[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100661320":3},{"organization":4,"outcomesModule":7,"designInfo":82,"detailedDescription":85,"studyPopulation":86,"armGroups":87,"interventions":98,"overallOfficials":107,"centralContacts":118,"locations":126,"responsibleParty":247,"collaborators":249,"id":265,"slug":266,"hasResults":267,"nctId":268,"briefTitle":269,"officialTitle":269,"acronym":270,"eligibilityCriteria":271,"healthyVolunteers":272,"sex":273,"minAge":81,"maxAge":81,"enrollmentInfo":274,"targetDuration":81,"studyType":277,"phases":81,"briefSummary":278,"conditions":279,"keywords":282,"overallStatus":288,"whyStopped":81,"lastUpdateSubmitDate":289,"lastUpdatePostDateStruct":290,"startDateStruct":293,"completionDateStruct":295,"leadSponsor":297,"locationsCount":298},{"fullName":5,"class":6},"Aristotle University Of Thessaloniki","OTHER",{"primaryOutcomes":8,"secondaryOutcomes":49,"otherOutcomes":81},[9,13,16,19,22,25,28,31,34,37,40,43,46],{"measure":10,"description":11,"timeFrame":12},"Accuracy of the multimodal AI algorithms","Accuracy of the multimodal AI algorithms will be assessed by comparing model predictions with the clinician-reported reference standard for each suspected lesion. Accuracy will be calculated for each applicable cancer type, with bootstrap confidence intervals.","Through study completion, an average of 6 months.",{"measure":14,"description":15,"timeFrame":12},"Precision of the multimodal AI algorithms","Precision of the multimodal AI algorithms will be assessed by comparing model predictions with the clinician-reported reference standard for each suspected lesion. Precision will be calculated for each applicable cancer type, with bootstrap confidence intervals.",{"measure":17,"description":18,"timeFrame":12},"F1-score of the multimodal AI algorithms","F1-score will be calculated to assess the classification performance of the multimodal AI algorithms against the clinician-reported reference standard for each suspected lesion. F1-score will be calculated for each applicable cancer type, with bootstrap confidence intervals.",{"measure":20,"description":21,"timeFrame":12},"Sensitivity of the multimodal AI algorithms","Sensitivity (recall) will be calculated to assess the ability of the multimodal AI algorithms to correctly identify positive cases relative to the clinician-reported reference standard. Sensitivity will be calculated for each applicable cancer type, with bootstrap confidence intervals.",{"measure":23,"description":24,"timeFrame":12},"Specificity of the multimodal AI algorithms","Specificity will be calculated to assess the ability of the multimodal AI algorithms to correctly identify negative cases relative to the clinician-reported reference standard. Specificity will be calculated for each applicable cancer type, with bootstrap confidence intervals.",{"measure":26,"description":27,"timeFrame":12},"Area under the receiver operating characteristic curve (AUC-ROC)","AUC-ROC will be calculated to characterize the classification performance of the multimodal AI algorithms relative to the clinician-reported reference standard for each applicable cancer type, with bootstrap confidence intervals.",{"measure":29,"description":30,"timeFrame":12},"Intersection over Union (IoU)","Intersection over Union (IoU) will be calculated for applicable object detection and segmentation tasks to assess agreement between AI-generated regions and the corresponding reference standard.",{"measure":32,"description":33,"timeFrame":12},"Agreement between AI-generated stratification and the clinical reference standard","Agreement between model-generated lesion stratification and the clinician-reported reference standard will be evaluated using a confusion matrix and quantified using weighted kappa.",{"measure":35,"description":36,"timeFrame":12},"Agreement between AI-generated PI-RADS score and the clinical reference standard","Agreement between the model-generated PI-RADS score and the clinician-reported reference standard will be evaluated using a confusion matrix and quantified using weighted kappa.",{"measure":38,"description":39,"timeFrame":12},"Agreement between AI-generated Bosniak score and the clinical reference standard","Agreement between the model-generated Bosniak score