Search

Abstract Purpose To build an Mult-Task Learning (MTL) based Artificial Intelligence(AI) model that can simultaneously predict clinical stage, histology, grade and LNM for cervical cancer before surgery. Methods This retrospective and prospective cohort study was conducted from January 2001 to March 2014 for the training set and from January 2018 to November 2021 for the validation set at Beijing Chaoyang Hospital, Capital Medical University. Preoperative clinical information of cervical cancer patients was used. An Artificial Neural Network (ANN) algorithm was used to build the MTL-based AI model. Accuracy and weighted F1 scores were calculated as evaluation indicators. The performance of the MTL model was compared with Single-Task Learning (STL) models. Additionally, a Turing test was performed by 20 gynecologists and compared with this AI model. Results A total of 223 cervical cancer cases were retrospectively enrolled into the training set, and 58 cases were prospectively collected as independent validation set. The accuracy of this cervical cancer AI model constructed with ANN algorithm in predicting stage, histology, grade and LNM were 75%, 95%, 86% and 76%, respectively. And the corresponding weighted F1 score were 70%, 94%, 86%, and 76%, respectively. The average time consumption of AI simultaneously predicting stage, histology, grade and LNM for cervical cancer was 0.01s (95%CI: 0.01–0.01) per 20 patients. The mean time consumption doctor and doctor with AI were 581.1s (95%CI: 300.0-900.0) per 20 patients and 534.8s (95%CI: 255.0-720.0) per 20 patients, respectively. Except for LNM, both the accuracy and F-score of the AI model were significantly better than STL AI, doctors and AI-assisted doctors in predicting stage, grade and histology. (P

Abstract An ever-increasing amount of data on a person’s daily functioning is being collected, which holds information to revolutionize person-centered healthcare. However, the full potential of data on daily functioning cannot yet be exploited as it is mostly stored in an unstructured and inaccessible manner. The integration of these data, and thereby expedited knowledge discovery, is possible by the introduction of functionomics as a complementary ‘omics’ initiative, embracing the advances in data science. Functionomics is the study of high-throughput data on a person’s daily functioning, that can be operationalized with the International Classification of Functioning, Disability and Health (ICF). A prerequisite for making functionomics operational are the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This paper illustrates a step by step application of the FAIR principles for making functionomics data machine readable and accessible, under strictly certified conditions, in a practical example. Establishing more FAIR functionomics data repositories, analyzed using a federated data infrastructure, enables new knowledge generation to improve health and person-centered healthcare. Together, as one allied health and healthcare research community, we need to consider to take up the here proposed methods.

Abstract Objective Hospitals and healthcare providers should assess and compare the quality of care given to patients and based on this improve the care. In the Netherlands, hospitals provide data to national quality registries, which in return provide annual quality indicators. However, this process is time-consuming, resource intensive and risks patient privacy and confidentiality. In this paper, we presented a multicentric ‘Proof of Principle’ study for federated calculation of quality indicators in patients with colorectal cancer. The findings suggest that the proposed approach is highly time-efficient and consume significantly lesser resources. Materials and methods Two quality indicators are calculated in an efficient and privacy presevering federated manner, by i) applying the Findable Accessible Interoperable and Reusable (FAIR) data principles and ii) using the Personal Health Train (PHT) infrastructure. Instead of sharing data to a centralized registry, PHT enables analysis by sending algorithms and sharing only insights from the data. Results ETL process extracted data from the Electronic Health Record systems of the hospitals, converted them to FAIR data and hosted in RDF endpoints within each hospital. Finally, quality indicators from each center are calculated using PHT and the mean result along with the individual results plotted. Discussion and conclusion PHT and FAIR data principles can efficiently calculate quality indicators in a privacy-preserving federated approach and the work can be scaled up both nationally and internationally. Despite this, application of the methodology was largely hampered by ELSI issues. However, the lessons learned from this study can provide other hospitals and researchers to adapt to the process easily and take effective measures in building quality of care infrastructures.

Abstract Federated learning makes it possible to train a machine learning model on decentralized data. Bayesian networks are widely used probabilistic graphical models. While some research has been published on the federated learning of Bayesian networks, publications on Bayesian networks in a vertically partitioned data setting are limited, with important omissions, such as handling missing data. We propose a novel method called VertiBayes to train Bayesian networks (structure and parameters) on vertically partitioned data, which can handle missing values as well as an arbitrary number of parties. For structure learning we adapted the K2 algorithm with a privacy-preserving scalar product protocol. For parameter learning, we use a two-step approach: first, we learn an intermediate model using maximum likelihood, treating missing values as a special value, then we train a model on synthetic data generated by the intermediate model using the EM algorithm. The privacy guarantees of VertiBayes are equivalent to those provided by the privacy preserving scalar product protocol used. We experimentally show VertiBayes produces models comparable to those learnt using traditional algorithms. Finally, we propose two alternative approaches to estimate the performance of the model using vertically partitioned data and we show in experiments that these give accurate estimates.

Abstract Predictive modelling of cancer outcomes using radiomics faces dimensionality problems and data limitations, as radiomics features often number in the hundreds, and multi-institutional data sharing is ()often unfeasible. Federated learning (FL) and feature selection (FS) techniques combined can help overcome these issues, as one provides the means of training models without exchanging sensitive data, while the other identifies the most informative features, reduces overfitting, and improves model interpretability. Our proposed FS pipeline based on FL principles targets data-driven radiomics FS in a multivariate survival study of non-small cell lung cancer patients. The pipeline was run across datasets from three institutions without patient-level data exchange. It includes two FS techniques, Correlation-based Feature Selection and LASSO regularization, and Cox Proportional-Hazard regression with Overall Survival as endpoint. Trained and validated on 828 patients overall, our pipeline yielded a radiomic signature comprising "intensity-based energy" and "mean discretised intensity". Validation resulted in a mean Harrell C-index of 0.59, showcasing fair efficacy in risk stratification. In conclusion, we suggest a distributed radiomics approach that incorporates preliminary feature selection to systematically decrease the feature set based on data-driven considerations. This aims to address dimensionality challenges beyond those associated with data constraints and interpretability concerns.

Summary: Introduction: Over the last two decades, there have been some efforts to improve maternal and child health around the globe. However, the efforts are still lacking longstanding outcomes. Lack of awareness and access to information for decision-making has been an obstacle for women, especially in developing countries. This study aims to find potential strategies to improve maternal and child health using mHealth in Ethiopia to enhance service uptake and future decisions. Methods: This study applies cluster randomized controlled trials to test if mobile phone (mHealth) text messages can improve the uptaking of postpartum family planning and child feeding practices such as prelacteal feeding, initiation of breastfeeding, exclusive breastfeeding, and complementary feeding. Repeated data collections during the first and fifth months enhance understanding of child feeding practice and its improvement compared to baseline information. It can also help to understand postpartum family planning practices among mothers. The sample size includes 672 mothers who are in the third trimester, have access to a mobile phone, can use mobile phones, and can read and understand text messages. Multilevel logistic regression, generalized estimation equation, and survival analysis are the models for final analysis. The models enable us to determine the percentage differences between baseline and intervention groups. Ethics: The team has collected ethical clearance to conduct the study from the Arba Minch University Board of Institutional Ethical Review. Dissemination: As part of open science communication, the team is committed to publishing the protocol, procedures, findings of the trial, and then the data. Trial registration number: PACTR202211547107725 Pan African Clinical Trial Registry.

