Research Platform Research Articles

Proceedings of the Second International Meeting on Endemic Mycoses of the Americas (IMEMA), and First International Symposium on Implantation Mycoses (ISIM).

The Second International Meeting on Endemic Mycoses of the Americas (IMEMA) and the First International Symposium on Implantation Mycoses (ISIM) took place in Santiago del Estero, Argentina during September 25-27th, 2023. The conference provided a platform for researchers, clinicians, and experts to discuss the latest developments in the field of endemic and implantation mycoses. Topics included epidemiology, diagnostic advances, treatment strategies, and the impact of environmental factors in the spread of these fungal diseases. IMEMA and ISIM contributed to the regional discourse on the mycoses, emphasizing the importance of international cooperation in addressing these public health challenges.

The egg-counter: a novel microfluidic platform for characterization of Caenorhabditis elegans egg-laying.

Reproduction is a fundamental process that shapes the demography of every living organism yet is often difficult to assess with high precision in animals that produce large numbers of offspring. Here, we present a novel microfluidic research platform for studying Caenorhabditis elegans' egg-laying. The platform provides higher throughput than traditional solid-media behavioral assays while providing a very high degree of temporal resolution. Additionally, the environmental control enabled by microfluidic animal husbandry allows for experimental perturbations difficult to achieve with solid-media assays. We demonstrate the platform's utility by characterizing C. elegans egg-laying behavior at two commonly used temperatures, 15 and 20 °C. As expected, we observed a delayed onset of egg-laying at 15 °C degrees, consistent with published temperature effects on development rate. Additionally, as seen in solid media studies, egg laying output was higher under the canonical 20 °C conditions. While we validated the Egg-Counter with a study of temperature effects in wild-type animals, the platform is highly adaptable to any nematode egg-laying research where throughput or environmental control needs to be maximized without sacrificing temporal resolution.

Bibliometric Analysis of Scientific Publications on Communicative Behavior Problems

Purpose of research. The purpose of the study is to analyze the dynamics of the publication activity of scientific research in the field of studying communicative behavior. Communicative behavior is an object with an interdisciplinary research status. It falls into the area of research interest of various scientific fields. A bibliometric analysis of publication activity was carried out in connection with solving several tasks: to find out areas of knowledge in which the greatest publication activity is concentrated, to study the methods that are used in various fields of communicative behavior analysis, to identify organizations that are included in this research search.Methods. The study was conducted in two scientific electronic databases: the Russian Scientific Electronic Library Elibrary.ru and the international open platform for researchers and scientific organizations Lens. The bibliometric analysis was used as the research method. It involves the quantification of documentary information flows and it is based on quantitative research indicators reflecting the state of science as a whole or its individual branches.Results. As a result of the bibliometric analysis of publication activity on the problems of scientific research in the field of communicative behavior, communicative behavior in the digital environment and communicative behavior in social networks, a significant increase in publication activity was revealed in both international and Russian information databases over the past 10 years (2013 - 2023). It is also noted that the predominant number of publications on the issues studied is concentrated in the field of psychology. However, we can trace a shift in the focus of foreign research on communicative behavior towards digitalization in information technology, and Russian research towards the field of digital technologies in the educational environment.Conclusion. The results obtained indicate the high relevance, as well as the scientific and practical significance of the research topic on the problems of communicative behavior in general, as well as communicative behavior in the digital environment and social networks, in particular.

The Abstract book of the XXI Conference of Junior Research

The Conference of Junior Researchers in Psychology is an annual event organized by doctoral students at the Institute of Psychology, Vilnius University. The conference provides a platform for psychology students and junior researchers from universities in Lithuania and abroad to showcase their scientific work and findings. This year's conference focused on the challenges and opportunities faced by people of our time.

The interaction between brain-based learning strategies and patterns of infographics and its influence on the development of information concepts among Saudi undergraduate cybersecurity students