and the clinician-reported reference standard will be evaluated using a confusion matrix and quantified using weighted kappa.",{"measure":41,"description":42,"timeFrame":12},"Agreement between AI-generated RENAL score and the clinical reference standard","Agreement between the model-generated RENAL score and the clinician-reported reference standard will be evaluated using a confusion matrix and quantified using weighted kappa.",{"measure":44,"description":45,"timeFrame":12},"Group-stratified performance of the multimodal AI algorithms","Performance metrics of the multimodal AI algorithms will be calculated separately for prespecified participant groups to assess differences in model performance across groups. Group-stratified metrics will be reported with bootstrap confidence intervals.",{"measure":47,"description":48,"timeFrame":12},"Group-stratified calibration of the multimodal AI algorithms","Calibration metrics of the multimodal AI algorithms will be calculated separately for prespecified participant groups to assess model calibration across groups. Group-stratified calibration metrics will be reported with bootstrap confidence intervals.",[50,53,56,59,62,65,68,72,75,78],{"measure":51,"description":52,"timeFrame":12},"Acceptability of the COMFORT platform","Clinician acceptability of the COMFORT platform will be assessed using the Technology Acceptance Model (TAM), applicable study questionnaires, and structured interviews. Questionnaire scores will be summarized using the median and interquartile range (IQR) for each study site and across the study. Comparisons between study sites will be performed using non-parametric hypothesis testing.",{"measure":54,"description":55,"timeFrame":12},"Usability of the COMFORT platform","Clinician-reported usability of the COMFORT platform will be assessed using the System Usability Scale (SUS). The SUS provides a total score ranging from 0 to 100, with higher scores indicating greater perceived usability. Scores will be summarized using the median and interquartile range (IQR) for each study site and across the study. Comparisons between study sites will be performed using non-parametric hypothesis testing.",{"measure":57,"description":58,"timeFrame":12},"Perceived trustworthiness of COMFORT AI outputs","Clinicians' perceived trustworthiness of AI-generated outputs will be assessed using the Trustworthiness of AI Output questionnaire and structured interviews. Questionnaire scores will be summarized using the median and interquartile range (IQR) for each study site and across the study.",{"measure":60,"description":61,"timeFrame":12},"Perceived information integration","Clinicians' perceptions of the integration of information provided by the COMFORT platform will be assessed using the Perceived Information Integration questionnaire and structured interviews. Questionnaire scores will be summarized using the median and interquartile range (IQR) for each study site and across the study.",{"measure":63,"description":64,"timeFrame":12},"Perceived effectiveness of the COMFORT platform","Clinicians' perceived effectiveness of the COMFORT platform will be assessed using the Effectiveness of COMFORT Platform questionnaire and structured interviews. Questionnaire scores will be summarized using the median and interquartile range (IQR) for each study site and across the study.",{"measure":66,"description":67,"timeFrame":12},"Care management efficiency","Clinician-reported care management efficiency associated with use of the COMFORT platform will be assessed using the Care Management Efficiency questionnaire and structured interviews. Questionnaire scores will be summarized using the median and interquartile range (IQR) for each study site and across the study. Comparisons between study sites will be performed using non-parametric hypothesis testing.",{"measure":69,"description":70,"timeFrame":71},"AI literacy","Clinician AI literacy will be assessed using the study-specified AI Literacy questionnaire and structured interviews. Questionnaire scores will be summarized using the median and interquartile range (IQR) for each study site and across the study.","Baseline",{"measure":73,"description":74,"timeFrame":12},"Clinical reading time: AI-assisted versus manual