Objectives Although neoadjuvant immunochemotherapy has been widely applied in non-small cell lung cancer (NSCLC), predicting treatment response remains a challenge. We used pretreatment multimodal CT to explore deep learning-based immunochemotherapy response image biomarkers.Methods This study retrospectively obtained non-contrast enhanced and contrast enhancedbubu CT scans of patients with NSCLC who underwent surgery after receiving neoadjuvant immunochemotherapy at multiple centers between August 2019 and February 2023. Deep learning features were extracted from both non-contrast enhanced and contrast enhanced CT scans to construct the predictive models (LUNAI-uCT model and LUNAI-eCT model), respectively. After the feature fusion of these two types of features, a fused model (LUNAI-fCT model) was constructed. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. SHapley Additive exPlanations analysis was used to quantify the impact of CT imaging features on model prediction. To gain insights into how our model makes predictions, we employed Gradient-weighted Class Activation Mapping to generate saliency heatmaps.Results The training and validation datasets included 113 patients from Center A at the 8:2 ratio, and the test dataset included 112 patients (Center B n=73, Center C n=20, Center D n=19). In the test dataset, the LUNAI-uCT, LUNAI-eCT, and LUNAI-fCT models achieved AUCs of 0.762 (95% CI 0.654 to 0.791), 0.797 (95% CI 0.724 to 0.844), and 0.866 (95% CI 0.821 to 0.883), respectively.Conclusions By extracting deep learning features from contrast enhanced and non-contrast enhanced CT, we constructed the LUNAI-fCT model as an imaging biomarker, which can non-invasively predict pathological complete response in neoadjuvant immunochemotherapy for NSCLC.

Purpose: This study aims to develop and externally validate a clinically plausible Bayesian network structure to predict one-year erectile dysfunction in prostate cancer patients by combining expert knowledge with evidence from data using clinical and Patient-reported outcome measures (PROMs) data. In addition, compare and contrast structures that stem from PROM information and routine clinical data. Summary of background: For men with localized prostate cancer, choosing the optimal treatment can be challenging since each option comes with different side effects, such as erectile dysfunction, which negatively impacts their quality of life. Our previous findings demonstrate that logistic regression models are able to identify patients at high risk of erectile dysfunction. However, methods such as Bayesian networks may be more successful, as they intricately represent the causal relations between the variables. Patients and methods: 946 prostate cancer patients from 65 Dutch hospitals were considered to develop the Bayesian network structure. Continuous variables were discretized before analysis based on expert opinions and literature. Patients with missing information and variables with more than 25% of missing information were excluded. Prostate cancer treating physicians first determined the relationships (arcs) between the available variables. The structures were then modified based on algorithmically derived structures using the hill-climbing algorithm. Structural Performance was evaluated based on the area under the curve (AUC) values and calibration plots on the training and test data. Results: BMI and prostate volume via MRI were excluded from this analysis due to their high percentage of missingness (>45 %). The final cohort was reduced to 505 and 216 after excluding 157 and 68 patients with missing information, respectively. The AUC of the PROM structure was better than the clinical structure in both the train and test data. The structure that combined both sources of information had an AUC value of 0.94 (0.92 – 0.96) and 0.84171 (0.77 91) in the train and test data, respectively. Conclusion: Bayesian network structures derived from PROM information by complimenting expert knowledge with evidence from the data produce a clinically plausible structure that is more performant than structures from clinical data. Our study supports the growing global recognition of incorporating the patient’s perspective in outcomes research for better decision-making and optimal outcomes. However, a structure that combines both sources of information gives a more holistic view of the patient with actionable insights and improved discriminative power.

Objective: To develop a model combining clinical and radiomics features from CT scans for a preoperative noninvasive evaluation of Huvos grading of neoadjuvant chemotherapy in patients with HOS. Methods: 183 patients from center A and 42 from center B were categorized into training and validation sets. Features derived from radiomics were obtained from unenhanced CT scans.Following dimensionality reduction, the most optimal features were selected and utilized in creating a radiomics model through logistic regression analysis. Integrating clinical features, a composite clinical radiomics model was developed, and a nomogram was constructed. Predictive performance of the model was evaluated using ROC curves and calibration curves. Additionally, decision curve analysis was conducted to assess practical utility of nomogram in clinical settings. Results: LASSO LR analysis was performed, and finally, three selected image omics features were obtained.Radiomics model yielded AUC values with a good diagnostic effect for both patient sets (AUCs: 0.69 and 0.68, respectively). Clinical models (including sex, age, pre-chemotherapy ALP and LDH levels, new lung metastases within 1 year after surgery, and incidence) performed well in terms of Huvos grade prediction, with an AUC of 0.74 for training set. The AUC for independent validation set stood at 0.70. Notably, the amalgamation of radiomics and clinical features exhibited commendable predictive prowess in training set, registering an AUC of 0.78. This robust performance was subsequently validated in the independent validation set, where the AUC remained high at 0.75. Calibration curves of nomogram showed that the predictions were in good agreement with actual observations. Conclusion: Combined model can be used for Huvos grading in patients with HOS after preoperative chemotherapy, which is helpful for adjuvant treatment decisions.

Abstract Objectives Stereotactic body radiotherapy (SBRT) is a treatment option for patients with early-stage non-small cell lung cancer (NSCLC) who are unfit for surgery. Some patients may experience distant metastasis. This study aimed to develop and validate a radiomics model for predicting distant metastasis in patients with early-stage NSCLC treated with SBRT. Methods Patients at five institutions were enrolled in this study. Radiomics features were extracted based on the PET/CT images. After feature selection in the training set (from Tianjin), CT-based and PET-based radiomics signatures were built. Models based on CT and PET signatures were built and validated using external datasets (from Zhejiang, Zhengzhou, Shandong, and Shanghai). An integrated model that included CT and PET radiomic signatures was developed. The performance of the proposed model was evaluated in terms of its discrimination, calibration, and clinical utility. Multivariate logistic regression was used to calculate the probability of distant metastases. The cutoff value was obtained using the receiver operator characteristic curve (ROC), and the patients were divided into high- and low-risk groups. Kaplan-Meier analysis was used to evaluate the distant metastasis-free survival (DMFS) of different risk groups. Results In total, 228 patients were enrolled. The median follow-up time was 31.4 (2.0-111.4) months. The model based on CT radiomics signatures had an area under the curve (AUC) of 0.819 in the training set (n = 139) and 0.786 in the external dataset (n = 89). The PET radiomics model had an AUC of 0.763 for the training set and 0.804 for the external dataset. The model combining CT and PET radiomics had an AUC of 0.835 for the training set and 0.819 for the external dataset. The combined model showed a moderate calibration and a positive net benefit. When the probability of distant metastasis was greater than 0.19, the patient was considered to be at high risk. The DMFS of patients with high- and low-risk was significantly stratified (P

Abstract Introduction Poor child feeding practice is a public health problem in Africa. Mobile health (mHealth) is a supportive intervention to improve this problem; however, the evidence available in the current literature is inconsistent and inconclusive in Africa. Some studies state that exclusive breastfeeding is not different between controls and mHealth interventions in the first month. Other studies state that health providers need additional training for the success of mHealth interventions. Objective This systematic review and meta-analysis aims to provide the summarized effect of mHealth on child-feeding practices in Africa to improve future planning and decisions. Method We conducted a systematic review and meta-analysis based on the published and unpublished evidence gathered from PubMed, Web of Science, Cochrane Library, and Embase databases between January 1, 2000, and March 1, 2022. Studies included were randomized control trials and experimental studies that compared mHealth to standards of care among postpartum women. Preferred Reporting Items for Systematic Review and Meta-analysis guidelines followed for the reporting. Results After screening 1188 studies, we identified six studies that fulfilled the study criteria. These studies had 2913 participants with the number of total intervention groups 1627 [1627/2913 = 56%]. Five studies were completed within 24 weeks while one required 12 weeks. We included two RCTs, two cluster RCTs, and two quasi-experimental studies all used mHealth as the major intervention and usual care as controls. We found significant improvement in child-feeding practices among intervention groups. Conclusion This systematic review and meta-analysis showed that the application of mHealth improved child-feeding practices in Africa. Although the finding is compelling, the authors recommend high-quality studies and mHealth interventions that consider sample size, design, regional differences, and environmental constraints to enhance policy decisions. The place of residence, access, low socioeconomic development, poor socio-demographic characteristics, low women empowerment, and low women’s education might cause high heterogeneity in the included regions and need consideration during interventions. Registration number: PROSPERO: CRD42022346950.

