Sunitinib for Metastatic Renal Cell Carcinoma: Real-World Data from the STAR-TOR Registry and Detailed Literature Review.

INTRODUCTION: We evaluated the effectiveness and safety profile of the tyrosine kinase inhibitor sunitinib in patients with advanced or metastatic renal cell carcinoma (a/mRCC) in a real-world setting. METHODS: We analyzed data of adult a/mRCC patients treated with sunitinib. Data were derived from the German non-interventional post-approval multicenter STAR-TOR registry (NCT00700258). Progression-free survival (PFS), overall survival (OS), and adverse events (AEs) were evaluated using descriptive statistics and survival analyses for the entire cohort and patient subgroups. RESULTS: A total of 116 study sites recruited 702 patients treated with sunitinib (73.1% male; median age 68.0 years; median Karnofsky index 90%) between November 2010 and May 2020. The most frequent histological subtype was clear cell RCC (81.6%). Sunitinib was administered as first-line treatment in 83.5%, as second line in 11.7%, and as third line or beyond in 4.8% of the patients. Drug-related AEs and serious AEs were reported in 66.3% and 13.9% of the patients, respectively (most common AE: gastrointestinal disorders; 39.7% of all patients). CONCLUSIONS: This study adds further real-world evidence of the persisting relevance of sunitinib for patients with a/mRCC who cannot receive or tolerate immune checkpoint inhibitors. The study population includes a high proportion of patients with unfavorable MSKCC poor-risk score, but shows still good PFS and OS results, while the drug demonstrates a favorable safety profile. The STAR-TOR registry is also registered in the database of US library of medicine (NCT00700258).

Current state and guidance on arterial spin labeling perfusion MRI in clinical neuroimaging.

This article focuses on clinical applications of arterial spin labeling (ASL) and is part of a wider effort from the International Society for Magnetic Resonance in Medicine (ISMRM) Perfusion Study Group to update and expand on the recommendations provided in the 2015 ASL consensus paper. Although the 2015 consensus paper provided general guidelines for clinical applications of ASL MRI, there was a lack of guidance on disease-specific parameters. Since that time, the clinical availability and clinical demand for ASL MRI has increased. This position paper provides guidance on using ASL in specific clinical scenarios, including acute ischemic stroke and steno-occlusive disease, arteriovenous malformations and fistulas, brain tumors, neurodegenerative disease, seizures/epilepsy, and pediatric neuroradiology applications, focusing on disease-specific considerations for sequence optimization and interpretation. We present several neuroradiological applications in which ASL provides unique information essential for making the diagnosis. This guidance is intended for anyone interested in using ASL in a routine clinical setting (i.e., on a single-subject basis rather than in cohort studies) building on the previous ASL consensus review.

X-nuclei imaging: Current state, technical challenges, and future directions.

1 H imaging is concerned with contrast generation among anatomically distinct soft tissues. X-nuclei imaging, on the other hand, aims to reveal the underlying changes in the physiological processes on a cellular level. Advanced clinical MR hardware systems improved 1 H image quality and simultaneously enabled X-nuclei imaging. Adaptation of 1 H methods and optimization of both sequence design and postprocessing protocols launched X-nuclei imaging past feasibility studies and into clinical studies. This review outlines the current state of X-nuclei MRI, with the focus on 23 Na, 35 Cl, 39 K, and 17 O. Currently, various aspects of technical challenges limit the possibilities of clinical X-nuclei MRI applications. To address these challenges, quintessential physical and technical concepts behind different applications are presented, and the advantages and drawbacks are delineated. The working process for methods such as quantification and multiquantum imaging is shown step-by-step. Clinical examples are provided to underline the potential value of X-nuclei imaging in multifaceted areas of application. In conclusion, the scope of the latest technical advance is outlined, and suggestions to overcome the most fundamental hurdles on the way into clinical routine by leveraging the full potential of X-nuclei imaging are presented. Level of Evidence: 1 Technical Efficacy Stage: 3 J. Magn. Reson. Imaging 2020;51:355-376.

Manual vs automated 68 Ga-radiolabelling-A comparison of optimized processes.

A critical factor for clinical practice is the production of 68 Ga radiopharmaceuticals manufactured manually or through an automated procedure. 68 Ga radiopharmaceuticals are often prepared manually, although this method can lead to an increased operator's radiation dose and potential variability within production. The present work compares 68 Ga-radiolabelling (PSMA-11; DOTA-TOC) utilizing a cassette module (GAIA; Elysia-Raytest; Germany) with a manual setup for routine clinical production with regard to process reliability and reproducibility.

