EAEkaterina Sergeevna Akhmad

Ekaterina Sergeevna Akhmad

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ekaterina Sergeevna Akhmad has a total of 100 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    AI Model Reporting Standards in Health Care: Systematic Review and Consolidation

    by Ekaterina Akhmad, Daniël Slob, Aiara Lobo Gomes, Simone Mingels, Andre Dekker, Johan van Soest

    Background: AI technologies are currently experiencing significant growth in development and use in health care. The AI model lifecycle includes several stages, all of which should be adequately described. Reporting standards are commonly used for this purpose. However, the plain-text structure of these standards prevents transparent machine-readability of this information. Objective: This systematic review aims to investigate AI model reporting standards from clinical databases and technical documents published since 2016. Methods: The methodological systematic review was conducted according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines. The inclusion criteria of this systematic review were papers published from 2016 to April 2026 in English and in a peer-reviewed journal with open access. We aimed to include standards for different data types (structured, images, and text-based). The exclusion criteria were specific medical domain, incomplete reports, and reviews. The following libraries have been consulted: Scopus and Web of Science, MEDLINE and Embase, the IEEE Xplore digital library, and the ACM Digital Library. We applied an Automated Systematic Review software tool (Utrecht University) to find relevant papers after records retrieval. Two reviewers (EA, DS) screened relevant papers independently and invited a third reviewer (JvS) to reach a consensus. All included papers were analyzed to extract relevant lifecycle stage, publication type, data type, and reporting questions. The results were presented and synthesized in a consolidated list by grouping questions and ordering them in a logical sequence according to the AI model lifecycle. Results: The total number of included studies was 25 from clinical and technical databases (22 and 3, respectively). The consolidated list includes 134 questions ordered in 7 groups: “Problem identification,” “Data collection and processing,” “Model development,” “Technical validation,” “Functional validation,” “Operation & Monitoring,” and one additional group with “Statements.” Groups according to the lifecycle stages contain all relevant information for each stage. Both clinical and technical papers reflect information for “Problem identification” (s=5), “Data collection and processing” (s=25), “Model development” (s=13), “Technical validation” (s=14). While “Functional validation” (s=30) was represented mostly in clinical papers and “Operation & Monitoring” (s=18) in technical ones. In the “Statements” (s=29), all general questions were summarized, describing reusability and reproducibility of the model, and highlighting ethical considerations, such as model fairness, explainability, interpretability, and related risk. It was shown that only 10 out of 15 FAIR (findable, accessible, interoperable, reusable) principles were addressed in the consolidated list, with focus on providing rich metadata (F2) and accurate and relevant descriptions (R1). Conclusions: We furthermore considered the mapping of the consolidated questions with FAIR principles. In future, we aim to incorporate the results of our work into a metadata schema for AI models developed according to FAIR principles.

  • Open Access

    Prospects for using artificial intelligence to detect Spina Bifida in fetuses, children, and adults

    by V. E. Kazarinova, V. V. Zinchenko, A. Y. Kovalchuk, E. S. Akhmad, A. P. Pamova, K. M. Arzamasov, O. V. Omelyanskaya, A. V. Vladzymyrskyy

    Background and Objective: Spina Bifida (SB) is a congenital spinal malformation requiring timely diagnosis. Digitalization of healthcare and rapid development of artificial intelligence technologies (AI) facilitate AI implementation in various fields of medicine, including SB diagnosis. The aim of this study is to analyze the potential of AI for detecting signs of Spina Bifida in fetuses, children, and adults, evaluate existing approaches, and identify key areas for further research and development. Methods: this review includes original and review publications, conference materials describing the application of AI algorithms to any type of data at any stage of the diagnostic process of SB in fetuses, children, and adults. A search of available literature was conducted in the following databases: PubMed, Google Scholar, and the Russian Science Citation Index (eLibrary.ru). Results: seventeen publications on the use of AI in the diagnosis of SB were selected, which met the search criteria. Using AI algorithms, the following types of data were identified and analyzed: medical imaging data (magnetic resonance imaging, ultrasound, X-ray, video urodynamics), laboratory diagnostics data, and genetic information. Discussion: AI algorithms have shown high efficiency in detecting SB and its complications at various stages of the diagnostic process. The prospect of using computer vision to detect SB in images of various modalities as well as machine learning algorithms in laboratory diagnostics and genetic research was demonstrated.