Abstract In the past decade, there has been a sharp increase in publications describing applications of convolutional neural networks (CNNs) in medical image analysis. However, recent reviews have warned of the lack of reproducibility of most such studies, which has impeded closer examination of the models and, in turn, their implementation in healthcare. On the other hand, the performance of these models is highly dependent on decisions on architecture and image pre-processing. In this work, we assess the reproducibility of three studies that use CNNs for head and neck cancer outcome prediction by attempting to reproduce the published results. In addition, we propose a new network structure and assess the impact of image pre-processing and model selection criteria on performance. We used two publicly available datasets: one with 298 patients for training and validation and another with 137 patients from a different institute for testing. All three studies failed to report elements required to reproduce their results thoroughly, mainly the image pre-processing steps and the random seed. Our model either outperforms or achieves similar performance to the existing models with considerably fewer parameters. We also observed that the pre-processing efforts significantly impact the model’s performance and that some model selection criteria may lead to suboptimal models. Although there have been improvements in the reproducibility of deep learning models, our work suggests that wider implementation of reporting standards is required to avoid a reproducibility crisis.

IntroductionVaccine-preventable diseases are the public health problems in Africa, although vaccination is an available, safe, simple, and effective method prevention. Technologies such as mHealth may provide maternal access to health information and support decisions on childhood vaccination. Many studies on the role of mHealth in vaccination decisions have been conducted in Africa, but the evidence needs to provide conclusive information to support mHealth introduction. This study provides essential information to assist planning and policy decisions regarding the use of mHealth for childhood vaccination.MethodsWe conducted a systematic review and meta-analysis for studies applying mHealth in Africa for vaccination decisions following the Preferred Reporting Items for Systematic and Meta-Analysis [PRISMA] guideline. Databases such as CINAHL, EMBASE, PubMed, PsycINFO, Scopus, Web of Science, Google Scholar, Global Health, HINARI, and Cochrane Library were included. We screened studies in Endnote X20 and performed the analysis using Revman 5.4.1.ResultsThe database search yielded 1,365 articles [14 RCTs and 4 quasi-experiments] with 21,070 participants satisfied all eligibility criteria. The meta-analysis showed that mHealth has an OR of 2.15 [95% CI: 1.70-2.72; PConclusionAlthough heterogeneous, this systematic review and meta-analysis showed that the application of mHealth could potentially improve childhood vaccination in Africa. It increased childhood vaccination by more than double [2.15 times] among children whose mothers are motivated by mHealth services. MHealth is more effective in less developed regions and when an additional incentive party with the messaging system. However, it can be provided at a comparably low cost based on the development level of regions and can be established as a routine service in Africa.RegistrationPROSPERO: CRD42023415956.

IntroductionMaternal and child mortality remained higher in developing regions such as Southern Ethiopia due to poor maternal and child health. Technologies such as mobile applications in health may be an opportunity to reduce maternal and child mortality because they can improve access to information. Therefore, the main aim of this study was to explore the role of mHealth in improving maternal and child health in Southern Ethiopia.MethodsThis study employed a qualitative study design to explore the role of mHealth in improving maternal and child health among health professionals in Southern Ethiopia from December 2022 to March 2023. We conducted nine in-depth interviews, six key informants' in-depth interviews, and four focused group discussions among health professionals. This is followed by thematic analyses to synthesize the collected evidence.ResultsThe results are based on 226 quotations, 5 major themes, and 24 subthemes. The study participants discussed the possible acceptance of mHealth in terms of its fitness in the existing health system, its support to health professionals, and its importance in improving maternal and child health. The participants ascertained the importance of awareness creation before the implementation of mHealth among women, families, communities, and providers. They reported the importance of mHealth for mothers and health professionals and the effectiveness of mHealth services. The participants stated that the main challenges related to acceptance, awareness, negligence, readiness, and workload. However, they also suggested strategic solutions such as using family support, provider support, mothers' forums, and community forums.ConclusionThe evidence generated during this analysis is important information for program implementations and can inform policy-making. The planned intervention needs to introduce mHealth in Southern Ethiopia. Planners, decision-makers, and researchers can use it in mobile technology-related interventions. For challenges identified, we recommend solution-identified-based interventions and quality studies.

Abstract Ensuring safe and healthy food is a big challenge due to the complexity of food supply chains and their vulnerability to many internal and external factors, including food fraud. Recent research has shown that Artificial Intelligence (AI) based algorithms, in particularly data driven Bayesian Network (BN) models, are very suitable as a tool to predict future food fraud and hence allowing food producers to take proper actions to avoid that such problems occur. Such models become even more powerful when data can be used from all actors in the supply chain, but data sharing is hampered by different interests, data security and data privacy. Federated learning (FL) may circumvent these issues as demonstrated in various areas of the life sciences. In this research, we demonstrate the potential of the FL technology for food fraud using a data driven BN, integrating data from different data owners without the data leaving the database of the data owners. To this end, a framework was constructed consisting of three geographically different data stations hosting different datasets on food fraud. Using this framework, a BN algorithm was implemented that was trained on the data of different data stations while the data remained at its physical location abiding by privacy principles. We demonstrated the applicability of the federated BN in food fraud and anticipate that such framework may support stakeholders in the food supply chain for better decision-making regarding food fraud control while still preserving the privacy and confidentiality nature of these data.

Cancer is a fatal disease and the second most cause of death worldwide. Treatment of cancer is a complex process and requires a multi-modality-based approach. Cancer detection and treatment starts with screening/diagnosis and continues till the patient is alive. Screening/diagnosis of the disease is the beginning of cancer management and continued with the staging of the disease, planning and delivery of treatment, treatment monitoring, and ongoing monitoring and follow-up. Imaging plays an important role in all stages of cancer management. Conventional oncology practice considers that all patients are similar in a disease type, whereas biomarkers subgroup the patients in a disease type which leads to the development of precision oncology. The utilization of the radiomic process has facilitated the advancement of diverse imaging biomarkers that find application in precision oncology. The role of imaging biomarkers and artificial intelligence (AI) in oncology has been investigated by many researchers in the past. The existing literature is suggestive of the increasing role of imaging biomarkers and AI in oncology. However, the stability of radiomic features has also been questioned. The radiomic community has recognized that the instability of radiomic features poses a danger to the global generalization of radiomic-based prediction models. In order to establish radiomic-based imaging biomarkers in oncology, the robustness of radiomic features needs to be established on a priority basis. This is because radiomic models developed in one institution frequently perform poorly in other institutions, most likely due to radiomic feature instability. To generalize radiomic-based prediction models in oncology, a number of initiatives, including Quantitative Imaging Network (QIN), Quantitative Imaging Biomarkers Alliance (QIBA), and Image Biomarker Standardisation Initiative (IBSI), have been launched to stabilize the radiomic features.

BackgroundComputerized radiological image analysis (radiomics) enables the investigation of image-derived phenotypes by extracting large numbers of quantitative features. We hypothesized that radiomics features may contain prognostic information that enhances conventional body composition analysis. We aimed to investigate whether body composition-associated radiomics features hold additional value over conventional body composition analysis and clinical patient characteristics used to predict survival of pancreatic ductal adenocarcinoma (PDAC) patients.MethodsComputed tomography images of 304 patients undergoing elective pancreatic cancer resection were analysed. 2D radiomics features were extracted from skeletal muscle and subcutaneous and visceral adipose tissue (SAT and VAT) compartments from a single slice at the third lumbar vertebra. The study population was randomly split (80:20) into training and holdout subsets. Feature ranking with Least Absolute Shrinkage Selection Operator (LASSO) followed by multivariable stepwise Cox regression in 1000 bootstrapped re-samples of the training data was performed and tested on the holdout data. The fitted regression predictors were used as “scores” for a clinical (C-Score), body composition (B-Score), and radiomics (R-Score) model. To stratify patients into the highest 25% and lowest 25% risk of mortality compared to the middle 50%, the Harrell Concordance Index was used.ResultsBased on LASSO and stepwise cox regression for overall survival, ASA ≥3 and age were the most important clinical variables and constituted the C-score, and VAT-index (VATI) was the most important body composition variable and constituted the B-score. Three radiomics features (SATI_original_shape2D_Perimeter, VATI_original_glszm_SmallAreaEmphasis, and VATI_original_firstorder_Maximum) emerged as the most frequent set of features and yielded an R-Score. Of the mean concordance indices of C-, B-, and R-scores, R-score performed best (0.61, 95% CI 0.56–0.65, p