Complementing clinical cancer registry data with patient reported outcomes: A feasibility study on routine electronic patient-reported outcome assessment for the Austrian Myelome Registry.

OBJECTIVES: Routinely assessed patient-reported outcomes (PROs), such as quality of life (QOL), are important to supplement clinical cancer data but requires rigorous implementation. This study aims at depicting the implementation procedure and evaluating the feasibility of routine electronic PRO monitoring (ePRO) for collecting data supplementing the Austrian Myeloma Registry (AMR). METHODS: Integration of ePRO monitoring into clinical routine was planned according to the Replicating Effective Programs framework. QOL data were assessed regularly during treatment and aftercare at the hematooncological outpatient unit at the Medical University of Innsbruck with the EORTC QLQ-C30/ +MY20 and the EQ-5D-5L. Feasibility and usability testing were performed via a multimethod approach. RESULTS: Within the first year, 94.4% of the MM patients (N = 142, mean age 65.4, SD 11.8, 60% male) provided 748 PRO assessment time points overall. Patients and clinicians were satisfied with ePRO monitoring and indicated no to little disruption in clinical routine. Patient preference on assessment time points and completion frequency became evident. CONCLUSIONS: Complementing the AMR with ePRO data proved to be feasible. Our findings provide useful insights for healthcare providers considering introducing ePRO monitoring to their units for informing clinical registries as well as individualised feedback to patients alike.

Vascular architecture mapping for early detection of glioblastoma recurrence.

OBJECTIVE: Treatment failure and inevitable tumor recurrence are the main reasons for the poor prognosis of glioblastoma (GB). Gross-total resection at repeat craniotomy for GB recurrence improves patient overall survival but requires early and reliable detection. It is known, however, that even advanced MRI approaches have limited diagnostic performance for distinguishing tumor progression from pseudoprogression. The novel MRI technique of vascular architectural mapping (VAM) provides deeper insight into tumor microvascularity and neovascularization. In this study the authors evaluated the usefulness of VAM for the monitoring of GB patients and quantitatively analyzed the features of neovascularization of early- and progressed-stage GB recurrence. METHODS: In total, a group of 115 GB patients who received overall 374 follow-up MRI examinations after standard treatment were retrospectively evaluated in this study. The clinical routine MRI (cMRI) protocol at 3 Tesla was extended with the authors' experimental VAM approach, requiring 2 minutes of extra time for data acquisition. Custom-made MATLAB software was used for calculation of imaging biomarker maps of macrovascular perfusion from perfusion cMRI as well as of microvascular perfusion and architecture from VAM data. Additionally, cMRI data were analyzed by two board-certified radiologists in consensus. Statistical procedures included receiver operating characteristic (ROC) analysis to determine diagnostic performances for GB recurrence detection. RESULTS: Overall, cMRI showed GB recurrence in 89 patients, and in 28 of these patients recurrence was detected earlier with VAM data, by 1 (20 patients) or 2 (8 patients) follow-up examinations, than with cMRI data. The mean time difference between recurrence detection with VAM and cMRI data was 147 days. During this time period the mean tumor volume increased significantly (p < 0.001) from 9.7 to 26.8 cm3. Quantitative analysis of imaging biomarkers demonstrated microvascular but no macrovascular hyperperfusion in early GB recurrence. Therefore, ROC analysis revealed superior diagnostic performance for VAM compared with cMRI. CONCLUSIONS: This study demonstrated that the targeted assessment of microvascular features using the VAM technique provided valuable information about early neovascularization activity in recurrent GB that is complementary to perfusion cMRI and may be helpful for earlier and more precise monitoring of patients suffering from GB. This VAM approach is compatible with existing cMRI protocols. Prospective clinical trials are necessary to investigate the clinical usefulness and potential benefit of increased overall survival with the use of VAM in patients with recurrent GB.

[Anatomy of the petrous portion of the temporal bone]. / Anatomie des Felsenbeins.