  • Open Access

    Understanding Clinicians’ Informational Needs for AI-Driven Clinical Decision Support Systems: Qualitative Interview Study

    by Simone Mingels, Hannah Piehl, Madeline Therrien, Ekaterina Akhmad, Anniek van Hienen, Johan van Soest, Laura Hochstenbach, Andre Dekker, Olga Damman, Rianne Fijten

    Background: Advancements in artificial intelligence (AI) are transforming health care, particularly through AI-driven clinical decision support systems (AI-CDSS) that aid in predicting disease progression and personalizing treatment. Despite their potential, adoption remains limited due to clinician concerns about algorithm misuse, misinterpretation, and lack of transparency. Objective: This qualitative study explores the informational needs and preferences of clinicians to better understand and appropriately use AI-CDSS in decision-making. In parallel, this study explores AI experts’ perspectives on what information should be communicated to enable safe and appropriate use of AI-CDSS. Methods: A qualitative description design study was conducted using semistructured interviews with 16 participants (8 clinicians and 8 AI experts). Discussions focused on experiences with AI, informational needs, and feedback on existing reporting standards, including Model Cards, Model Facts, and the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis–Artificial Intelligence (TRIPOD-AI) checklist. The transcripts were analyzed through codebook thematic analysis. Results: Four key themes were identified: (1) clinicians need clear information on training data, its origin, size, and inclusion and exclusion criteria, to judge model applicability; (2) performance metrics must go beyond the area under the curve (AUC) and be clinically relevant to support informed decisions; (3) limitations and warnings about inappropriate use should be specific and clearly communicated to prevent misuse; and (4) information should be presented in layered, customizable formats within existing clinical software, avoiding unnecessary jargon, and allowing optional deeper explanations. While each of the reviewed reporting standards offered strengths, none were considered sufficient alone. Participants recommended a combined and clinician-centered approach to information delivery. Alignment of reporting standards with clinical workflows and decision thresholds was thought to be crucial to bridge the usability gap. Conclusions: To improve AI-CDSS adoption in clinical practice, reporting standards must be designed for better clinician comprehension and usability. Enhancing transparency, particularly regarding training data and performance, can likely help clinicians assess AI-CDSS more effectively. Information should be delivered in an accessible, layered format, fitting clinical workflows. Co-creation with clinicians throughout AI-CDSS development was a cross-cutting theme, highlighting its importance in ensuring tools are not only technically sound but also practically usable. Future research should explore how to structurally report on performance and validation metrics for clinician understanding and assess the impact of information provision on AI-CDSS adoption.


  • Open Access

    Understanding Clinicians’ Informational Needs for AI-driven Clinical Decision Support Systems: Qualitative Interview Study (Preprint)

    by Simone Mingels, Hannah Piehl, Madeline Therrien, Ekaterina Akhmad, Anniek van Hienen, Johan van Soest, Laura Hochstenbach, Andre Dekker, Olga Damman, Rianne Fijten

    BACKGROUND Advancements in Artificial Intelligence (AI) are transforming healthcare, particularly through AI-driven Clinical Decision Support Systems (AI-CDSS) that aid in predicting disease progression and personalizing treatment. Despite their potential, adoption remains limited due to clinician concerns about algorithm misuse, misinterpretation, and lack of transparency. OBJECTIVE This qualitative study explores the informational needs and preferences of clinicians to better understand and appropriately use AI-CDSS in decision-making. In parallel this study explores AI experts’ perspectives on what information should be communicated to enable safe and appropriate use of AI-CDSS. METHODS A qualitative description design study was conducted using semi-structured interviews with 16 participants (8 clinicians and 8 AI experts). Discussions focused on experiences with AI, informational needs, and feedback on existing reporting standards including Model Cards (Mitchell et al., 2019), Model Facts (Sendak et al., 2020), and the TRIPOD-AI checklist (Collins et al., 2015, 2024). The transcripts were analyzed through codebook thematic analysis. RESULTS Four key themes were identified: (i) Clinicians need clear information on training data, its origin, size, and inclusion/exclusion criteria, to judge model applicability; (ii) Performance metrics must go beyond AUC and be clinically relevant to support informed decisions; (iii) Limitations and warnings about inappropriate use should be specific and clearly communicated to prevent misuse; (iv) Information should be presented in layered, customizable formats within existing clinical software, avoiding unnecessary jargon and allowing optional deeper explanations. While each of the reviewed reporting standards offered strengths, none were considered sufficient alone. Participants recommended a combined and clinician-centered approach to information delivery. Alignment of reporting standards with clinical workflows and decision thresholds was thought to be crucial to bridge the current usability gap. CONCLUSIONS To improve AI-CDSS adoption in clinical practice, reporting standards must be designed for better clinician comprehension and usability. Enhancing transparency, particularly regarding training data and performance, can likely help clinicians assess AI-CDSS more effectively. Information should be delivered in an accessible, layered format, fitting clinical workflows. Co-creation with clinicians throughout AI-CDSS development was a cross-cutting theme, highlighting its importance in ensuring tools are not only technically sound but also practically usable. Future research should explore how to structurally report on performance and validation metrics for clinician understanding and assess the impact of information provision on AI-CDSS adoption.