Abstract Background Data shortage is a common challenge in developing computer-aided diagnosis systems. We developed a generative adversarial network (GAN) model to generate synthetic lung lesions mimicking ground glass nodules (GGNs). Methods We used 216 computed tomography images with 340 GGNs from the Lung Image Database Consortium and Image Database Resource Initiative database. A GAN model retrieving information from the whole image and the GGN region was built. The generated samples were evaluated with visual Turing test performed by four experienced radiologists or pulmonologists. Radiomic features were compared between real and synthetic nodules. Performances were evaluated by area under the curve (AUC) at receiver operating characteristic analysis. In addition, we trained a classification model (ResNet) to investigate whether the synthetic GGNs can improve the performances algorithm and how performances changed as a function of labelled data used in training. Results Of 51 synthetic GGNs, 19 (37%) were classified as real by clinicians. Of 93 radiomic features, 58 (62.4%) showed no significant difference between synthetic and real GGNs (p ≥ 0.052). The discrimination performances of physicians (AUC 0.68) and radiomics (AUC 0.66) were similar, with no-significantly different (p = 0.23), but clinicians achieved a better accuracy (AUC 0.74) than radiomics (AUC 0.62) (p

Background and purpose: The model based approach involves the use of normal tissue complication models for selection of head and neck cancer patients to proton therapy. Our goal was to validate the clinical utility of the related dysphagia model using an independent patient cohort. Materials and Methods: A dataset of 277 head and neck cancer (pharynx and larynx) patients treated with (chemo)radiotherapy between 2019 and 2021 was acquired. For the evaluation of the model discrimination we used statistical metrics such as the sensitivity, specificity and the area under the receiver operating characteristic curve. After the validation we evaluated if the dysphagia model can be improved using the closed testing procedure, the Brier and the Hosmer-Lemeshow score. Results: The performance of the original normal tissue complication probability model for dysphagia grade II-IV at 6 months was good (AUC = 0.80). According to the graphical calibration assessment, the original model showed underestimated dysphagia risk predictions. The closed testing procedure indicated that the model had to be updated and selected a revised model with new predictor coefficients as an optimal model. The revised model had also satisfactory discrimination (AUC = 0.83) with improved calibration. Conclusion: The validation of the normal tissue complication probability model for grade II-IV dysphagia was successful in our independent validation cohort. However, the closed testing procedure indicated that the model should be updated with new coefficients.

Abstract Background Anal cancer is a rare cancer with rising incidence. Despite the relatively good outcomes conferred by state-of-the-art chemoradiotherapy, further improving disease control and reducing toxicity has proven challenging. Developing and validating prognostic models using routinely collected data may provide new insights for treatment development and selection. However, due to the rarity of the cancer, it can be difficult to obtain sufficient data, especially from single centres, to develop and validate robust models. Moreover, multi-centre model development is hampered by ethical barriers and data protection regulations that often limit accessibility to patient data. Distributed (or federated) learning allows models to be developed using data from multiple centres without any individual-level patient data leaving the originating centre, therefore preserving patient data privacy. This work builds on the proof-of-concept three-centre atomCAT1 study and describes the protocol for the multi-centre atomCAT2 study, which aims to develop and validate robust prognostic models for three clinically important outcomes in anal cancer following chemoradiotherapy. Methods This is a retrospective multi-centre cohort study, investigating overall survival, locoregional control and freedom from distant metastasis after primary chemoradiotherapy for anal squamous cell carcinoma. Patient data will be extracted and organised at each participating radiotherapy centre (n = 18). Candidate prognostic factors have been identified through literature review and expert opinion. Summary statistics will be calculated and exchanged between centres prior to modelling. The primary analysis will involve developing and validating Cox proportional hazards models across centres for each outcome through distributed learning. Outcomes at specific timepoints of interest and factor effect estimates will be reported, allowing for outcome prediction for future patients. Discussion The atomCAT2 study will analyse one of the largest available cross-institutional cohorts of patients with anal cancer treated with chemoradiotherapy. The analysis aims to provide information on current international clinical practice outcomes and may aid the personalisation and design of future anal cancer clinical trials through contributing to a better understanding of patient risk stratification.

Abstract Background Lung cancer treatment decisions are typically made among clinical experts in a multidisciplinary tumour board (MTB) based on clinical data and guidelines. The rise of artificial intelligence and cultural shifts towards patient autonomy are changing the nature of clinical decision‐making towards personalized treatments. This can be supported by clinical decision support systems (CDSSs) that generate personalized treatment information as a basis for shared decision‐making (SDM). Little is known about lung cancer patients' treatment decisions and the potential for SDM supported by CDSSs. The aim of this study is to understand to what extent SDM is done in current practice and what clinicians need to improve it. Objective To explore (1) the extent to which patient preferences are taken into consideration in non‐small‐cell lung cancer (NSCLC) treatment decisions; (2) clinician perspectives on using CDSSs to support SDM. Design Mixed methods study consisting of a retrospective cohort study on patient deviation from MTB advice and reasons for deviation, qualitative interviews with lung cancer specialists and observations of MTB discussions and patient consultations. Setting and Participants NSCLC patients (N = 257) treated at a single radiotherapy clinic and nine lung cancer specialists from six Dutch clinics. Results We found a 10.9% (n = 28) deviation rate from MTB advice; 50% (n = 14) were due to patient preference, of which 85.7% (n = 12) chose a less intensive treatment than MTB advice. Current MTB recommendations are based on clinician experience, guidelines and patients' performance status. Most specialists (n = 7) were receptive towards CDSSs but cited barriers, such as lack of trust, lack of validation studies and time. CDSSs were considered valuable during MTB discussions rather than in consultations. Conclusion Lung cancer decisions are heavily influenced by clinical guidelines and experience, yet many patients prefer less intensive treatments. CDSSs can support SDM by presenting the harms and benefits of different treatment options rather than giving single treatment advice. External validation of CDSSs should be prioritized. Patient or Public Contribution This study did not involve patients or the public explicitly; however, the study design was informed by prior interviews with volunteers of a cancer patient advocacy group. The study objectives and data collection were supported by Dutch health care insurer CZ for a project titled ‘My Best Treatment’ that improves patient‐centeredness and the lung cancer patient pathway in the Netherlands.

BackgroundThe role of artificial intelligence and radiomics in prediction model development in cancer has been increasing every passing day. Cervical cancer is the 4th most common cancer in women worldwide, contributing to 6.5% of all cancer types. The treatment outcome of cervical cancer patients varies and individualized prediction of disease outcome is of paramount importance.PurposeThe purpose of this study is to develop and validate the digital signature for 5-year overall survival prediction in cervical cancer using robust CT radiomic and clinical features.Materials and MethodsPretreatment clinical features and CT radiomic features of 68 patients, who were treated with chemoradiation therapy in our hospital, were used in this study. Radiomic features were extracted using an in-house developed python script and pyradiomic package. Clinical features were selected by the recursive feature elimination technique. Whereas radiomic feature selection was performed using a multi-step process i.e., step-1: only robust radiomic features were selected based on our previous study, step-2: a hierarchical clustering was performed to eliminate feature redundancy, and step-3: recursive feature elimination was performed to select the best features for prediction model development. Four machine algorithms i.e., Logistic regression (LR), Random Forest (RF), Support vector classifier (SVC), and Gradient boosting classifier (GBC), were used to develop 24 models (six models using each algorithm) using clinical, radiomic and combined features. Models were compared based on the prediction score in the internal validation.ResultsThe average prediction accuracy was found to be 0.65 (95% CI: 0.60–0.70), 0.72 (95% CI: 0.63–0.81), and 0.77 (95% CI: 0.72–0.82) for clinical, radiomic, and combined models developed using four prediction algorithms respectively. The average prediction accuracy was found to be 0.69 (95% CI: 0.62–0.76), 0.79 (95% CI: 0.72–0.86), 0.71 (95% CI: 0.62–0.80), and 0.72 (95% CI: 0.66–0.78) for LR, RF, SVC and GBC models developed on three datasets respectively.ConclusionOur study shows the promising predictive performance of a robust radiomic signature to predict 5-year overall survival in cervical cancer patients.