CLINICAL METHOD: The complexity of the anatomy of the petrous portion of the temporal bone with the crossing nerval, vascular, and muscular structures together with the important parts of the human vestibulocochlear organ poses challenges in clinical routine, especially in the preoperative diagnostic workup. In particular, the presence of standard anatomical variations bears a higher risk of intraoperative injuries. STANDARD RADIOLOGICAL METHOD: MRI and CT examinations are important image-based diagnostic methods in the detection of neoplastic, traumatic and inflammatory lesions of the petrous part of the temporal bone. These kinds of methods are absolutely necessary for the identification of the entity of the lesion, the extent of the infiltration, possible bone involvement or the presence of standard anatomical variations.

Additive value of amyloid-PET in routine cases of clinical dementia work-up after FDG-PET.

PURPOSE: In recent years, several [18F]-labeled amyloid-PET tracers have been developed and have obtained clinical approval. Despite their widespread scientific use, studies in routine clinical settings are limited. We therefore investigated the impact of [18F]-florbetaben (FBB)-PET on the diagnostic management of patients with suspected dementia that was still unclarified after [18F]-fluordeoxyglucose (FDG)-PET. METHODS: All subjects were referred in-house with a suspected dementia syndrome due to neurodegenerative disease. After undergoing an FDG-PET exam, the cases were discussed by the interdisciplinary dementia board, where the most likely diagnosis as well as potential differential diagnoses were documented. Because of persistent diagnostic uncertainty, the patients received an additional FBB-PET exam. Results were interpreted visually and classified as amyloid-positive or amyloid-negative, and we then compared the individual clinical diagnoses before and after additional FBB-PET. RESULTS: A total of 107 patients (mean age 69.4 ± 9.7y) were included in the study. The FBB-PET was rated as amyloid-positive in 65/107. In 83% of the formerly unclear cases, a final diagnosis was reached through FBB-PET, and the most likely prior diagnosis was changed in 28% of cases. The highest impact was observed for distinguishing Alzheimer's dementia (AD) from fronto-temporal dementia (FTLD), where FBB-PET altered the most likely diagnosis in 41% of cases. CONCLUSIONS: FBB-PET has a high additive value in establishing a final diagnosis in suspected dementia cases when prior investigations such as FDG-PET are inconclusive. The differentiation between AD and FTLD was particularly facilitated by amyloid-PET, predicting a considerable impact on patient management, especially in the light of upcoming disease-modifying therapies.

Evaluation of Noncompletion Bias and Long-Term Adherence in a 10-Year Patient-Reported Outcome Monitoring Program in Clinical Routine.

BACKGROUND: Currently there is little knowledge on real-life sustainability of routine patient-reported outcome (PRO) measurement and the representativeness of collected data. OBJECTIVES: The investigation of routine PRO with regard to noncompletion bias and long-term adher- ence, considering the potential impact of mode of assessment (MOA) (paper-pencil vs. electronic PRO [ePRO]) and patient characteristics. METHODS: At our department, routine PRO measurement in oncological patients is being done since 2005 using different MOA (paper-pencil assessment until 2011 and ePRO assessment from 2011 onward). We analyzed two different patient groups: patients eligible in both periods (both-MOA group) and patients eligible in only one period (one-MOA group). The primary outcome was PRO noncompletion (100% missing questionnaires). The secondary outcome was poor PRO adherence (>20% missing questionnaires). Multivariate logistic regression models were developed, testing the impact of MOA and patient characteristics on the outcomes in the different patient groups. RESULTS: Data from 1484 eligible patients were included in the analyses. Most of the patients could be included in PRO assessment at least once. PRO noncompletion rates were clearly higher during paper-pencil assessment (odds ratios between 2.72 and 4.31), as were poor PRO adherence rates (odd ratio 2.23). Analyses of potential bias by patient characteristics showed that male patients had a higher risk of poor adherence. Other factors with significant impact were age, country, and cancer diagnosis, but results were indecisive. CONCLUSIONS: ePRO increased the feasibility of our clinical routine PRO data for retrospective analyses by increasing completion rates. In general, potential completion bias regarding certain patient characteristics requires attention before generalizing results to the respective populations.

Study design of PANGAEA 2.0, a non-interventional study on RRMS patients to be switched to fingolimod.