  • Open Access

    Opportunistic screening for osteoporosis using artificial intelligence-based morphometric analysis of chest computed tomography images: a retrospective multi-center study in Russia leveraging the COVID-19 pandemic

    by Alexey Vladimirovich Petraikin, Perry Joseph Pickhardt, Mikhail Gennadevich Belyaev, Zhanna Evgenievna Belaya, Maxim Evgenievich Pisov, Alim Niyazovich Bukharaev, Aleksei Andreevich Zakharov, Nikita Dmitrievich Kudryavtsev, Tatiana Mikhailovna Bobrovskaya, Dmitry Sergeevich Semenov, et al.

    Study Design: Retrospective cohort study.Purpose: To evaluate the effectiveness of opportunistic osteoporosis screening using an artificial intelligence (AI) algorithm for detecting vertebral compression deformity (VCD >25%) and reduced bone mineral density (BMD) from routine chest computed tomography (CT) scans.Overview of Literature: Osteoporosis is an insidious metabolic disease that often remains asymptomatic for a long time, and is typically diagnosed due to the occurrence of complications. An approach for diagnosing osteoporosis based on routine CT examinations, including the use of AI services, is being actively studied.Methods: Patients aged >50 years who underwent chest CT using the standard protocol between 09.06.2021 and 30.06.2021 at four inpatient and three outpatient clinics were retrospectively enrolled. The morphometric AI algorithm detected vertebral compression index and vertebrae density in Hounsfield units (HU). The AI algorithm was calibrated for BMD measurements using a phantom. Osteoporotic BMD was defined according to the American College of Radiology criteria (<80 mg/mL). The presence of vertebral fracture (VF) was verified using semiquantitative and algorithm-based qualitative methods by three radiologists, followed by two experts with 15 and 35 years of experience in the field.Results: CT studies of 1,888 patients (mean age, 66.3 years) were included. The AI algorithm detected VCD in 336 patients (17.8%), with 105 (5.5%) having VF. Low BMD values were detected in 501 patients (26.5%; 31.0% of females, 18.6% of males).Conclusions: We observed high diagnostic accuracy of opportunistic osteoporosis screening using AI algorithms for detecting VF and low BMD. AI-based opportunistic screening of osteoporosis and VF in chest CT scans can facilitate the identification of high-risk cohorts.


  • Open Access

    What to Report? A Systematic Review of Medical AI Reporting Guidelines: Preliminary Results

    by Ekaterina Akhmad, Daniël Slob, Aiara Lobo Gomes, Andre Dekker, Johan van Soest

    We present preliminary results of a systematic review of reporting guidelines for nine papers from clinical and non-clinical databases. Initial results show that there is no single standard that fulfills the needs of distinct stakeholders.


  • Open Access

    The inter-reader agreement in the interpretation of mammography images according to BI-RADS by Moscow radiologists

    by Avet S. Azaryan, Lev D. Pestrenin, Yuriy A. Vasilev, Ekaterina S. Akhmad, Kirill M. Arzamasov

    Background: Breast malignancies take a leading position among incident cancers in women. Mammography has been recognized as the main method for early detection of breast cancer. However, mammogram assessments are based on a subjective opinion of the radiologist, which could lead to diagnostic disagreement. According to the literature, inter-radiologist agreement on mammograms varies from 0.450 to 0.888. Aim: To assess the inter-reader agreement in mammogram interpretation with BI-RADS (Breast Imaging Reporting and Data System) by radiologists of the Moscow city (Russia). Methods: The study included 741 mammography images done from January 15, 2020, to June 25, 2023. All mammograms were downloaded from the Unified Radiology Information Service of the Unified Medical Information and Analytical System (EMIAS) of the Moscow city and included radiologist reports with a BI-RADS score (the initial assessment). Each mammogram was further analyzed by two radiologists (with their job experience from 2 to 5 years) (this was the first revision) and thereafter by two more radiologists (with their job experience above 5 years and scientific degree) as a part of the expert review. The inter-reader agreement was assessed using an intra-class correlation coefficient. Results: The inter-reader agreement for the full BI-RADS score between radiologists who performed the initial assessment and those performing the first revision ranged from 0.836 [95% confidence interval (CI) 0.801–0.865] to 0.875 [95% CI 0.848–0.897]. Similar agreement was observed between radiologists who performed the initial assessment and the experts: 0.838 [95% CI 0.804–0.866] to 0.879 [95% CI 0.854–0.901]. The agreement on the full BI-RADS scale between radiologists who performed the first revision and the experts was significantly higher (p 0.001) than with those performing the initial assessment and ranged from 0.890 [95% CI 0.866–0.910] to 0.963 [95% CI 0.954–0.970]. Conclusion: The inter-reader agreement between radiologists of the Moscow city in the assessment of mammography study results on the full BI-RADS scale is high. The agreement between the radiologists who performed the revision is higher than their agreement with the radiologists who performed the initial assessment, which may indicate better and more stable results obtained during the revision.