The study reported in this paper investigates the impact of the interaction between brain-based learning strategies (spaced repetition and distributed practice - mental models) and patterns of infographics (static/animated) in e-learning environments and its impact on the development of informational concepts among cybersecurity students. The quantitative data were collected by means of Information Concept Test to determine the levels of information concepts according to the Frayer model (1969). The research sample consists of 80 male and female undergraduate students in Qassim University, who were classified into four quasi-experimental groups according to their preferred patterns in the infographic. Quantitative analysis of findings from this study shows an effect for the interaction between the variables of brain-based learning strategies (spaced repetition and distributed practice - mental models) and patterns of infographics (static/animated) in e-learning environments in the test scores of information concepts in the post-administration, where the significance level (.011) is less than the significance level (0.05). Findings also revealed that the repetition of information at increasing intervals of time using the infographics is effective to learning concepts in an organized manner and to improving short memory. Furthermore, the mental model’s strategy also helped to retain information. The study recommends encouraging the use of brain-based learning strategies and patterns of infographics (static/animated) in e-learning environments to explore the relationships between different scientific concepts, to expand students’ knowledge, and to discover inter-relationships between different subject elements. The study provides a platform for further research to employ different brain-based learning strategies within e-learning environments to acquire higher-order thinking skills and improve students’ memory and mental capacity with the use of modern technological techniques that achieve learning quality.

An open-source research platform for mechanical ventilation based on Simulink® and STM32 nucleo

Abstract Gain in knowledge in experimental fields of research is mostly achieved using commercial hardware platforms. The linked costs however can limit a broad access by scientists and in the specific case of mechanical ventilation the pandemic demonstrated that further and collective research is essential and necessary. This contribution presents the modular design and implementation of a research platform which is based on STM32 Nucleo boards and Simulink®. The hardware required such as the pneumatic circuit are covered as well as the software architecture in which clinician related settings are processed for control references. The core functionality of mandatory volume controlled (VCV) and pressure controlled ventilation (PCV) while ensuring a positive end-expiratory pressure for the patient ( PEEP ) $(\text{PEEP})$ is evaluated and the foundational software models are published in a repository.

Mimicking chronic alcohol effects through a controlled and sustained ethanol release device

Alcohol consumption, a pervasive societal issue, poses considerable health risks and socioeconomic consequences. Alcohol-induced hepatic disorders, such as fatty liver disease, alcoholic hepatitis, chronic hepatitis, liver fibrosis, and cirrhosis, underscore the need for comprehensive research. Existing challenges in mimicking chronic alcohol exposure in cellular systems, attributed to ethanol evaporation, necessitate innovative approaches. In this study, we developed a simple, reusable, and controllable device for examining the physiological reactions of hepatocytes to long-term alcohol exposure. Our approach involved a novel device designed to continuously release ethanol into the culture medium, maintaining a consistent ethanol concentration over several days. We evaluated device performance by examining gene expression patterns and cytokine secretion alterations during long-term exposure to ethanol. These patterns were correlated with those observed in patients with alcoholic hepatitis. Our results suggest that our ethanol-releasing device can be used as a valuable tool to study the mechanisms of chronic alcohol-mediated hepatic diseases at the cellular level. Our device offers a practical solution for studying chronic alcohol exposure, providing a reliable platform for cellular research. This innovative tool holds promise for advancing our understanding of the molecular processes involved in chronic alcohol-mediated hepatic diseases. Future research avenues should explore broader applications and potential implications for predicting and treating alcohol-related illnesses.

FTH1 overexpression using a dCasRx translation enhancement system protects the kidney from calcium oxalate crystal-induced injury

The engineered clustered regularly interspaced short palindromic repeats (CRISPR)–CRISPR-associated protein (Cas) system is currently widely applied in genetic editing and transcriptional regulation. The catalytically inactivated CasRx (dCasRx) has the ability to selectively focus on the mRNA coding region without disrupting transcription and translation, opening up new avenues for research on RNA modification and protein translation control. This research utilized dCasRx to create a translation-enhancement system for mammals called dCasRx-eIF4GI, which combined eukaryotic translation initiation factor 4G (eIF4GI) to boost translation levels of the target gene by recruiting ribosomes, without affecting mRNA levels, ultimately increasing translation levels of different endogenous proteins. Due to the small size of dCasRx, the dCasRx-eIF4GI translation enhancement system was integrated into a single viral vector, thus optimizing the delivery and transfection efficiency in subsequent applications. Previous studies reported that ferroptosis, mediated by calcium oxalate (CaOx) crystals, significantly promotes stone formation. In order to further validate its developmental potential, it was applied to a kidney stone model in vitro and in vivo. The manipulation of the ferroptosis regulatory gene FTH1 through single-guide RNA (sgRNA) resulted in a notable increase in FTH1 protein levels without affecting its mRNA levels. This ultimately prevented intracellular ferroptosis and protected against cell damage and renal impairment caused by CaOx crystals. Taken together, this study preliminarily validated the effectiveness and application prospects of the dCasRx-eIF4GI translation enhancement system in mammalian cell-based disease models, providing novel insights and a universal tool platform for protein translation research and future therapeutic approaches for nephrolithiasis.