BACKGROUND: The therapeutic options for patients with Multiple Sclerosis (MS) have steadily increased due to the approval of new substances that now supplement traditional first-line agents, demanding a paradigm shift in the assessment of disease activity and treatment response in clinical routine. Here, we report the study design of PANGAEA 2.0 (Post-Authorization Non-interventional GermAn treatment benefit study of GilEnyA in MS patients), a non-interventional study in patients with relapsing-remitting MS (RRMS) identify patients with disease activity and monitor their disease course after treatment switch to fingolimod (Gilenya®), an oral medication approved for patients with highly active RRMS. METHOD/DESIGN: In the first phase of the PANGAEA 2.0 study the disease activity status of patients receiving a disease-modifying therapy (DMT) is evaluated in order to identify patients at risk of disease progression. This evaluation is based on outcome parameters for both clinical disease activity and magnetic resonance imaging (MRI), and subclinical measures, describing disease activity from the physician's and the patient's perspective. In the second phase of the study, 1500 RRMS patients identified as being non-responders and switched to fingolimod (oral, 0.5 mg/daily) are followed-up for 3 years. Data on relapse activity, disability progression, MRI lesions, and brain volume loss will be assessed in accordance to 'no evidence of disease activity-4' (NEDA-4). The modified Rio score, currently validated for the evaluation of treatment response to interferons, will be used to evaluate the treatment response to fingolimod. The MS management software MSDS3D will guide physicians through the complex processes of diagnosis and treatment. A sub-study further analyzes the benefits of a standardized quantitative evaluation of routine MRI scans by a central reading facility. PANGAEA 2.0 is being conducted between June 2015 and December 2019 in 350 neurological practices and centers in Germany, including 100 centers participating in the sub-study. DISCUSSION: PANGAEA 2.0 will not only evaluate the long-term benefit of a treatment change to fingolimod but also the applicability of new concepts of data acquisition, assessment of MS disease activity and evaluation of treatment response for the in clinical routine. TRIAL REGISTRATION: BfArM6532; Trial Registration Date: 20/05/2015.

[Current aspects of therapy conversion for multiple sclerosis]. / Aktuelles zur Therapieumstellung bei Multipler Sklerose.

In recent years the approval of new substances has led to a substantial increase in the number of course-modifying immunotherapies available for multiple sclerosis. Therapy conversion therefore represents an increasing challenge. The treatment options sometimes show complex adverse effect profiles and necessitate a long-term and comprehensive monitoring. This article presents an overview of therapy conversion of immunotherapies for multiple sclerosis in accordance with the recommendations of the Disease-Related Competence Network for Multiple Sclerosis and the German Multiple Sclerosis Society as well as the guidelines on diagnostics and therapy for multiple sclerosis of the German Society of Neurology and the latest research results. At the present point in time it should be noted that no studies have been carried out for most of the approaches for therapy conversion given here; however, the recommendations are based on theoretical considerations and therefore correspond to recommendations at the level of expert consensus, which is currently essential for the clinical daily routine.

Beating the Clock: A Prediction Model for Timely Care in Emergency Departments.

We developed and validated a statistical prediction model using 2.5 electronic health records from 24 German emergency departments (EDs) to estimate treatment timeliness at triage. The model's moderate fit and reliance on interoperable, routine data suggest its potential for implementation in ED crowding management.

Harmonizing tumor mutational burden analysis: Insights from a multicenter study using in silico reference data sets in clinical whole-exome sequencing (WES).

OBJECTIVES: Tumor mutational burden (TMB) is a significant biomarker for predicting immune checkpoint inhibitor response, but the clinical performance of whole-exome sequencing (WES)-based TMB estimation has received less attention compared to panel-based methods. This study aimed to assess the reliability and comparability of WES-based TMB analysis among laboratories under routine testing conditions. METHODS: A multicenter study was conducted involving 24 laboratories in China using in silico reference data sets. The accuracy and comparability of TMB estimation were evaluated using matched tumor-normal data sets. Factors such as accuracy of variant calls, limit of detection (LOD) of WES test, size of regions of interest (ROIs) used for TMB calculation, and TMB cutoff points were analyzed. RESULTS: The laboratories consistently underestimated the expected TMB scores in matched tumor-normal samples, with only 50% falling within the ±30% TMB interval. Samples with low TMB score (<2.5) received the consensus interpretation. Accuracy of variant calls, LOD of the WES test, ROI, and TMB cutoff points were important factors causing interlaboratory deviations. CONCLUSIONS: This study highlights real-world challenges in WES-based TMB analysis that need to be improved and optimized. This research will aid in the selection of more reasonable analytical procedures to minimize potential methodologic biases in estimating TMB in clinical exome sequencing tests. Harmonizing TMB estimation in clinical testing conditions is crucial for accurately evaluating patients' response to immunotherapy.

