An Overview of Real-World Data Infrastructure for Cancer Research.

AIMS: There is increasing interest in the opportunities offered by Real World Data (RWD) to provide evidence where clinical trial data does not exist, but access to appropriate data sources is frequently cited as a barrier to RWD research. This paper discusses current RWD resources and how they can be accessed for cancer research. MATERIALS AND METHODS: There has been significant progress on facilitating RWD access in the last few years across a range of scales, from local hospital research databases, through regional care records and national repositories, to the impact of federated learning approaches on internationally collaborative studies. We use a series of case studies, principally from the UK, to illustrate how RWD can be accessed for research and healthcare improvement at each of these scales. RESULTS: For each example we discuss infrastructure and governance requirements with the aim of encouraging further work in this space that will help to fill evidence gaps in oncology. CONCLUSION: There are challenges, but real-world data research across a range of scales is already a reality. Taking advantage of the current generation of data sources requires researchers to carefully define their research question and the scale at which it would be best addressed.

An adversarial learning approach to generate pressure support ventilation waveforms for asynchrony detection.

BACKGROUND AND OBJECTIVE: Mechanical ventilation is a life-saving treatment for critically-ill patients. During treatment, patient-ventilator asynchrony (PVA) can occur, which can lead to pulmonary damage, complications, and higher mortality. While traditional detection methods for PVAs rely on visual inspection by clinicians, in recent years, machine learning models are being developed to detect PVAs automatically. However, training these models requires large labeled datasets, which are difficult to obtain, as labeling is a labour-intensive and time-consuming task, requiring clinical expertise. Simulating the lung-ventilator interactions has been proposed to obtain large labeled datasets to train machine learning classifiers. However, the obtained data lacks the influence of different hardware, of servo-controlled algorithms, and different sources of noise. Here, we propose VentGAN, an adversarial learning approach to improve simulated data by learning the ventilator fingerprints from unlabeled clinical data. METHODS: In VentGAN, the loss functions are designed to add characteristics of clinical waveforms to the generated results, while preserving the labels of the simulated waveforms. To validate VentGAN, we compare the performance for detection and classification of PVAs when training a previously developed machine learning algorithm with the original simulated data and with the data generated by VentGAN. Testing is performed on independent clinical data labeled by experts. The McNemar test is applied to evaluate statistical differences in the obtained classification accuracy. RESULTS: VentGAN significantly improves the classification accuracy for late cycling, early cycling and normal breaths (p< 0.01); no significant difference in accuracy was observed for delayed inspirations (p = 0.2), while the accuracy decreased for ineffective efforts (p< 0.01). CONCLUSIONS: Generation of realistic synthetic data with labels by the proposed framework is feasible and represents a promising avenue for improving training of machine learning models.

Federated Learning Survival Model and Potential Radiotherapy Decision Support Impact Assessment for Non-small Cell Lung Cancer Using Real-World Data.

AIMS: The objective of this study was to develop a two-year overall survival model for inoperable stage I-III non-small cell lung cancer (NSCLC) patients using routine radiation oncology data over a federated (distributed) learning network and evaluate the potential of decision support for curative versus palliative radiotherapy. METHODS: A federated infrastructure of data extraction, de-identification, standardisation, image analysis, and modelling was installed for seven clinics to obtain clinical and imaging features and survival information for patients treated in 2011-2019. A logistic regression model was trained for the 2011-2016 curative patient cohort and validated for the 2017-2019 cohort. Features were selected with univariate and model-based analysis and optimised using bootstrapping. System performance was assessed by the receiver operating characteristic (ROC) and corresponding area under curve (AUC), C-index, calibration metrics and Kaplan-Meier survival curves, with risk groups defined by model probability quartiles. Decision support was evaluated using a case-control analysis using propensity matching between treatment groups. RESULTS: 1655 patient datasets were included. The overall model AUC was 0.68. Fifty-eight percent of patients treated with palliative radiotherapy had a low-to-moderate risk prediction according to the model, with survival times not significantly different (p = 0.87 and 0.061) from patients treated with curative radiotherapy classified as high-risk by the model. When survival was simulated by risk group and model-indicated treatment, there was an estimated 11% increase in survival rate at two years (p < 0.01). CONCLUSION: Federated learning over multiple institution data can be used to develop and validate decision support systems for lung cancer while quantifying the potential impact of their use in practice. This paves the way for personalised medicine, where decisions can be based more closely on individual patient details from routine care.