Designing the user interface of a ventilator under the constraints of a pandemic

Abstract This paper reports on the design of the GUI component of the PV1000, a fully-functional, cost-efficient pandemic ventilator developed during the COVID-19 pandemic. Our main objective in designing the user interface was to expose the rich features of the ventilator, which are on-par with many commercial medical devices, through an interface that is simple to use even by medical staff with little prior experience with ventilators. We present an agile development process which is intended to address the fast changing and potentially unclear requirements of a pandemic. This is to address the specific situation where domain experts as well as specific hardware have shortages, resulting in recurring changes in requirements. This occurs in conjunction with the collaboration of developers, not all of whom are familiar with the development of medical devices. Despite the pandemic situation, we have made a deliberate decision to use existing software engineering tools such as continuous integration. Additionally, we are employing a multi-platform development framework in order to utilise the resulting advantages, for example, if there are changes in requirements. We present and discuss the system, hardware and software architecture of the components that allow users to interact with the device. The focus here is on the dynamic generation of parts of the software architecture, which enables rapid adaptation to changing conditions on the part of the software. The user interface is evaluated through a user survey, where the majority of participants describe the interface as clear and intuitive. The entire ventilator was evaluated in one animal trial and fortunately never had to be used on humans. The next step is to convert the setup into an open source project that can be used as a research platform for ventilators.

Bringing platform trials closer to reality by enabling with digital research environment (DRE) connectivity

Platform trials are generally regarded as an innovative approach to address clinical valuation of early stage candidates, regardless of modality as the evidence evolves. As a type of randomized clinical trial (RCT) design construct in which multiple interventions are evaluated concurrently against a common control group allowing new interventions to be added and the control group to be updated throughout the trial, they provide a dynamic and efficient mechanism to compare and potentially discriminate new treatment candidates. Their recent use in the evaluation of new therapies for COVID-19 has spurred new interest in the approach. The paucity of platform trials is less influenced by the novelty and operational requirements as opposed to concerns regarding the sharing of intellectual property (IP) and the lack of infrastructure to operationalize the conduct in the context of IP and data sharing. We provide a mechanism how this can be accomplished through the use of a digital research environment (DRE) providing a safe and secure platform for clinical researchers, quantitative and physician scientists to analyze and develop tools (e.g., models) on sensitive data with the confidence that the data and models developed are protected. A DRE, in this context, expands on the concept of a trusted research environment (TRE) by providing remote access to data alongside tools for analysis in a securely controlled workspace, while allowing data and tools to be findable, accessible, interoperable, and reusable (FAIR), version-controlled, and dynamically grow in size or quality as a result of each treatment evaluated in the trial.

The Influence of Technological Capability on Internationalization Status of Public Universities in Kenya

Purpose: The purpose of the study was to determine influence of technological capability on internationalization status of public universities in Kenya. Descriptive research design was used to conduct the study. Methodology: The study employed a descriptive research design. This research study used positivism research philosophy. The target population comprised of all the 31 fully chartered public universities in Kenya. Since the population was small, no sampling was done and a census approach was applied in the study. Primary quantitative data was assembled by administering structured questionnaires. To analyze quantitative data, descriptive analysis, factor analysis and inferential statistics were used. Descriptive analysis comprised of the standard deviations and means. Inferential statistics comprised regression and correlations. Both multiple and linear regressions was used. Coding and analyzing of data was done using Statistical Package for Social Sciences (SPSS 26.0). Tables, diagrams and charts were further used to display the outcomes. Findings: From the study findings technological capability had a statistically significant and positive influence on internationalization status. Unique contribution to theory, practice and policy: Research findings showed that there was need for improvement in the use of online platforms for teaching and research.  The study therefore recommends that public universities should therefore invest in upgrading of their online platforms for teaching and research so as to increase on their economies of scale.