Quality Assessment Framework of Clinical Routine Data for Secondary Use.

To systematically and comprehensively identify data issues in large clinical datasets, we adopted a harmonized data quality assessment framework with Python scripts before integrating the data into FHIR® for secondary use. We also added a preliminary step of categorizing data fields within the database scheme to facilitate the implementation of the data quality framework. As a result, we demonstrated the efficiency and comprehensiveness of detecting data issues using the framework. In future steps, we plan to continually utilize the framework to identify data issues and develop strategies for improving our data quality.

Population-Based Biobanking.

Population-based biobanking is an essential element of medical research that has grown substantially over the last two decades, and many countries are currently pursuing large national biobanking initiatives. The rise of individual biobanks is paralleled by various networking activities in the field at both the national and international level, such as BBMRI-ERIC in the EU. A significant contribution to population-based biobanking comes from large cohort studies and national repositories, including the United Kingdom Biobank (UKBB), the CONSTANCES project in France, the German National Cohort (NAKO), LifeLines in the Netherlands, FinnGen in Finland, and the All of Us project in the U.S. At the same time, hospital-based biobanking has also gained importance in medical research. We describe some of the scientific questions that can be addressed particularly well by the use of population-based biobanks, including the discovery and calibration of biomarkers and the identification of molecular correlates of health parameters and disease states. Despite the tremendous progress made so far, some major challenges to population-based biobanking still remain, including the need to develop strategies for the long-term sustainability of biobanks, the handling of incidental findings, and the linkage of sample-related and sample-derived data to other relevant resources.

Body Composition Analysis of the Clinical Routine Using Air Displacement Plethysmography: Age-Group-Specific Feasibility Analysis among Preterm Infants.

Body composition assessments using air displacement plethysmography (ADP, PEAPOD®) have been introduced into clinical practice at a few neonatal units. To allow accurate body composition assessments in term and preterm infants, a workflow for routine testing is needed. The aim of this study was to analyze the feasibility of weekly routine ADP testing. We analyzed (1) postnatal ages at first ADP assessment, (2) the number of weekly routine in-hospital assessments, and (3) the workload of body composition measurements using ADP in clinical practice on the basis of an retrospective analysis of our own clinical operating procedures. The retrospective analysis of weekly routine ADP testing proved feasible at Nuremberg Children's Hospital. The analysis of postnatal age at the first ADP test revealed differences across groups, with extremely preterm infants starting at a mean postmenstrual age of 36.6 weeks, very preterm infants starting at 34.2 weeks, and moderate to late preterm infants starting at 35.3 weeks. The mean number of tests before discharge was significantly greater in the extremely preterm group (n = 3.0) than in the very preterm (n = 2.4) and moderate to late preterm groups (n = 1.7). The workload of the procedure is reasonable, at 8-13 min per test cycle. The study proved that weekly routine ADP assessments in preterm infants are feasible. However, the initiation of routine testing in extremely preterm infants starts at a significantly greater postnatal age than in the more mature population. ADP assessments can be safely and easily integrated into clinical practice and may be valuable tools for providing additional information on nutritional status and infant growth. A standardized routine protocol allowing identical measurement conditions across healthcare institutions and a standardized interpretation tool for age-adapted body composition data, however, would improve comparability and usability.

A scalable approach for critical care data extraction and analysis in an academic medical center.

BACKGROUND: Electronic health records are a valuable asset for research, but their use is challenging due to inconsistencies of records, heterogeneous formats and the distribution over multiple, non-integrated information systems. Hence, specialized health data engineering and data science expertise are required to enable research. To facilitate secondary use of clinical routine data collected in our intensive care wards, we developed a scalable approach, consisting of cohort generation, variable filtering and data extraction steps. OBJECTIVE: With this report we share our workflow of data request, cohort identification and data extraction. We present an algorithm for automatic data extraction from our critical care information system (CCIS) that can be adapted to other object-oriented data bases. METHODS: We introduced a data request process with functionalities for automated identification of patient cohorts and a specialized hierarchical data structure that supports filtering relevant variables from the CCIS and further systems for the specified cohorts. The data extraction algorithm takes patient pseudonyms and variable lists as inputs. Algorithms are implemented in Python, leveraging the PySpark framework running on our data lake infrastructure. RESULTS: Our data request process is in operational use since June 2022. Since then we have served 121 projects with 148 service requests in total. We discuss the hierarchical structure and the frequently used data items of our CCIS in detail and present an application example, including cohort selection, data extraction and data transformation into an analyses-ready format. CONCLUSIONS: Using clinical routine data for secondary research is challenging and requires an interdisciplinary team. We developed a scalable approach that automates steps for cohort identification, data extraction and common data pre-processing steps. Additionally, we facilitate data harmonization, integration and consult on typical data analysis scenarios, machine learning algorithms and visualizations in dashboards.