Personalized surveillance and aftercare for non-metastasized breast cancer: the NABOR study protocol of a multiple interrupted time series design.

BACKGROUND: Follow-up of curatively treated primary breast cancer patients consists of surveillance and aftercare and is currently mostly the same for all patients. A more personalized approach, based on patients' individual risk of recurrence and personal needs and preferences, may reduce patient burden and reduce (healthcare) costs. The NABOR study will examine the (cost-)effectiveness of personalized surveillance (PSP) and personalized aftercare plans (PAP) on patient-reported cancer worry, self-rated and overall quality of life and (cost-)effectiveness. METHODS: A prospective multicenter multiple interrupted time series (MITs) design is being used. In this design, 10 participating hospitals will be observed for a period of eighteen months, while they -stepwise- will transit from care as usual to PSPs and PAPs. The PSP contains decisions on the surveillance trajectory based on individual risks and needs, assessed with the 'Breast Cancer Surveillance Decision Aid' including the INFLUENCE prediction tool. The PAP contains decisions on the aftercare trajectory based on individual needs and preferences and available care resources, which decision-making is supported by a patient decision aid. Patients are non-metastasized female primary breast cancer patients (N = 1040) who are curatively treated and start follow-up care. Patient reported outcomes will be measured at five points in time during two years of follow-up care (starting about one year after treatment and every six months thereafter). In addition, data on diagnostics and hospital visits from patients' Electronical Health Records (EHR) will be gathered. Primary outcomes are patient-reported cancer worry (Cancer Worry Scale) and overall quality of life (as assessed with EQ-VAS score). Secondary outcomes include health care costs and resource use, health-related quality of life (as measured with EQ5D-5L/SF-12/EORTC-QLQ-C30), risk perception, shared decision-making, patient satisfaction, societal participation, and cost-effectiveness. Next, the uptake and appreciation of personalized plans and patients' experiences of their decision-making process will be evaluated. DISCUSSION: This study will contribute to insight in the (cost-)effectiveness of personalized follow-up care and contributes to development of uniform evidence-based guidelines, stimulating sustainable implementation of personalized surveillance and aftercare plans. TRIAL REGISTRATION: Study sponsor: ZonMw. Retrospectively registered at ClinicalTrials.gov (2023), ID: NCT05975437.

Radiomics biopsy signature for predicting survival in patients with spinal bone metastases (SBMs).

STUDY DESIGN: Retrospective analysis of a registered cohort of patients treated and irradiated for metastases in the spinal column in a single institute. OBJECTIVE: This is the first study to develop and internally validate radiomics features for predicting six-month survival probability for patients with spinal bone metastases (SBM). BACKGROUND DATA: Extracted radiomics features from routine clinical CT images can be used to identify textural and intensity-based features unperceivable to human observers and associate them with a patient survival probability or disease progression. METHODS: A study was conducted on 250 patients treated for metastases in the spinal column irradiated for the first time between 2014 and 2016, at the MAASTRO clinic in Maastricht, the Netherlands. The first 150 available patients were used to develop the model and the subsequent 100 patient were considered as a test set for the model. A bootstrap (B = 400) stepwise model selection, which combines both the forward and backward variable elimination procedure, was used to select the most useful predictive features from the training data based on the Akaike information criterion (AIC). The stepwise selection procedure was applied to the 400 bootstrap samples, and the results were plotted as a histogram to visualize how often each variable was selected. Only variables selected more than 90 % of the time over the bootstrap runs were used to build the final model.A prognostic index (PI) called radiomics score (radscore) and clinical score (clinscore) was calculated for each patient. The prognostic index was not scaled, the original values were used which can be extracted from the model directly or calculated as a linear combination of the variables in the model multiplied by the respective beta value for each patient. RESULTS: The clinical model had a good discrimination power. The radiomics model, on the other hand, had an inferior performance with no added predictive power to the clinical model. The internal imaging characteristics do not seem to have a value in the prediction of survival. However, the Shape features were excluded from further analyses in our study since all biopsies had a standard shape hence no variability.

Recurrent inference machines as inverse problem solvers for MR relaxometry.