Background and purpose: Radiomics models trained with limited single institution data are often not reproducible and generalisable. We developed radiomics models that predict loco-regional recurrence within two years of radiotherapy with private and public datasets and their combinations, to simulate small and multi-institutional studies and study the responsiveness of the models to feature selection, machine learning algorithms, centre-effect harmonization and increased dataset sizes. Materials and methods: 562 patients histologically confirmed and treated for locally advanced head-and-neck cancer (LA-HNC) from two public and two private datasets; one private dataset exclusively reserved for validation. Clinical contours of primary tumours were not recontoured and were used for Pyradiomics based feature extraction. ComBat harmonization was applied, and LASSO-Logistic Regression (LR) and Support Vector Machine (SVM) models were built. 95% confidence interval (CI) of 1000 bootstrapped area-under-the-Receiver-operating-curves (AUC) provided predictive performance. Responsiveness of the models’ performance to the choice of feature selection methods, ComBat harmonization, machine learning classifier, single and pooled data was evaluated. Results: LASSO and SelectKBest selected 14 and 16 features, respectively; three were overlapping. Without ComBat, the LR and SVM models for three institutional data showed AUCs (CI) of 0.513 (0.481–0.559) and 0.632 (0.586–0.665), respectively. Performances following ComBat revealed AUCs of 0.559 (0.536–0.590) and 0.662 (0.606–0.690), respectively. Compared to single cohort AUCs (0.562–0.629), SVM models from pooled data performed significantly better at AUC = 0.680. Conclusions: Multi-institutional retrospective data accentuates the existing variabilities that affect radiomics. Carefully designed prospective, multi-institutional studies and data sharing are necessary for clinically relevant head-and-neck cancer prognostication models.

IntroductionUrinary incontinence (UI) is a common side effect of prostate cancer treatment, but in clinical practice, it is difficult to predict. Machine learning (ML) models have shown promising results in predicting outcomes, yet the lack of transparency in complex models known as “black-box” has made clinicians wary of relying on them in sensitive decisions. Therefore, finding a balance between accuracy and explainability is crucial for the implementation of ML models. The aim of this study was to employ three different ML classifiers to predict the probability of experiencing UI in men with localized prostate cancer 1-year and 2-year after treatment and compare their accuracy and explainability. MethodsWe used the ProZIB dataset from the Netherlands Comprehensive Cancer Organization (Integraal Kankercentrum Nederland; IKNL) which contained clinical, demographic, and PROM data of 964 patients from 65 Dutch hospitals. Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) algorithms were applied to predict (in)continence after prostate cancer treatment. ResultsAll models have been externally validated according to the TRIPOD Type 3 guidelines and their performance was assessed by accuracy, sensitivity, specificity, and AUC. While all three models demonstrated similar performance, LR showed slightly better accuracy than RF and SVM in predicting the risk of UI one year after prostate cancer treatment, achieving an accuracy of 0.75, a sensitivity of 0.82, and an AUC of 0.79. All models for the 2-year outcome performed poorly in the validation set, with an accuracy of 0.6 for LR, 0.65 for RF, and 0.54 for SVM. ConclusionThe outcomes of our study demonstrate the promise of using non-black box models, such as LR, to assist clinicians in recognizing high-risk patients and making informed treatment choices. The coefficients of the LR model show the importance of each feature in predicting results, and the generated nomogram provides an accessible illustration of how each feature impacts the predicted outcome. Additionally, the model’s simplicity and interpretability make it a more appropriate option in scenarios where comprehending the model’s predictions is essential.

Abstract Circulating leukocytes are an important part of the immune system. The aim of this work is to explore the role of preoperative circulating leukocytes in serous ovarian carcinoma and investigate whether they can be used to predict survival prognosis. Routine blood test results and clinical information of patients with serous ovarian carcinoma were retrospectively collected. And to predict survival according to the blood routine test result the decision tree method was applied to build a machine learning model. The results showed that the number of preoperative white blood cells (p = 0.022), monocytes (p

Background and Purpose: Tumor recurrence, a characteristic of malignant tumors, is the biggest concern for rectal cancer survivors. The epidemiology of the disease calls for a pressing need to improve healthcare quality and patient outcomes. Prediction models such as Bayesian networks, which can probabilistically reason under uncertainty, could assist caregivers with patient management. However, some concerns are associated with the standard approaches to developing these structures in medicine. Therefore, this study aims to compare Bayesian network structures that stem from these two techniques. Materials and Methods: A retrospective analysis was performed on 6754 locally advanced rectal cancer (LARC) patients enrolled in 14 international clinical trials. Local tumor recurrence at 2, 3, and 5-years was defined as the endpoints of interest. Five rectal cancer treating physicians from three countries elicited the expert structure. The algorithmic structure was inferred from the data with the hill-climbing algorithm. Structural performance was assessed with calibration plots and area under the curve values. Results: The area under the curve for the expert structure on the training and validation data was above 0.9 and 0.8, respectively, for all the time points. However, the algorithmic structure had superior predictive performance over the expert structure for all time points of interest. Conclusion: We have developed and internally validated a Bayesian networks structure from experts’ opinions, which can predict the risk of a LARC patient developing a tumor recurrence at 2, 3, and 5 years. Our result shows that the algorithmic-based structures are more performant and less interpretable than expert-based structures.

BackgroundNatural language processing (NLP) is thought to be a promising solution to extract and store concepts from free text in a structured manner for data mining purposes. This is also true for radiology reports, which still consist mostly of free text. Accurate and complete reports are very important for clinical decision support, for instance, in oncological staging. As such, NLP can be a tool to structure the content of the radiology report, thereby increasing the report’s value. ObjectiveThis study describes the implementation and validation of an N-stage classifier for pulmonary oncology. It is based on free-text radiological chest computed tomography reports according to the tumor, node, and metastasis (TNM) classification, which has been added to the already existing T-stage classifier to create a combined TN-stage classifier. MethodsSpaCy, PyContextNLP, and regular expressions were used for proper information extraction, after additional rules were set to accurately extract N-stage. ResultsThe overall TN-stage classifier accuracy scores were 0.84 and 0.85, respectively, for the training (N=95) and validation (N=97) sets. This is comparable to the outcomes of the T-stage classifier (0.87-0.92). ConclusionsThis study shows that NLP has potential in classifying pulmonary oncology from free-text radiological reports according to the TNM classification system as both the T- and N-stages can be extracted with high accuracy.

PurposeArtificial intelligence applications in radiation oncology have been the focus of study in the last decade. The introduction of automated and intelligent solutions for routine clinical tasks, such as treatment planning and quality assurance, has the potential to increase safety and efficiency of radiotherapy. In this work, we present a multi-institutional study across three different institutions internationally on a Bayesian network (BN)-based initial plan review assistive tool that alerts radiotherapy professionals for potential erroneous or suboptimal treatment plans.MethodsClinical data were collected from the oncology information systems in three institutes in Europe (Maastro clinic - 8753 patients treated between 2012 and 2020) and the United States of America (University of Vermont Medical Center [UVMMC] - 2733 patients, University of Washington [UW] - 6180 patients, treated between 2018 and 2021). We trained the BN model to detect potential errors in radiotherapy treatment plans using different combinations of institutional data and performed single-site and cross-site validation with simulated plans with embedded errors. The simulated errors consisted of three different categories: i) patient setup, ii) treatment planning and iii) prescription. We also compared the strategy of using only diagnostic parameters or all variables as evidence for the BN. We evaluated the model performance utilizing the area under the receiver-operating characteristic curve (AUC).ResultsThe best network performance was observed when the BN model is trained and validated using the dataset in the same center. In particular, the testing and validation using UVMMC data has achieved an AUC of 0.92 with all parameters used as evidence. In cross-validation studies, we observed that the BN model performed better when it was trained and validated in institutes with similar technology and treatment protocols (for instance, when testing on UVMMC data, the model trained on UW data achieved an AUC of 0.84, compared with an AUC of 0.64 for the model trained on Maastro data). Also, combining training data from larger clinics (UW and Maastro clinic) and using it on smaller clinics (UVMMC) leads to satisfactory performance with an AUC of 0.85. Lastly, we found that in general the BN model performed better when all variables are considered as evidence.ConclusionWe have developed and validated a Bayesian network model to assist initial treatment plan review using multi-institutional data with different technology and clinical practices. The model has shown good performance even when trained on data from clinics with divergent profiles, suggesting that the model is able to adapt to different data distributions.