Use of waste plastic oil as a fuel in reactivity-controlled compression ignition engines: a bibliometric investigation from 2017–23

Abstract Waste plastic oil, generated through the pyrolysis of plastic without oxygen, known as plastic-to-fuel conversion, stands as a promising alternative fuel. This research employs bibliometric analysis, a quantitative method, to comprehensively assess publications in the domain of waste plastic oil integration within reactivity-controlled compression ignition engines. Utilizing Scopus as the primary repository post-2017, the study categorizes information into pivotal aspects, including influential journals, countries, authors, affiliations, document types, thematic areas, sponsors and keywords. The analysis reveals significant contributions from diverse nations, prominently India, China, Turkey and Malaysia. Noteworthy is the prevalence of Energy, Engineering and Chemical Engineering as thematic focal points, with the journal Fuel leading the count followed by the journal Energy emerging as a prominent conduit. Institutional contributions are prolific, led by Gandhi Institute of Technology and Management University and Vellore Institute of Technology. Renowned authors ‘Gugulothu S.K’ and ‘He Z’ play a pivotal role in shaping the discourse. The National Natural Science Foundation of China stands out as a primary patron. This bibliometric analysis provides a structured understanding of waste plastic oil integration in reactivity-controlled compression ignition engines, laying the groundwork for future research avenues. The study identifies potential research platforms beyond Scopus, including Web of Science, CrossRef, Science Direct and Google Scholar, as valuable repositories for further exploration. Moreover, after careful observation of the research articles published by the top 10 authors as found in the study, it was found that the authors share a few common characteristics that helped them in advancing the understanding and application of waste plastic oil in reactivity-controlled compression ignition engines. These are also summarized in the present study with supporting data.

The impact of institutional support on university research efficiency in China: based on super-efficiency SBM and panel regression models

ABSTRACT This study utilizes provincial-level panel data from 2013 to 2021 from the Chinese mainland and applies the super-efficiency SBM model to measure provincial university research efficiency. This study categorizes institutional support into formal and informal types, examines the impact of institutional support on university research efficiency, and analyzes the mediating role of industry-university cooperation intensity and university research platform construction in this impact. Through regression analysis, the findings indicate that both formal and informal institutional support can promote university research efficiency. Institutional support can influence university research efficiency through the mediation of industry-university cooperation intensity and university research platform construction.

Increasing the appeal of plant-based foods through describing the consumption experience: A data-driven procedure

Global meat consumption is a significant contributor to greenhouse gases emissions and environmental degradation, therefore, shifting diets to plant-based products will help to protect planetary health. However, omnivorous consumers often perceive plant-based products as less tasty and appealing than their meat-based counterparts. Previous research has shown that presenting plant-based dishes in terms of the rewarding aspects of consumption (i.e., with consumption and reward descriptions) can make them more appealing. Here, we report three online studies (using the research platform Prolific) to illustrate and test a systematic, data-driven procedure for generating such consumption and reward descriptions. In Study 1 (N = 653), we asked participants to rate the extent to which various sensory, context, and hedonic features were viewed as positive or negative in relation to 20 savoury dishes. In Study 2 (N = 246), we selected the most positive features from Study 1 and asked participants to rate the fit of these features in relation to 12 novel plant-based dishes. In Study 3 (N = 1,204), we used the features with the highest “fit” scores from Study 2 to examine whether descriptions that incorporated them could increase the appeal and intention to order the same 12 plant-based dishes. As predicted, consumption and reward descriptions led to significantly higher dish appeal and order intentions compared to control descriptions. Consequently, consumption and reward descriptions may help to increase the consumption of plant-based foods, reducing the demand for animal-based products and the associated greenhouse gas emissions and other environmental impacts.

Gastric Organoid, a Promising Modeling for Gastric Stem Cell Homeostasis and Therapeutic Application.

The elucidation of the pathophysiology underlying various diseases necessitates the development of research platforms that faithfully mimic in vivo conditions. Traditional model systems such as two-dimensional cell cultures and animal models have proven inadequate in capturing the complexities of human disease modeling. However, recent strides in organoid culture systems have opened up new avenues for comprehending gastric stem cell homeostasis and associated diseases, notably gastric cancer. Given the significance of gastric cancer, a thorough understanding of its pathophysiology and molecular underpinnings is imperative. To this end, the utilization of patient-derived organoid libraries emerges as a remarkable platform, as it faithfully mirrors patient-specific characteristics, including mutation profiles and drug sensitivities. Furthermore, genetic manipulation of gastric organoids facilitates the exploration of molecular mechanisms underlying gastric cancer development. This review provides a comprehensive overview of recent advancements in various adult stem cell-derived gastric organoid models and their diverse applications.