In this paper, we propose the use of Recurrent Inference Machines (RIMs) to perform T1 and T2 mapping. The RIM is a neural network framework that learns an iterative inference process based on the signal model, similar to conventional statistical methods for quantitative MRI (QMRI), such as the Maximum Likelihood Estimator (MLE). This framework combines the advantages of both data-driven and model-based methods, and, we hypothesize, is a promising tool for QMRI. Previously, RIMs were used to solve linear inverse reconstruction problems. Here, we show that they can also be used to optimize non-linear problems and estimate relaxometry maps with high precision and accuracy. The developed RIM framework is evaluated in terms of accuracy and precision and compared to an MLE method and an implementation of the Residual Neural Network (ResNet). The results show that the RIM improves the quality of estimates compared to the other techniques in Monte Carlo experiments with simulated data, test-retest analysis of a system phantom, and in-vivo scans. Additionally, inference with the RIM is 150 times faster than the MLE, and robustness to (slight) variations of scanning parameters is demonstrated. Hence, the RIM is a promising and flexible method for QMRI. Coupled with an open-source training data generation tool, it presents a compelling alternative to previous methods.

Current applications of deep-learning in neuro-oncological MRI.

PURPOSE: Magnetic Resonance Imaging (MRI) provides an essential contribution in the screening, detection, diagnosis, staging, treatment and follow-up in patients with a neurological neoplasm. Deep learning (DL), a subdomain of artificial intelligence has the potential to enhance the characterization, processing and interpretation of MRI images. The aim of this review paper is to give an overview of the current state-of-art usage of DL in MRI for neuro-oncology. METHODS: We reviewed the Pubmed database by applying a specific search strategy including the combination of MRI, DL, neuro-oncology and its corresponding search terminologies, by focussing on Medical Subject Headings (Mesh) or title/abstract appearance. The original research papers were classified based on its application, into three categories: technological innovation, diagnosis and follow-up. RESULTS: Forty-one publications were eligible for review, all were published after the year 2016. The majority (N = 22) was assigned to technological innovation, twelve had a focus on diagnosis and seven were related to patient follow-up. Applications ranged from improving the acquisition, synthetic CT generation, auto-segmentation, tumor classification, outcome prediction and response assessment. The majority of publications made use of standard (T1w, cT1w, T2w and FLAIR imaging), with only a few exceptions using more advanced MRI technologies. The majority of studies used a variation on convolution neural network (CNN) architectures. CONCLUSION: Deep learning in MRI for neuro-oncology is a novel field of research; it has potential in a broad range of applications. Remaining challenges include the accessibility of large imaging datasets, the applicability across institutes/vendors and the validation and implementation of these technologies in clinical practise.

Repeatability and reproducibility study of radiomic features on a phantom and human cohort.

The repeatability and reproducibility of radiomic features extracted from CT scans need to be investigated to evaluate the temporal stability of imaging features with respect to a controlled scenario (test-retest), as well as their dependence on acquisition parameters such as slice thickness, or tube current. Only robust and stable features should be used in prognostication/prediction models to improve generalizability across multiple institutions. In this study, we investigated the repeatability and reproducibility of radiomic features with respect to three different scanners, variable slice thickness, tube current, and use of intravenous (IV) contrast medium, combining phantom studies and human subjects with non-small cell lung cancer. In all, half of the radiomic features showed good repeatability (ICC > 0.9) independent of scanner model. Within acquisition protocols, changes in slice thickness was associated with poorer reproducibility compared to the use of IV contrast. Broad feature classes exhibit different behaviors, with only few features appearing to be the most stable. 108 features presented both good repeatability and reproducibility in all the experiments, most of them being wavelet and Laplacian of Gaussian features.

Testing the effects of checklists on team behaviour during emergencies on general wards: An observational study using high-fidelity simulation.

