problem in Kazakhstan, with late diagnosis and poor survival being the main challenges. This study highlights the need to improve the timely detection of PC and address the identified disparities.

In 2008, Kazakhstan introduced a structured ophthalmology residency program. Between 2008 and 2020, two parallel training pathways coexisted: a three-year

The epidemiology of type 1 diabetes mellitus (T1DM) in children aged 0-17 in Kazakhstan was explored using aggregated large-scale healthcare data from the unified national electronic health system (UNEHS) in 2014-2021. Incidence, period prevalence, and mortality rates per 100,000 population at risk were calculated. Cox proportional hazards regression modelling and Kaplan-Meier methodology were used. The follow-up period was from the initial date of T1DM until death or the end of the follow-up (31 December 2021). Among the 11,088 patients, the incidence rate of T1DM decreased from 28.1 to 24.5 per 100,000 population, whereas the period prevalence rate increased from 48.8 to 179.1, and the mortality rate rose from 0.18 to 0.67. Diagnosis at age 0-1 years (hazards ratio [HR] 4.42), presence of nephropathy (HR 8.94) or neoplasms (HR 1.64) were associated with a higher risk of death, while the presence of retinopathy (HR 0.31) was associated with a lower risk of death.

Background/Objectives: Epilepsy is a major neurological disorder associated with significant comorbidity and treatment challenges. In low- and middle-income countries, access to newer antiseizure medications (ASMs) remains limited, and prescription patterns often rely on older agents. This study aimed to characterize national prescribing patterns of ASMs among patients with epilepsy in Kazakhstan from 2021 to 2023. Methods: We conducted a retrospective observational study using de-identified electronic health record data from the Unified National Electronic Health System of Kazakhstan. All patients with an ICD-10 diagnosis of epilepsy (G40) and at least one ASM prescription during 2021–2023 were included. Prescription frequencies, therapy type, and chronic polytherapy levels were analyzed. Associations between therapy type, age, and comorbidity status were determined. Results: A total of 54,274 patients were identified (median age 42 years; interquartile range (IQR) 31–57). Monotherapy predominated: 61.7% remained on monotherapy, 18.5% remained on polytherapy, and 19.8% had mixed exposure. Carbamazepine and valproic acid were most frequently prescribed (64.3% and 45.6% of patients, respectively). Among those with chronic medication data (n = 15,752), nervous-system drugs were common (70.1%), led by psycholeptics (49.7%); frequently dispensed agents included chlorpromazine (n = 5991), clozapine (n = 1875), and risperidone (n = 1642). Cardiovascular agents were recorded in 37.2% (acetylsalicylic acid n = 4056; atorvastatin n = 2235), and diabetes drugs in 12.1% (metformin n = 1430). Conclusions: Epilepsy treatment in Kazakhstan remains dominated by older broad-spectrum ASMs, while the use of lamotrigine and levetiracetam is steadily increasing. The frequent co-prescription of psychotropic and cardiometabolic drugs underscores the need for coordinated, multidisciplinary care and continued monitoring of prescribing patterns to enhance treatment safety and effectiveness.