  • Open Access

    Prostate magnetic resonance imaging (MRI) in patients with hip implants—presetting a protocol using a phantom

    by Yuriy A. Vasilev, Olga Yu. Panina, Dmitry S. Semenov, Ekaterina S. Akhmad, Kristina A. Sergunova, Stanislav A. Kivasev, Alexey V. Petraikin

    Background: Metal structures are a source of artifacts that significantly complicate the interpretation of magnetic resonance imaging (MRI). The use of prostate MRI as a preliminary test in men with a suspicion on prostate cancer leads to an increased use of the test. The aim of this study was to solve a clinically significant problem: to ensure the reduction of artifacts from metal hip implants during prostate MRI. Another goal was to evaluate the impact of artifact reduction methods on quantitative measurements. Methods: The prostate gland (PG) phantom model was a cylinder filled with an aqueous solution of polyvinylpyrrolidone at the concentrations of 40%, 30%, and 20% [central zone (CZ), peripheral zone (PZ), and “lesion”, respectively]. Phantom MRI study was conducted on Philips Ingenia 1.5T and Philips Ingenia 3T scanners. Results: For 1.5 T, the reduction in the influence of artifacts inside region of interest (ROI) was observed, expressed in a decrease in the average apparent diffusion coefficient (ADC) (CZ, PZ, “lesion”) for the manual artifact reduction (MAR) and ZOOM (title of software artifact reduction) techniques compared to the standard method. For 3T this effect was not detected. The same ADC results were obtained for Standard and MAR techniques, and increased ADC values for ZOOM. Despite the fact that the spread of ADC values on 3.0T scanners was minimal, there was a significant deviation of ADC values from the reference ones (up to 30.4%). Therefore, it is necessary to use a correction coefficient in the ADC calculation for the 3.0 T device. In the presented clinical case, high-quality tomograms were obtained without any artifacts, despite the presence of two hip replacement devices in the scanning area. Conclusions: The accurate prostate MRI in the presence of implants is essential for an accurate diagnosis. This approach allows to reduce artifacts from hip implants, to visualize PG and periprostatic tissue in the best way, and to detect malignant and benign changes.


  • Quality control of quantitative diffusion-weighted magnetic resonance imaging: metrological problems

    by Yu. A. Vasilev, E. S. Akhmad, M. V. Cherkasskaya, D. S. Semenov, O. Yu. Panina, A. V. Petraikin

  • Quality control of quantitative diffusion-weighted magnetic resonance imaging: metrological problems

    by V. A. Vasilev, E. S. Akhmad, M. V. Cherkasskaya, D. S. Semenov, O. Yu. Panina, A. V. Petraikin

    Quantitative magnetic resonance imaging is a modern method for detecting pathological changes in the patient’s tissues. However, images with quantitative characteristics are not widely used due to the limitation of the accuracy and reproducibility of the measured values. The purpose of this work is to formulate the metrological problem of quantitative magnetic resonance imaging and to ensure the reliability of research based on the analysis of practical approaches to quality control of diffusion-weighted magnetic resonance imaging. As part of the work performed, an analysis was carried out of the use of phantoms as means to ensure quality control of certain parameters of quantitative magnetic resonance imaging. The importance of validation was noted, the metrics used to control the quality of quantitative magnetic resonance imaging were highlighted, an overview of examples of clinical studies using diffusion-weighted magnetic resonance imaging was presented. It was found that accurate calibration and testing of magnetic resonance imaging scanners, as well as verification of image analysis tools, are necessary for the use of quantitative magnetic resonance imaging data in clinical practice.