INTRODUCTION: Clinical teams struggle on general wards with acute management of deteriorating patients. We hypothesized that the Crisis Checklist App, a mobile application containing checklists tailored to crisis-management, can improve teamwork and acute care management. METHODS: A before-and-after study was undertaken in high-fidelity simulation centres in the Netherlands, Denmark and United Kingdom. Clinical teams completed three scenarios with a deteriorating patient without checklists followed by three scenarios using the Crisis Checklist App. Teamwork performance as the primary outcome was assessed by the Mayo High Performance Teamwork scale. The secondary outcomes were the time required to complete all predefined safety-critical steps, percentage of omitted safety-critical steps, effects on other non-technical skills, and users' self-assessments. Linear mixed models and a non-parametric survival test were conducted to assess these outcomes. RESULTS: 32 teams completed 188 scenarios. The Mayo High Performance Teamwork scale mean scores improved to 23.4 out of 32 (95% CI: 22.4-24.3) with the Crisis Checklist App compared to 21.4 (20.4-22.3) with local standard of care. The mean difference was 1.97 (1.34-2.6; p < 0.001). Teams that used the checklists were able to complete all safety-critical steps of a scenario in more simulations (40/95 vs 21/93 scenarios) and these steps were completed faster (stratified log-rank test χ2 = 8.0; p = 0.005). The self-assessments of the observers and users showed favourable effects after checklist usage for other non-technical skills including situational awareness, decision making, task management and communication. CONCLUSIONS: Implementation of a novel mobile crisis checklist application among clinical teams was associated in a simulated general ward setting with improved teamwork performance, and a higher and faster completion rate of predetermined safety-critical steps.

Atom column detection from simultaneously acquired ABF and ADF STEM images.

In electron microscopy, the maximum a posteriori (MAP) probability rule has been introduced as a tool to determine the most probable atomic structure from high-resolution annular dark-field (ADF) scanning transmission electron microscopy (STEM) images exhibiting low contrast-to-noise ratio (CNR). Besides ADF imaging, STEM can also be applied in the annular bright-field (ABF) regime. The ABF STEM mode allows to directly visualize light-element atomic columns in the presence of heavy columns. Typically, light-element nanomaterials are sensitive to the electron beam, limiting the incoming electron dose in order to avoid beam damage and leading to images exhibiting low CNR. Therefore, it is of interest to apply the MAP probability rule not only to ADF STEM images, but to ABF STEM images as well. In this work, the methodology of the MAP rule, which combines statistical parameter estimation theory and model-order selection, is extended to be applied to simultaneously acquired ABF and ADF STEM images. For this, an extension of the commonly used parametric models in STEM is proposed. Hereby, the effect of specimen tilt has been taken into account, since small tilts from the crystal zone axis affect, especially, ABF STEM intensities. Using simulations as well as experimental data, it is shown that the proposed methodology can be successfully used to detect light elements in the presence of heavy elements.

Burden of disease in children with respiratory tract infections in primary care: diary-based cohort study.

BACKGROUND: Respiratory tract infections (RTIs) are a common reason for children to consult in general practice. Antibiotics are often prescribed, in part due to miscommunication between parents and GPs. The duration of specific respiratory symptoms has been widely studied. Less is known about illness-related symptoms and the impact of these symptoms on family life, including parental production loss. Better understanding of the natural course of illness-related symptoms in RTI in children and impact on family life may improve GP-parent communication during RTI consultations. OBJECTIVE: To describe the general impact of RTI on children and parents regarding illness-related symptoms, absenteeism from childcare, school and work, use of health care facilities, and the use of over-the-counter (OTC) medication. METHODS: Prospectively collected diary data from two randomized clinical trials in children with RTI in primary care (n = 149). Duration of symptoms was analysed using survival analysis. RESULTS: Disturbed sleep, decreased intake of food and/or fluid, feeling ill and/or disturbance at play or other daily activities are very common during RTI episodes, with disturbed sleep lasting longest. Fifty-two percent of the children were absent for one or more days from childcare or school, and 28% of mothers and 20% of fathers reported absence from work the first week after GP consultation. Re-consultation occurred in 48% of the children. OTC medication was given frequently, particularly paracetamol and nasal sprays. CONCLUSION: Appreciation of, and communication about the general burden of disease on children and their parents, may improve understanding between GPs and parents consulting with their child.

Continuing acromioclavicular joint pain after excision arthroplasty: is further surgery effective?