reading","The effectiveness of the COMFORT platform in assisting clinicians will be assessed by comparing the time required to complete AI-assisted clinical reading with the time required for manual clinical reading. Reading time will be summarized using the mean and standard deviation for each study site and across the study. Comparisons between study sites will be performed using parametric testing.",{"measure":76,"description":77,"timeFrame":12},"Clinical reading quality: AI-assisted versus manual reading","The effectiveness of the COMFORT platform in assisting clinicians will be assessed by comparing the quality of AI-assisted clinical reading with that of manual clinical reading. Reading quality will be summarized for each study site and across the study and compared using a test of proportions.",{"measure":79,"description":80,"timeFrame":12},"Average Treatment Effect of potential privacy leakage causes","Potential causes of privacy leakage from COMFORT AI models will be evaluated using a privacy causal analysis model. The model will generate a causal graph and an Average Treatment Effect (ATE) value for each potential privacy leakage cause associated with COMFORT AI model outputs, such as Bosniak Classification.",null,{"allocation":81,"interventionModel":81,"interventionModelDescription":81,"primaryPurpose":81,"observationalModel":83,"timePerspective":84,"maskingInfo":81},"COHORT","PROSPECTIVE","The COMFORT study aims to evaluate an AI-based platform developed to support the clinical assessment of patients with kidney and prostate cancer. The COMFORT platform provides AI-generated outputs intended to assist clinicians in the assessment and characterization of suspected lesions. The study evaluates not only the technical performance of the AI algorithms but also their integration into clinical practice, their fairness across different groups, and potential privacy risks.\n\nThe pipelines developed for kidney and prostate cancer provide outputs relevant to the respective diagnostic pathways. Depending on the clinical application, these outputs include lesion stratification and assessments such as PI-RADS, Bosniak, and RENAL scores. The performance of the AI algorithms will be evaluated by comparing model-generated predictions with the corresponding clinical reference standards. The evaluation will include measures of classification performance and agreement between AI-generated assessments and the reference standard. Performance will also be evaluated separately for the relevant cancer types.\n\nAn additional component of the study concerns the fairness of the COMFORT AI models. Model performance will be examined across different participant groups to identify potential differences in the behavior of the algorithms between groups. This analysis will complement the overall evaluation of model performance and contribute to the assessment of the reliability of the platform across the study population.\n\nThe study will also evaluate the integration of the COMFORT platform into clinical practice from the perspective of participating clinicians. Questionnaires and structured interviews will be used to assess clinicians' perceptions and experiences with the platform. Areas of evaluation include acceptability, usability, trustworthiness of AI-generated outputs, perceived information integration, workload management, perceived effectiveness, care management efficiency, and AI literacy. These assessments will provide information on how clinicians interact with the platform and perceive its potential contribution to clinical practice.\n\nIn addition to these subjective assessments, the effectiveness of the COMFORT platform in assisting clinicians during clinical reading will be evaluated objectively. AI-assisted clinical reading will be compared with manual clinical reading in terms of the time required to complete the reading and the quality of the resulting clinical assessment. These evaluations will be considered at individual study sites as well as across the study to examine the implementation of the platform in different clinical settings.\n\nPotential privacy risks associated with the COMFORT AI models will also be investigated. A privacy causal analysis approach will be used to examine potential causes of privacy leakage associated with AI model outputs and to characterize their potential causal effects.