While the 10-year survival rate for localized prostate cancer patients is very good (>98%), side effects of treatment may limit quality of life significantly. Erectile dysfunction (ED) is a common burden associated with increasing age as well as prostate cancer treatment. Although many studies have investigated the factors affecting erectile dysfunction (ED) after prostate cancer treatment, only limited studies have investigated whether ED can be predicted before the start of treatment. The advent of machine learning (ML) based prediction tools in oncology offers a promising approach to improve the accuracy of prediction and quality of care. Predicting ED may help aid shared decision-making by making the advantages and disadvantages of certain treatments clear, so that a tailored treatment for an individual patient can be chosen. This study aimed to predict ED at 1-year and 2-year post-diagnosis based on patient demographics, clinical data and patient-reported outcomes (PROMs) measured at diagnosis. We used a subset of the ProZIB dataset collected by the Netherlands Comprehensive Cancer Organization (Integraal Kankercentrum Nederland; IKNL) that contained information on 964 localized prostate cancer cases from 69 Dutch hospitals for model training and external validation. Two models were generated using a logistic regression algorithm coupled with Recursive Feature Elimination (RFE). The first predicted ED 1 year post-diagnosis and required 10 pre-treatment variables; the second predicted ED 2 years post-diagnosis with 9 pre-treatment variables. The validation AUCs were 0.84 and 0.81 for 1 year and 2 years post-diagnosis respectively. To immediately allow patients and clinicians to use these models in the clinical decision-making process, nomograms were generated. In conclusion, we successfully developed and validated two models that predicted ED in patients with localized prostate cancer. These models will allow physicians and patients alike to make informed evidence-based decisions about the most suitable treatment with quality of life in mind.

Background: To maximize the likelihood of positive outcome in non-small-cell lung cancer (NSCLC) survivors, potential benefits of treatment modalities have to be weighed against the possibilities of damage to normal tissues, such as the heart. High-quality data-driven evidence regarding appropriate risk stratification strategies is still scarce. The aim of this review is to summarize and appraise available prediction models for treatment-induced cardiac events in patients with NSCLC. Methods: A systematic search of MEDLINE was performed using a Boolean combination of appropriate truncation and indexing terms related to “NSCLC”, “prediction models”, “cardiac toxicity”, and “treatment modalities”. The following exclusion criteria were applied: sample-size of less than 100, no significant predictors in multivariate analysis, lack of model specifications, and case-mix studies. The generic inverse variance method was used to pool the summary effect estimate for each predictor. The quality of the papers was assessed using the Prediction model Risk Of Bias Assessment Tool. Results: Of the 3,056 papers retrieved, 28 prediction models were identified, including seven for (chemo-)radiotherapy, one for immunotherapy, and 20 for surgical resection. Forty-one distinct predictors were entered in the prediction models. The pooled effect estimate of the mean heart dose (HR = 1.06, 95%CI:1.04–1.08) and history of cardiovascular diseases (HR = 3.1, 95%CI:1.8–5.36) were shown to significantly increase the risk of developing late cardiac toxicity after (chemo-)radiotherapy. Summary estimates of age (OR = 1.17, 95%CI:1.06–1.29), male gender (OR = 1.61, 95%CI:1.4–1.85), and advanced stage (OR = 1.34, 95%CI:1.06–1.69) were significantly associated with higher risk of acute cardiac events after surgery. Risk of bias varied across studies, but analysis was the most concerning domain where none of the studies were judged to be low risk. Conclusion: This review highlights the need for a robust prediction model which can inform patients and clinicians about expected treatment-induced heart damage. Identified clues suggest incorporation of detailed cardiac metrics (substructures’ volumes and doses).

With the development of society and the advancement of science and technology, artificial intelligence has also emerged as the times require. In computer vision, deep learning based on convolutional neural networks(CNN) achieves state-of-the-art performance. However, the massive data requirements of deep learning have long been a pain point in the field, especially in the medical field, where it is often difficult (and sometimes impossible) to obtain enough training data for some specific tasks. To overcome insufficient and unbalanced data, in this paper, we focus on the generation and balance of data on radiation-induced pneumonia, an extremely rare disease with a low incidence. As a result, datasets on this disease are extremely sparse and unevenly distributed. To address the above problems, the predecessors’ method is often to use generative models to generate data as a complement of the fewer samples to achieve a balanced distribution of data samples. Among various generative models, CycleGAN is widely used in medical image generation due to its cycle consistency to achieve style migration without changing the basic content. However, the original CycleGAN method has many shortcomings, especially in Few-shot and the data unevenly distributed, its performance will be greatly reduced. To make the generated data samples retain the original structure and have finer and clearer details, this paper proposes a mask-based self-attention CycleGAN data augmentation method. A self-attention branch is added to the generator and two different loss functions named Self-Attention Loss and Mask Loss are designed. To stabilize the training process, spectral normalization is introduced to improve the discriminator and MS-SSIM and L1 joint loss are used to improve the original identity loss. The ResNet18 is used to complete classification experiments on the radiation-induced pneumonia dataset and the COVID-19 dataset respectively. Four classification performance indicators: the area under the ROC curve (AUC), Accuracy (ACC), Sensitivity (SEN), and Specificity (SPE) are calculated to verify the effectiveness and generalization of our method. Compared with the original CycleGAN and traditional data augmentation, the classifier trained by data augmentation using our method has outstanding performance in multiple classification indicators and has better classification performance. Experimental results show that our method solves the problem of insufficient samples and data imbalance in the pneumonia dataset by generating high-quality pneumonia images. Code is available at https://github.com/ngfufdrdh/CycleGAN-lung.

Cancer registries collect multisource data and provide valuable information that can lead to unique research opportunities. In the Netherlands, a registry and model-based approach (MBA) are used for the selection of patients that are eligible for proton therapy. We collected baseline characteristics including demographic, clinical, tumour and treatment information. These data were transformed into a machine readable format using the FAIR (Findable, Accessible, Interoperable, Reusable) data principles and resulted in a knowledge graph with baseline characteristics of proton therapy patients. With this approach, we enable the possibility of linking external data sources and optimal flexibility to easily adapt the data structure of the existing knowledge graph to the needs of the clinic.

Radiomics is referred to as quantitative imaging of biomarkers used for clinical outcome prognosis or tumor characterization. In order to bridge radiomics and its clinical application, we aimed to build an integrated solution of radiomics extraction with an open-source Picture Archiving and Communication System (PACS). The integrated SQLite4Radiomics software was tested in three different imaging modalities and its performance was benchmarked in lung cancer open datasets RIDER and MMD with median extraction time of 10.7 (percentiles 25–75: 8.9–18.7) seconds per ROI in three different configurations.

Background and Purpose: Although quantitative image biomarkers (radiomics) show promising value for cancer diagnosis, prognosis, and treatment assessment, these biomarkers still lack reproducibility. In this systematic review, we aimed to assess the progress in radiomics reproducibility and repeatability in the recent years. Methods and materials: Four hundred fifty-one abstracts were retrieved according to our search pattern criteria, with the publication dates ranging from 2017/05/01 to 2020/12/01. Each abstract including the keywords was independently screened by four observers. Forty-two full-text articles were selected for further analysis. Patient population data, radiomic feature classes, feature extraction software, image preprocessing, and reproducibility results were extracted from each article. To support the community with a standardized reporting strategy, we propose a specific reporting checklist to evaluate the feasibility to reproduce each study. Results: Many studies continue to under-report essential reproducibility information: all but one clinical and all but two phantom studies missed to report at least one important item reporting image acquisition. The studies included in this review indicate that all radiomic features are sensitive to image acquisition, reconstruction, tumor segmentation, and interpolation. However, the amount of sensitivity is feature dependent, for instance, textural features were, in general, less robust than statistical features. Conclusions: Radiomics repeatability, reproducibility, and reporting quality can substantially be improved regarding feature extraction software and settings, image preprocessing and acquisition, cutoff values for stable feature selection. Our proposed radiomics reporting checklist can serve to simplify and improve the reporting and, eventually, guarantee the possibility to fully replicate and validate radiomic studies.