Brain atrophy assessment in multiple sclerosis: technical- and subject-related barriers for translation to real-world application in individual subjects.

INTRODUCTION: Brain atrophy is a well-established MRI outcome for predicting clinical progression and monitoring treatment response in persons with multiple sclerosis (pwMS) at the group level. Despite the important progress made, the translation of brain atrophy assessment into clinical practice faces several challenges. AREAS COVERED: In this review, the authors discuss technical- and subject-related barriers for implementing brain atrophy assessment as part of the clinical routine at the individual level. Substantial progress has been made to understand and mitigate technical barriers behind MRI acquisition. Numerous research and commercial segmentation techniques for volume estimation are available and technically validated, but their clinical value has not been fully established. A systematic assessment of subject-related barriers, which include genetic, environmental, biological, lifestyle, comorbidity, and aging confounders, is critical for the interpretation of brain atrophy measures at the individual subject level. Educating both medical providers and pwMS will help better clarify the benefits and limitations of assessing brain atrophy for disease monitoring and prognosis. EXPERT OPINION: Integrating brain atrophy assessment into clinical practice for pwMS requires overcoming technical and subject-related challenges. Advances in MRI standardization, artificial intelligence, and clinician education will facilitate this process, improving disease management and potentially reducing long-term healthcare costs.

Implementing a Biomedical Data Warehouse From Blueprint to Bedside in a Regional French University Hospital Setting: Unveiling Processes, Overcoming Challenges, and Extracting Clinical Insight.

Background: Biomedical data warehouses (BDWs) have become an essential tool to facilitate the reuse of health data for both research and decisional applications. Beyond technical issues, the implementation of BDWs requires strong institutional data governance and operational knowledge of the European and national legal framework for the management of research data access and use. Objective: In this paper, we describe the compound process of implementation and the contents of a regional university hospital BDW. Methods: We present the actions and challenges regarding organizational changes, technical architecture, and shared governance that took place to develop the Nantes BDW. We describe the process to access clinical contents, give details about patient data protection, and use examples to illustrate merging clinical insights. Unlabelled: More than 68 million textual documents and 543 million pieces of coded information concerning approximately 1.5 million patients admitted to CHUN between 2002 and 2022 can be queried and transformed to be made available to investigators. Since its creation in 2018, 269 projects have benefited from the Nantes BDW. Access to data is organized according to data use and regulatory requirements. Conclusions: Data use is entirely determined by the scientific question posed. It is the vector of legitimacy of data access for secondary use. Enabling access to a BDW is a game changer for research and all operational situations in need of data. Finally, data governance must prevail over technical issues in institution data strategy vis-à-vis care professionals and patients alike.

Deep Hybrid Learning Prediction of Patient-Specific Quality Assurance in Radiotherapy: Implementation in Clinical Routine.

BACKGROUND: Arc therapy allows for better dose deposition conformation, but the radiotherapy plans (RT plans) are more complex, requiring patient-specific pre-treatment quality assurance (QA). In turn, pre-treatment QA adds to the workload. The objective of this study was to develop a predictive model of Delta4-QA results based on RT-plan complexity indices to reduce QA workload. METHODS: Six complexity indices were extracted from 1632 RT VMAT plans. A machine learning (ML) model was developed for classification purpose (two classes: compliance with the QA plan or not). For more complex locations (breast, pelvis and head and neck), innovative deep hybrid learning (DHL) was trained to achieve better performance. RESULTS: For not complex RT plans (with brain and thorax tumor locations), the ML model achieved 100% specificity and 98.9% sensitivity. However, for more complex RT plans, specificity falls to 87%. For these complex RT plans, an innovative QA classification method using DHL was developed and achieved a sensitivity of 100% and a specificity of 97.72%. CONCLUSIONS: The ML and DHL models predicted QA results with a high degree of accuracy. Our predictive QA online platform is offering substantial time savings in terms of accelerator occupancy and working time.