\n\nOverall, the study is designed to provide a comprehensive evaluation of the COMFORT platform across several complementary dimensions, including AI model performance, fairness, clinical usability and acceptability, effects on clinical reading, and potential privacy risks. This combined evaluation is intended to provide evidence regarding the performance of the platform and its use in the clinical assessment of kidney and prostate cancer.","Healthcare professionals participating in the study who use the COMFORT platform during the study period. Participants will use the platform as specified in the study protocol and data related to platform assessment and study outcomes will be collected",[88,94],{"label":89,"type":81,"description":90,"interventionNames":91},"Urologists","Group of residents and specialists in urology",[92,93],"Other: Medical Reading","Other: AI assisted Medical reading",{"label":95,"type":81,"description":96,"interventionNames":97},"Radiologists","Group of residents and specialists in radiology",[92,93],[99,103],{"type":6,"name":100,"description":101,"armGroupLabels":102,"otherNames":81},"Medical Reading","Participants will perform medical reading of abdominal CT for renal cancer and prostate mpMRI for prostate cancer, without access to AI output using the COMFORT platform.",[95,89],{"type":6,"name":104,"description":105,"armGroupLabels":106,"otherNames":81},"AI assisted Medical reading","Participants will perform medical reading of abdominal CT for renal cancer and prostate mpMRI for prostate cancer, with access to AI output using the COMFORT platform.",[95,89],[108,112,115],{"name":109,"affiliation":110,"role":111},"Keno Bressem, MD","Technical University of Munich","PRINCIPAL_INVESTIGATOR",{"name":113,"affiliation":5,"role":114},"Antonis Billis, PhD","STUDY_DIRECTOR",{"name":116,"affiliation":117,"role":114},"Alessa Hering, PhD","Radboud Universiteit",[119,123],{"name":109,"role":120,"phone":121,"phoneExt":81,"email":122},"CONTACT","+498941402621","keno.bressem@tum.de",{"name":113,"role":120,"phone":124,"phoneExt":81,"email":125},"+302310999237","ampillis@auth.gr",[127,149,167,190,206,228],{"facility":128,"status":81,"city":129,"state":130,"zip":131,"country":132,"countryCode":133,"cosmosGeoPoint":134,"geoPoint":139,"contacts":140},"Klinikum rechts der Isar, TUM","München","Bavaria","81675","Germany","DE",{"type":135,"coordinates":136},"Point",[137,138],13.46314,48.69668,{"lat":138,"lon":137},[141,145,146],{"name":142,"role":120,"phone":143,"phoneExt":81,"email":144},"Lisa C Adams, Prof.","+49 89 4140-1084","lisa.adams@tum.de",{"name":142,"role":111,"phone":81,"phoneExt":81,"email":81},{"name":147,"role":148,"phone":81,"phoneExt":81,"email":81},"Keno K Bressem, Prof.","SUB_INVESTIGATOR",{"facility":150,"status":81,"city":151,"state":152,"zip":153,"country":132,"countryCode":133,"cosmosGeoPoint":154,"geoPoint":158,"contacts":159},"Department of Neuroradiology, Charite","Berlin","State of Berlin","13353",{"type":135,"coordinates":155},[156,157],13.41053,52.52437,{"lat":157,"lon":156},[160,164,165],{"name":161,"role":120,"phone":162,"phoneExt":81,"email":163},"Jawed Nawabi, MD, MHBA, MSc","+49 30 450 557 192","jawed.nawabi@charite.de",{"name":161,"role":111,"phone":81,"phoneExt":81,"email":81},{"name":166,"role":148,"phone":81,"phoneExt":81,"email":81},"Hartmut Häntze, MSc",{"facility":168,"status":81,"city":169,"state":170,"zip":171,"country":172,"countryCode":173,"cosmosGeoPoint":174,"geoPoint":178,"contacts":179},"Department of Urology, University Hospital of Patras","Pátrai","Achaia","26504","Greece","GR",{"type":135,"coordinates":175},[176,177],21.73508,38.2462,{"lat":177,"lon":176},[180,184,187,189],{"name":181,"role":120,"phone":182,"phoneExt":81,"email":183},"Evangelos Liatsikos, MD","+302613603386","liatsikos@yahoo.com",{"name":185,"role":120,"phone":81,"phoneExt":81,"email":186},"Vasilis Tatanis, MD","tatanisbas@gmail.com",{"name":188,"role":111,"phone":81,"phoneExt":81,"email":81},"Evaggelos Liatsikos, MD",{"name":185,"role":148,"phone":81,"phoneExt":81,"email":81},{"facility":191,"status":81,"city":192,"state":193,"zip":81,"country":172,"countryCode":173,"cosmosGeoPoint":194,"geoPoint":198,"contacts":199},"Laboratory