The establishment of a multiple myeloma clinical registry in the Asia–Pacific region: The Asia–Pacific Myeloma and Related Diseases Registry (APAC MRDR)

BackgroundMultiple myeloma (MM) is the second most common haematological cancer worldwide. Along with related diseases including monoclonal gammopathy of undetermined significance (MGUS), plasma cell leukaemia (PCL) and plasmacytoma, MM incidence is rising, yet it remains incurable and represents a significant disease burden. Clinical registries can provide important information on management and outcomes, and are vital platforms for clinical trials and other research. The Asia–Pacific Myeloma and Related Diseases Registry (APAC MRDR) was developed to monitor and explore variation in epidemiology, treatment regimens and their impact on clinical outcomes across this region. Here we describe the registry’s design and development, initial data, progress and future plans.MethodsThe APAC MRDR was established in 2018 as a multicentre collaboration across the Asia–Pacific, collecting prospective data on patients newly diagnosed with MM, MGUS, PCL and plasmacytoma in Korea, Singapore, Malaysia and Taiwan, with China recently joining. Development of the registry required a multidisciplinary team of clinicians, researchers, legal and information technology support, and financial resources, as well as local clinical context from key opinion leaders in the APAC region. Written informed consent is obtained and data are routinely collected throughout treatment by hospital staff. Data are stored securely, meeting all local privacy and ethics requirements. Data were collected from October 2018 to March 2024.ResultsOver 1700 patients from 24 hospitals have been enrolled onto the APAC MRDR to date, with the majority (86%) being newly diagnosed with MM. Bortezomib with an immunomodulatory drug was most frequently used in first-line MM therapy, and lenalidomide-based therapy was most common in second-line. Establishment and implementation challenges include regulatory and a range of operational issues.ConclusionThe APAC MRDR is providing ‘real-world’ data to participating sites, clinicians and policy-makers to explore factors influencing outcomes and survival, and to support high quality studies. It is already a valuable resource that will continue to grow and support research and clinical collaboration in MM and related diseases across the APAC region.

Abstract Wrk2-01: Organoid Models of Cancer and the Tumor Microenvironment

Abstract Both cell-intrinsic and microenvironmental influences vitally govern tumor progression. Mutational, chromosomal and epigenetic alterations represent the former, while the latter is influenced by diverse stromal populations including fibroblasts, vasculature and immune cells. In vitro organoid culture provides an experimentally tractable platform for cancer research that is applicable to cell-autonomous and tumor microenvironmental studies. The first part of this lecture will describe our work using organoid culture to functionally validate tumor cell-intrinsic genomic alterations. Notably, cancer research has traditionally lacked in vitro methods where tumors can be holistically cultured in a non-reconstitutive manner that co-preserves neoplastic cells together with endogenous stromal components. Thus, the second part of this lecture will describe advances in 3D tumor organoid culture that allow growth of cancer cells in a manner that preserves their native interaction with diverse tumor-infiltrating immune cells and allows analysis of immune checkpoint inhibition. Citation Format: C. Kuo. Organoid Models of Cancer and the Tumor Microenvironment [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr Wrk2-01.

Exploring machine learning strategies for predicting cardiovascular disease risk factors from multi-omic data

BackgroundMachine learning (ML) classifiers are increasingly used for predicting cardiovascular disease (CVD) and related risk factors using omics data, although these outcomes often exhibit categorical nature and class imbalances. However, little is known about which ML classifier, omics data, or upstream dimension reduction strategy has the strongest influence on prediction quality in such settings. Our study aimed to illustrate and compare different machine learning strategies to predict CVD risk factors under different scenarios.MethodsWe compared the use of six ML classifiers in predicting CVD risk factors using blood-derived metabolomics, epigenetics and transcriptomics data. Upstream omic dimension reduction was performed using either unsupervised or semi-supervised autoencoders, whose downstream ML classifier performance we compared. CVD risk factors included systolic and diastolic blood pressure measurements and ultrasound-based biomarkers of left ventricular diastolic dysfunction (LVDD; E/e' ratio, E/A ratio, LAVI) collected from 1,249 Finnish participants, of which 80% were used for model fitting. We predicted individuals with low, high or average levels of CVD risk factors, the latter class being the most common. We constructed multi-omic predictions using a meta-learner that weighted single-omic predictions. Model performance comparisons were based on the F1 score. Finally, we investigated whether learned omic representations from pre-trained semi-supervised autoencoders could improve outcome prediction in an external cohort using transfer learning.ResultsDepending on the ML classifier or omic used, the quality of single-omic predictions varied. Multi-omics predictions outperformed single-omics predictions in most cases, particularly in the prediction of individuals with high or low CVD risk factor levels. Semi-supervised autoencoders improved downstream predictions compared to the use of unsupervised autoencoders. In addition, median gains in Area Under the Curve by transfer learning compared to modelling from scratch ranged from 0.09 to 0.14 and 0.07 to 0.11 units for transcriptomic and metabolomic data, respectively.ConclusionsBy illustrating the use of different machine learning strategies in different scenarios, our study provides a platform for researchers to evaluate how the choice of omics, ML classifiers, and dimension reduction can influence the quality of CVD risk factor predictions.