PurposeThe purpose of the study was to build an AI model with selected preoperative clinical features to further improve the accuracy of the assessment of benign and malignant breast nodules.MethodsPatients who underwent ultrasound, strain elastography, and S-Detect before ultrasound-guided biopsy or surgical excision were enrolled. The diagnosis model was built using a logistic regression model. The diagnostic performances of different models were evaluated and compared.ResultsA total of 179 lesions (101 benign and 78 malignant) were included. The whole dataset consisted of a training set (145 patients) and an independent test set (34 patients). The AI models constructed based on clinical features, ultrasound features, and strain elastography to predict and classify benign and malignant breast nodules had ROC AUCs of 0.87, 0.81, and 0.79 in the test set. The AUCs of the sonographer and S-Detect were 0.75 and 0.82, respectively, in the test set. The AUC of the combined AI model with the best performance was 0.89 in the test set. The combined AI model showed a better specificity of 0.92 than the other models. The sonographer’s assessment showed better sensitivity (0.97 in the test set).ConclusionThe combined AI model could improve the preoperative identification of benign and malignant breast masses and may reduce unnecessary breast biopsies.

Digital health is a promising tool to support people with an elevated risk for atherosclerotic cardiovascular disease (ASCVD) and patients with an established disease to improve cardiovascular outcomes. Many digital health initiatives have been developed and employed. However, barriers to their large-scale implementation have remained. This paper focuses on these barriers and presents solutions as proposed by the Dutch CARRIER (ie, Coronary ARtery disease: Risk estimations and Interventions for prevention and EaRly detection) consortium. We will focus in 4 sections on the following: (1) the development process of an eHealth solution that will include design thinking and cocreation with relevant stakeholders; (2) the modeling approach for two clinical prediction models (CPMs) to identify people at risk of developing ASCVD and to guide interventions; (3) description of a federated data infrastructure to train the CPMs and to provide the eHealth solution with relevant data; and (4) discussion of an ethical and legal framework for responsible data handling in health care. The Dutch CARRIER consortium consists of a collaboration between experts in the fields of eHealth development, ASCVD, public health, big data, as well as ethics and law. The consortium focuses on reducing the burden of ASCVD. We believe the future of health care is data driven and supported by digital health. Therefore, we hope that our research will not only facilitate CARRIER consortium but may also facilitate other future health care initiatives.

LARC is managed by multimodal treatments whose intensity can be highly modulated. In this context, we need surrogate endpoints to help predict long-term outcomes and better personalize treatments. A previous study identified 2yDFS as a stronger predictor of OS than pCR in LARC patients undergoing neoadjuvant RT. The aim of this pooled analysis was to assess the role of pCR and 2yDFS as surrogate endpoints for OS in a larger cohort. The pooled and subgroup analyses were performed on large rectal cancer randomized trial cohorts who received long-course RT. Our analysis focused on the evaluation of OS in relation to the pCR and 2-year disease status. A total of 4600 patients were analyzed. Four groups were identified according to intermediate outcomes: 12% had both pCR and 2yDFS (the better); 67% achieved 2yDFS but not pCR (the good); 1% had pCR but not 2yDFS; and 20% had neither pCR nor 2yDFS (the bad). The pCR and 2yDFS were favorably associated with OS in the univariate analysis, and 2yDFS maintained a statistically significant association in the multivariate analysis independently of the pCR status. The combination of the pCR and 2yDFS results in a strong predictor of OS, whereas failure to achieve 2yDFS carries a poor prognosis regardless of the pCR status. This new stratification of LARC patients could help design predictive models where the combination of 2yDFS and pCR should be employed as the primary outcome.

PurposeTo build a machine learning model to predict histology (type I and type II), stage, and grade preoperatively for endometrial carcinoma to quickly give a diagnosis and assist in improving the accuracy of the diagnosis, which can help patients receive timely, appropriate, and effective treatment.Materials and MethodsThis study used a retrospective database of preoperative examinations (tumor markers, imaging, diagnostic curettage, etc.) in patients with endometrial carcinoma. Three algorithms (random forest, logistic regression, and deep neural network) were used to build models. The AUC and accuracy were calculated. Furthermore, the performance of machine learning models, doctors’ prediction, and doctors with the assistance of models were compared.ResultsA total of 329 patients were included in this study with 16 features (age, BMI, stage, grade, histology, etc.). A random forest algorithm had the highest AUC and Accuracy. For histology prediction, AUC and accuracy was 0.69 (95% CI=0.67-0.70) and 0.81 (95%CI=0.79-0.82). For stage they were 0.66 (95% CI=0.64-0.69) and 0.63 (95% CI=0.61-0.65) and for differentiation grade 0.64 (95% CI=0.63-0.65) and 0.43 (95% CI=0.41-0.44). The average accuracy of doctors for histology, stage, and grade was 0.86 (with AI) and 0.79 (without AI), 0.64 and 0.53, 0.5 and 0.45, respectively. The accuracy of doctors’ prediction with AI was higher than that of Random Forest alone and doctors’ prediction without AI.ConclusionA random forest model can predict histology, stage, and grade of endometrial cancer preoperatively and can help doctors in obtaining a better diagnosis and predictive results.

Tumor grading is an essential factor for cancer staging and survival prognostication. The widely used the WHO grading system defines the histological grade of CRC adenocarcinoma based on the density of glandular formation on whole-slide images (WSIs). We developed a fully automated approach for stratifying colorectal cancer (CRC) patients’ risk of mortality directly from histology WSI relating to gland formation. A tissue classifier was trained to categorize regions on WSI as glands, stroma, immune cells, background, and other tissues. A gland formation classifier was trained on expert annotations to categorize regions as different degrees of tumor gland formation versus normal tissues. The glandular formation density can thus be estimated using the aforementioned tissue categorization and gland formation information. This estimation was called a semi-quantitative gland formation ratio (SGFR), which was used as a prognostic factor in survival analysis. We evaluated gland formation percentage and validated it by comparing it against the WHO cutoff point. Survival data and gland formation maps were then used to train a spatial pyramid pooling survival network (SPPSN) as a deep survival model. We compared the survival prediction performance of estimated gland formation percentage and the SPPSN deep survival grade and found that the deep survival grade had improved discrimination. A univariable Cox model for survival yielded moderate discrimination with SGFR (c-index 0.62) and deep survival grade (c-index 0.64) in an independent institutional test set. Deep survival grade also showed better discrimination performance in multivariable Cox regression. The deep survival grade significantly increased the c-index of the baseline Cox model in both validation set and external test set, but the inclusion of SGFR can only improve the Cox model less in external test and is unable to improve the Cox model in the validation set.

Research exploring CycleGAN-based synthetic image generation has recently accelerated in the medical community due to its ability to leverage unpaired images effectively. However, a commonly established drawback of the CycleGAN, the introduction of artifacts in generated images, makes it unreliable for medical imaging use cases. In an attempt to address this, we explore the effect of structure losses on the CycleGAN and propose a generalized frequency-based loss that aims at preserving the content in the frequency domain. We apply this loss to the use-case of cone-beam computed tomography (CBCT) translation to computed tomography (CT)-like quality. Synthetic CT (sCT) images generated from our methods are compared against baseline CycleGAN along with other existing structure losses proposed in the literature. Our methods (MAE: 85.5, MSE: 20433, NMSE: 0.026, PSNR: 30.02, SSIM: 0.935) quantitatively and qualitatively improve over the baseline CycleGAN (MAE: 88.8, MSE: 24244, NMSE: 0.03, PSNR: 29.37, SSIM: 0.935) across all investigated metrics and are more robust than existing methods. Furthermore, no observable artifacts or loss in image quality were observed. Finally, we demonstrated that sCTs generated using our methods have superior performance compared to the original CBCT images on selected downstream tasks.