BACKGROUND: Little published evidence exists on the incidence of continuing acromioclavicular joint pain with no published outcomes for revision surgery. This study aimed to establish the incidence and outcomes of revision acromioclavicular joint excision surgery. MATERIALS AND METHODS: A consecutive retrospective cohort of patients undergoing revision arthroscopic or open acromioclavicular joint excision was identified. Patients were identified from a prospectively collected database. Inclusion criteria were revision acromioclavicular joint excisions over a 14-year period between 2001 and 2015. Exclusion criteria were previous surgery for acromioclavicular joint instability or shoulder arthroplasty. Outcome measures were Oxford Shoulder scores and a satisfaction survey. RESULTS: Forty-three consecutive cases of revision acromioclavicular joint excision over 14 years (37 after arthroscopic excision with subacromial decompression, 5 after arthroscopic excision with rotator cuff repair, 1 after open excision). Continuing acromioclavicular joint pain was associated with incomplete resection from arthroscopic surgery, which was the primary indication for revision surgery. Revision occurred a mean 14.2 months after primary surgery (standard deviation 7.6 months). Mean Oxford Shoulder score was preoperatively 18 (standard deviation 8.1) and 23.4 (standard deviation 11.1) after primary surgery, which did not reach significance until after revision surgery with a mean 31.7 (standard deviation 13.6; P = 0.021). Median follow up was 15 months (interquartile range 4-31 months). A survey at a mean of 6 years (standard deviation 2.3) post-revision surgery found that 65% of patients felt improved, 77% would have their surgery again and 69% of patients felt satisfied. The incidence of postoperative frozen shoulder was 14.3%. CONCLUSION: Functional outcomes after revision surgery showed improvement from scores taken before primary surgery; however, long-term satisfaction rates were relatively low.

The maximum a posteriori probability rule for atom column detection from HAADF STEM images.

Recently, the maximum a posteriori (MAP) probability rule has been proposed as an objective and quantitative method to detect atom columns and even single atoms from high-resolution high-angle annular dark-field (HAADF) scanning transmission electron microscopy (STEM) images. The method combines statistical parameter estimation and model-order selection using a Bayesian framework and has been shown to be especially useful for the analysis of the structure of beam-sensitive nanomaterials. In order to avoid beam damage, images of such materials are usually acquired using a limited incoming electron dose resulting in a low contrast-to-noise ratio (CNR) which makes visual inspection unreliable. This creates a need for an objective and quantitative approach. The present paper describes the methodology of the MAP probability rule, gives its step-by-step derivation and discusses its algorithmic implementation for atom column detection. In addition, simulation results are presented showing that the performance of the MAP probability rule to detect the correct number of atomic columns from HAADF STEM images is superior to that of other model-order selection criteria, including the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC). Moreover, the MAP probability rule is used as a tool to evaluate the relation between STEM image quality measures and atom detectability resulting in the introduction of the so-called integrated CNR (ICNR) as a new image quality measure that better correlates with atom detectability than conventional measures such as signal-to-noise ratio (SNR) and CNR.

OPTIMA: a phase II dose and volume de-escalation trial for human papillomavirus-positive oropharyngeal cancer.

BACKGROUND: Patients with HPV+ oropharyngeal squamous cell carcinoma were assigned to dose and volume de-escalated radiotherapy (RT) or chemoradiotherapy (CRT) based on response to induction chemotherapy in an effort to limit treatment-related toxicity while preserving efficacy. PATIENTS AND METHODS: Patients were classified as low-risk (≤T3, ≤N2B, ≤10 pack-year history) or high-risk (T4 or ≥N2C or >10 PYH). After three cycles of carboplatin/nab-paclitaxel, response was assessed using Response Evaluation Criteria in Solid Tumors 1.1. Low-risk patients with ≥50% response received 50 Gray (Gy) RT (RT50) while low-risk patients with 30%-50% response or high-risk patients with ≥50% response received 45 Gy CRT (CRT45). Patients with lesser response received standard-of-care 75 Gy CRT (CRT75). RT/CRT was limited to the first echelon of uninvolved nodes. The primary end point was 2-year progression-free survival compared with a historic control of 85%. Secondary end points included overall survival and toxicity. RESULTS: Sixty-two patients (28 low risk/34 high risk) were enrolled. Of low-risk patients, 71% received RT50 while 21% received CRT45. Of high-risk patients, 71% received CRT45. With a median follow-up of 29 months, 2-year PFS and OS were 95% and 100% for low-risk patients and 94% and 97% for high-risk patients, respectively. The overall 2-year PFS was 94.5% and within the 11% noninferiority margin for the historic control. Grade 3+ mucositis occurred in 30%, 63%, and 91% of the RT50, CRT45, and CRT75 groups, respectively (P = 0.004). Rates of any PEG-tube use were 0%, 31%, and 82% for RT50, CRT45, and CRT75 groups, respectively (P < 0.0001). CONCLUSIONS: Induction chemotherapy with response and risk-stratified dose and volume de-escalated RT/CRT for HPV+ OPSCC is associated with favorable oncologic outcomes and reduced acute and chronic toxicity. Further evaluation of induction-based de-escalation in large multicenter studies is justified. CLINICAL TRIAL REGISTRATION: Clinical trials.gov identifier: NCT02258659.