Abstract PO5-26-11: The Breast Cancer Research Foundation Drug Research Collaborative – A unique and innovative model for industry-funded, academically driven research to advance the field of breast cancer

Abstract The Breast Cancer Research Foundation (BCRF) is committed to preventing and curing breast cancer through groundbreaking research. In pursuit of this mission, the BCRF launched the Drug Research Collaborative (DRC) in 2016—a pioneering program designed to bridge the gap between academic investigators and access to investigational therapies, thereby fostering greater academic-driven research in breast cancer. The DRC's primary objective is to fund independent, innovative, and high-quality investigator-initiated trials (IITs) and pre-clinical/translational research projects. In conventional drug development, industry-sponsored registration trials play a crucial role, leaving limited resources and scope for exploratory and translational IITs that fall outside the industry's drug approval strategy. Additionally, industry-funded IIT research faces challenges such as reputational risks, perceived influence during internal review processes, intellectual property (IP) concerns, and logistics/program management burdens. The BCRF-DRC program addresses these challenges by issuing requests for proposals to generate creative and unbiased ideas, which are then vetted through an academic review process involving leading breast cancer experts. The most promising research projects are selected for further advancement. The BCRF-DRC program is facilitated by the BCRF research staff, providing project management, while the Translational Breast Cancer Research Consortium (TBCRC), founded by the BCRF and also supported by Susan G. Komen, supports the clinical trial aspects of the program. Since its inception, the BCRF-DRC has expanded from one to three industry partners, securing a total funding of $25 million for 15 projects, including seven clinical trials and eight pre-clinical projects. This abstract reports on the ongoing progress and outcomes achieved by these three programs. The BCRF-DRC represents a revolutionary paradigm in research funding and collaboration by harnessing the collective power of industry partners, philanthropic organizations, and academic institutions. Through this collaborative effort, the BCRF-DRC provides a unique platform for researchers to accelerate the translation of scientific discoveries into effective clinical interventions, thus making significant strides in the field of breast cancer in the coming decades. By empowering academic investigators, fostering unbiased research, and addressing the limitations of industry-funded IITs, the BCRF-DRC is revolutionizing breast cancer research and driving the development of novel interventions. This abstract highlights the transformative potential of the BCRF-DRC program and its contribution to advancing breast cancer treatments and ultimately improving patient outcomes. The success of this collaborative model serves as a testament to the power of multi-sector partnerships and the pivotal role they play in shaping the future of breast cancer research. Citation Format: Unnati Jariwala, Dorraya El-Ashry, Judy Garber, Larry Norton. The Breast Cancer Research Foundation Drug Research Collaborative – A unique and innovative model for industry-funded, academically driven research to advance the field of breast cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO5-26-11.

A novel model of artificial intelligence based automated image analysis of CT urography to identify bladder cancer in patients investigated for macroscopic hematuria.

To evaluate whether artificial intelligence (AI) based automatic image analysis utilising convolutional neural networks (CNNs) can be used to evaluate computed tomography urography (CTU) for the presence of urinary bladder cancer (UBC) in patients with macroscopic hematuria. Our study included patients who had undergone evaluation for macroscopic hematuria. A CNN-based AI model was trained and validated on the CTUs included in the study on a dedicated research platform (Recomia.org). Sensitivity and specificity were calculated to assess the performance of the AI model. Cystoscopy findings were used as the reference method. The training cohort comprised a total of 530 patients. Following the optimisation process, we developed the last version of our AI model. Subsequently, we utilised the model in the validation cohort which included an additional 400 patients (including 239 patients with UBC). The AI model had a sensitivity of 0.83 (95% confidence intervals [CI], 0.76-0.89), specificity of 0.76 (95% CI 0.67-0.84), and a negative predictive value (NPV) of 0.97 (95% CI 0.95-0.98). The majority of tumours in the false negative group (n = 24) were solitary (67%) and smaller than 1 cm (50%), with the majority of patients having cTaG1-2 (71%). We developed and tested an AI model for automatic image analysis of CTUs to detect UBC in patients with macroscopic hematuria. This model showed promising results with a high detection rate and excessive NPV. Further developments could lead to a decreased need for invasive investigations and prioritising patients with serious tumours.