Abstract The difference in incidence of oral cavity cancer (OCC) between Taiwan and the Netherlands is striking. Different risk factors and treatment expertise may result in survival differences between the two countries. However due to regulatory restrictions, patient-level analyses of combined data from the Netherlands and Taiwan are infeasible. We implemented a software infrastructure for federated analyses on data from multiple organisations. We included 41,633‬ patients with single-tumour OCC between 2004 and 2016, undergoing surgery, from the Taiwan Cancer Registry and Netherlands Cancer Registry. Federated Cox Proportional Hazard was used to analyse associations between patient and tumour characteristics, country, treatment and hospital volume with survival. Five factors showed differential effects on survival of OCC patients in the Netherlands and Taiwan: age at diagnosis, stage, grade, treatment and hospital volume. The risk of death for OCC patients younger than 60 years, with advanced stage, higher grade or receiving adjuvant therapy after surgery was lower in the Netherlands than in Taiwan; but patients older than 70 years, with early stage, lower grade and receiving surgery alone in the Netherlands were at higher risk of death than those in Taiwan. The mortality risk of OCC in Taiwanese patients treated in hospitals with higher hospital volume (≥ 50 surgeries per year) was lower than in Dutch patients. We conducted analyses without exchanging patient-level information, overcoming barriers for sharing privacy sensitive information. The outcomes of patients treated in the Netherlands and Taiwan were slightly different after controlling for other prognostic factors.

PurposeAlthough an increasing body of literature suggests a relationship between brain irradiation and deterioration of neurocognitive function, it remains as the standard therapeutic and prophylactic modality in patients with brain tumors. This review was aimed to abstract and evaluate the prediction models for radiation-induced neurocognitive decline in patients with primary or secondary brain tumors.MethodsMEDLINE was searched on October 31, 2021 for publications containing relevant truncation and MeSH terms related to “radiotherapy,” “brain,” “prediction model,” and “neurocognitive impairments.” Risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool.ResultsOf 3,580 studies reviewed, 23 prediction models were identified. Age, tumor location, education level, baseline neurocognitive score, and radiation dose to the hippocampus were the most common predictors in the models. The Hopkins verbal learning (n = 7) and the trail making tests (n = 4) were the most frequent outcome assessment tools. All studies used regression (n = 14 linear, n = 8 logistic, and n = 4 Cox) as machine learning method. All models were judged to have a high risk of bias mainly due to issues in the analysis.ConclusionExisting models have limited quality and are at high risk of bias. Following recommendations are outlined in this review to improve future models: developing cognitive assessment instruments taking into account the peculiar traits of the different brain tumors and radiation modalities; adherence to model development and validation guidelines; careful choice of candidate predictors according to the literature and domain expert consensus; and considering radiation dose to brain substructures as they can provide important information on specific neurocognitive impairments.

This study aimed to systematically review the use of clinical prediction models (CPMs) in personalised lifestyle interventions for the prevention of cardiovascular disease. We searched PubMed and PsycInfo for articles describing relevant studies published up to August 1, 2021. These were supplemented with items retrieved via screening references of citations and cited by references. In total, 32 studies were included. Nineteen different CPMs were used to guide the intervention. Most frequently, a version of the Framingham risk score was used. The CPM was used to inform the intensity of the intervention in five studies (16 %), and the intervention’s type in 31 studies (97 %). The CPM was supplemented with relative risk estimates for additional risk factors in three studies (9 %), and relative risk estimates for intervention effects in four (13 %). In addition to the estimated risk, the personalisation was determined using criteria based on univariable risk factors in 18 studies (56 %), a lifestyle score in three (9 %), and a physical examination index in one (3 %). We noted insufficient detail in reporting regarding the CPM’s use in 20 studies (63 %). In 15 studies (47 %), the primary outcome was a CPM estimate. A statistically significant effect favouring the intervention to the comparator arm was reported in four out of eight analyses (50 %), and a statistically significant improvement compared to baseline in five out of seven analyses (71 %). Due to the design of the included studies, the effect of the use of CPMs is still unclear. Therefore, we see a need for future research.

Purpose: Radiomics are quantitative features extracted from medical images. Many radiomic features depend not only on tumor properties, but also on non-tumor related factors such as scanner signal-to-noise ratio (SNR), reconstruction kernel and other image acquisition settings. This causes undesirable value variations in the features and reduces the performance of prediction models. In this paper, we investigate whether we can use phantom measurements to characterize and correct for the scanner SNR dependence. Methods: We used a phantom with 17 regions of interest (ROI) to investigate the influence of different SNR values. CT scans were acquired with 9 different exposure settings. We developed an additive correction model to reduce scanner SNR influence. Results: Sixty-two of 92 radiomic features showed high variance due to the scanner SNR. Of these 62 features, 47 showed at least a factor 2 significant standard deviation reduction by using the additive correction model. We assessed the clinical relevance of radiomics instability by using a 221 NSCLC patient cohort measured with the same scanner. Conclusions: Phantom measurements show that roughly two third of the radiomic features depend on the exposure setting of the scanner. The dependence can be modeled and corrected significantly reducing the variation in feature values with at least a factor of 2. More complex models will likely increase the correctability. Scanner SNR correction will result in more reliable radiomics predictions in NSCLC. Keywords: Radiomics, Reproducibility, Predictive modeling, Phantoms

Transparency, openness, and reproducibility are important characteristics in scientific publishing. Although many researchers embrace these characteristics, data sharing has yet to become common practice. Nevertheless, data sharing is becoming an increasingly important topic among societies, publishers, researchers, patient advocates, and funders, especially as it pertains to data from clinical trials. In response, ASTRO developed a data policy and guide to best practices for authors submitting to its journals. ASTRO's data sharing policy is that authors should indicate, in data availability statements, if the data are being shared and if so, how the data may be accessed.

PurposeExternal Beam Radiotherapy (EBRT) techniques dramatically changed over the years. This may have affected the risk of radiation-induced second primary cancers (SPC), due to increased irradiated low dose volumes and scatter radiation. We investigated whether patterns of SPC after EBRT have changed over the years in prostate cancer (PCa) survivors.Materials and MethodsPCa survivors diagnosed between 1990-2014 were selected from the Netherlands Cancer Registry. Patients treated with EBRT were divided in three time periods, representing 2-dimensional Radiotherapy (RT), 3-dimensional conformal RT (3D-CRT), and the advanced RT (AdvRT) era. Standardized incidence ratios (SIR) and absolute excess risks (AER) were calculated to estimate relative and excess absolute SPC risks. Sub-hazard ratios (sHRs) were calculated to compare SPC rates between the EBRT and prostatectomy cohort. SPCs were categorized by subsite and anatomic region.ResultsPCa survivors who received EBRT had an increased risk of developing a solid SPC (SIR=1.08; 1.05-1.11), especially in patients aged

This study aims to analyze the relationship between the available variables and treatment compliance in elderly cancer patients treated with radiotherapy and to establish a decision tree model to guide caregivers in their decision-making process. For this purpose, 456 patients over 74 years of age who received radiotherapy between 2005 and 2017 were included in this retrospective analysis. The outcome of interest was radiotherapy compliance, determined by whether patients completed their scheduled radiotherapy treatment (compliance means they completed their treatment and noncompliance means they did not). A bootstrap (B = 400) technique was implemented to select the best tuning parameters to establish the decision tree. The developed decision tree uses patient status, the Charlson comorbidity index, the Eastern Cooperative Oncology Group Performance scale, age, sex, cancer type, health insurance status, radiotherapy aim, and fractionation type (conventional fractionation versus hypofractionation) to distinguish between compliant and noncompliant patients. The decision tree’s mean area under the curve and 95% confidence interval was 0.71 (0.66–0.77). Although external validation is needed to determine the decision tree’s clinical usefulness, its discriminating ability was moderate and it could serve as an aid for caregivers to select the optimal treatment for elderly cancer patients.