Treatment data and technical process challenges for practical big data efforts in radiation oncology.

The term Big Data has come to encompass a number of concepts and uses within medicine. This paper lays out the relevance and application of large collections of data in the radiation oncology community. We describe the potential importance and uses in clinical practice. The important concepts are then described and how they have been or could be implemented are discussed. Impediments to progress in the collection and use of sufficient quantities of data are also described. Finally, recommendations for how the community can move forward to achieve the potential of big data in radiation oncology are provided.

Single Atom Detection from Low Contrast-to-Noise Ratio Electron Microscopy Images.

Single atom detection is of key importance to solving a wide range of scientific and technological problems. The strong interaction of electrons with matter makes transmission electron microscopy one of the most promising techniques. In particular, aberration correction using scanning transmission electron microscopy has made a significant step forward toward detecting single atoms. However, to overcome radiation damage, related to the use of high-energy electrons, the incoming electron dose should be kept low enough. This results in images exhibiting a low signal-to-noise ratio and extremely weak contrast, especially for light-element nanomaterials. To overcome this problem, a combination of physics-based model fitting and the use of a model-order selection method is proposed, enabling one to detect single atoms with high reliability.

PRODIGE: PRediction models in prOstate cancer for personalized meDIcine challenGE.

AIM: Identifying the best care for a patient can be extremely challenging. To support the creation of multifactorial Decision Support Systems (DSSs), we propose an Umbrella Protocol, focusing on prostate cancer. MATERIALS & METHODS: The PRODIGE project consisted of a workflow for standardizing data, and procedures, to create a consistent dataset useful to elaborate DSSs. Techniques from classical statistics and machine learning will be adopted. The general protocol accepted by our Ethical Committee can be downloaded from cancerdata.org . RESULTS: A standardized knowledge sharing process has been implemented by using a semi-formal ontology for the representation of relevant clinical variables. CONCLUSION: The development of DSSs, based on standardized knowledge, could be a tool to achieve a personalized decision-making.

Current practice of closed-loop mechanical ventilation modes on intensive care units - a nationwide survey in the Netherlands.

BACKGROUND: The most recent modes for mechanical ventilation are closed-loop modes, which are able to automatically adjust certain respiratory settings. Although closed-loop modes have been investigated in various clinical trials, it is unclear to what extent these modes are actually used in clinical practice. The aim of this study was to determine closed-loop ventilation practice on intensive care units (ICUs) in the Netherlands, and to explore reasons for not applying closed-loop ventilation. Our hypothesis was that closed-loop ventilation is increasingly used. METHODS: A short survey was conducted among all non-paediatric ICUs in the Netherlands. Use of closed-loop modes was classified as frequently, occasionally or never, if respondents stated they had used these modes in the last week, in the last month/year, or never, respectively. RESULTS: The response rate of the survey was 82% (72 of 88). Respondents had access to a closed-loop ventilation mode in 58% of the ICUs (42 of 72). Of these ICUs, 43% (18 of 42) frequently applied a closed-loop ventilation mode, while 57% (24 of 42) never or occasionally used it. Reasons for not using these modes were lack of knowledge (40%), insufficient evidence reporting a beneficial effect (35%) and lack of confidence (25%). CONCLUSION: This study does not support our hypothesis that closed-loop ventilation is increasingly used in the Dutch ICU setting. While industry continues to develop new closed-loop modes, implementation of these modes in clinical practice seems to encounter difficulties. Various barriers could play a role, and these all need attention in future investigations.