of Medical Physics and Digital Innovation, School of Medicine","Thessaloniki","Central Macedonia",{"type":135,"coordinates":195},[196,197],22.93493,40.64072,{"lat":197,"lon":196},[200,201,204,205],{"name":113,"role":120,"phone":124,"phoneExt":81,"email":125},{"name":202,"role":120,"phone":124,"phoneExt":81,"email":203},"Panagiotis-Emmanouil Kartsidis, MSc","pkartsidis@auth.gr",{"name":113,"role":111,"phone":81,"phoneExt":81,"email":81},{"name":202,"role":148,"phone":81,"phoneExt":81,"email":81},{"facility":207,"status":81,"city":208,"state":209,"zip":210,"country":211,"countryCode":212,"cosmosGeoPoint":213,"geoPoint":217,"contacts":218},"Department of Advanced Biomedical Sciences","Naples","Campania","80131","Italy","IT",{"type":135,"coordinates":214},[215,216],14.26811,40.85216,{"lat":216,"lon":215},[219,223,225,226],{"name":220,"role":120,"phone":221,"phoneExt":81,"email":222},"Arnaldo Stanzione, MD, PhD","+393426927819","arnaldo.stanzione@unina.it",{"name":224,"role":120,"phone":81,"phoneExt":81,"email":81},"Alberto Cuocolo, MD, PhD",{"name":224,"role":111,"phone":81,"phoneExt":81,"email":81},{"name":227,"role":148,"phone":81,"phoneExt":81,"email":81},"Arlando Stanzione, Md, PhD",{"facility":229,"status":81,"city":230,"state":230,"zip":231,"country":232,"countryCode":233,"cosmosGeoPoint":234,"geoPoint":238,"contacts":239},"Hospital Universitario 12 de Octubre","Madrid","28041","Spain","ES",{"type":135,"coordinates":235},[236,237],-3.70256,40.4165,{"lat":237,"lon":236},[240,244,245],{"name":241,"role":120,"phone":242,"phoneExt":81,"email":243},"Guillermo de Velasco, MD, PhD","+34 91 390 87 83 - 83 49","unidadc@h12o.es",{"name":241,"role":111,"phone":81,"phoneExt":81,"email":81},{"name":246,"role":148,"phone":81,"phoneExt":81,"email":81},"Jorge Esteban-Villarrubia, MD",{"type":248,"investigatorFullName":81,"investigatorTitle":81,"investigatorAffiliation":81,"oldNameTitle":81,"oldOrganization":81},"SPONSOR",[250,252,253,255,257,260,262,263],{"name":251,"class":6},"Charite University, Berlin, Germany",{"name":110,"class":6},{"name":254,"class":6},"University of Patras",{"name":256,"class":6},"Radboud University Medical Center",{"name":258,"class":259},"Fraunhofer Institute for Digital Medicine MEVIS","UNKNOWN",{"name":261,"class":6},"University of Salerno",{"name":229,"class":6},{"name":264,"class":6},"Federico II University","100661320","assessment-of-intelligent-algorithms-for-detection-diagnosis-and-risk-stratification-of-tumors-of-the-kidney-and-prostate-100661320",false,"NCT07888322","Assessment of Intelligent Algorithms for Detection, Diagnosis and Risk Stratification of Tumors of the Kidney and Prostate","COMFORT","Inclusion Criteria:\n\n* Healthcare professional resident or specialised in Urology\n* Healthcare professional resident or specialised in Radiology\n* Proficient in English\n\nExclusion Criteria:\n\n\\-",true,"ALL",{"count":275,"type":276},50,"ESTIMATED","OBSERVATIONAL","The COMFORT study will evaluate an artificial intelligence-based platform developed to support the clinical assessment of kidney and prostate cancer. The platform utilises imaging data to provide AI-generated outputs intended to assist clinicians in the assessment of suspected lesions.\n\nThe primary objective of the study is to assess the role of the COMFORT platform in the clinical decision making process of clinicians managing kidney or prostate cancer cases.\n\nSecondary objectives include evaluation of the performance of AI models on anatomical segmentations, tumor characterisation (localisation, volumetric measurements, lesion classification, and scoring (e.g., Bosniak, PI-RADS, RENAL). Also the acceptability, usability, utility and trustworthiness of the AI models will be evaluated.\n\nIn addition, potential causes of privacy leakage associated with the COMFORT AI models will be evaluated as part of the platform's privacy assessment.",[280,281],"Kidney Cancers","Prostate Cancer",[283,284,285,286,287],"Artificial Intelligence","Decision support","Reader study","Kidney cancer","Prostate cancer","NOT_YET_RECRUITING","2026-10-30",{"date":291,"type":292},"2026-11-02","ACTUAL",{"date":294,"type":276},"2026-10-15",{"date":296,"type":276},"2027-02-28",{"name":5,"class":6},6]