Data harmonization and federated learning for multi-cohort dementia research using the OMOP common data model: A Netherlands consortium of dementia cohorts case study.

BACKGROUND: Establishing collaborations between cohort studies has been fundamental for progress in health research. However, such collaborations are hampered by heterogeneous data representations across cohorts and legal constraints to data sharing. The first arises from a lack of consensus in standards of data collection and representation across cohort studies and is usually tackled by applying data harmonization processes. The second is increasingly important due to raised awareness for privacy protection and stricter regulations, such as the GDPR. Federated learning has emerged as a privacy-preserving alternative to transferring data between institutions through analyzing data in a decentralized manner. METHODS: In this study, we set up a federated learning infrastructure for a consortium of nine Dutch cohorts with appropriate data available to the etiology of dementia, including an extract, transform, and load (ETL) pipeline for data harmonization. Additionally, we assessed the challenges of transforming and standardizing cohort data using the Observational Medical Outcomes Partnership (OMOP) common data model (CDM) and evaluated our tool in one of the cohorts employing federated algorithms. RESULTS: We successfully applied our ETL tool and observed a complete coverage of the cohorts' data by the OMOP CDM. The OMOP CDM facilitated the data representation and standardization, but we identified limitations for cohort-specific data fields and in the scope of the vocabularies available. Specific challenges arise in a multi-cohort federated collaboration due to technical constraints in local environments, data heterogeneity, and lack of direct access to the data. CONCLUSION: In this article, we describe the solutions to these challenges and limitations encountered in our study. Our study shows the potential of federated learning as a privacy-preserving solution for multi-cohort studies that enhance reproducibility and reuse of both data and analyses.

Colorectal cancer health and care quality indicators in a federated setting using the Personal Health Train.

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.

Operationalizing and digitizing person-centered daily functioning: a case for functionomics.

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.

Frequency-Domain-Based Structure Losses for CycleGAN-Based Cone-Beam Computed Tomography Translation.

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.

External Validation of Robust Radiomic Signature to Predict 2-Year Overall Survival in Non-Small-Cell Lung Cancer.

Lung cancer is the second most fatal disease worldwide. In the last few years, radiomics is being explored to develop prediction models for various clinical endpoints in lung cancer. However, the robustness of radiomic features is under question and has been identified as one of the roadblocks in the implementation of a radiomic-based prediction model in the clinic. Many past studies have suggested identifying the robust radiomic feature to develop a prediction model. In our earlier study, we identified robust radiomic features for prediction model development. The objective of this study was to develop and validate the robust radiomic signatures for predicting 2-year overall survival in non-small cell lung cancer (NSCLC). This retrospective study included a cohort of 300 stage I-IV NSCLC patients. Institutional 200 patients' data were included for training and internal validation and 100 patients' data from The Cancer Image Archive (TCIA) open-source image repository for external validation. Radiomic features were extracted from the CT images of both cohorts. The feature selection was performed using hierarchical clustering, a Chi-squared test, and recursive feature elimination (RFE). In total, six prediction models were developed using random forest (RF-Model-O, RF-Model-B), gradient boosting (GB-Model-O, GB-Model-B), and support vector(SV-Model-O, SV-Model-B) classifiers to predict 2-year overall survival (OS) on original data as well as balanced data. Model validation was performed using 10-fold cross-validation, internal validation, and external validation. Using a multistep feature selection method, the overall top 10 features were chosen. On internal validation, the two random forest models (RF-Model-O, RF-Model-B) displayed the highest accuracy; their scores on the original and balanced datasets were 0.81 and 0.77 respectively. During external validation, both the random forest models' accuracy was 0.68. In our study, robust radiomic features showed promising predictive performance to predict 2-year overall survival in NSCLC.

Clinical Concept-Based Radiology Reports Classification Pipeline for Lung Carcinoma.

Rising incidence and mortality of cancer have led to an incremental amount of research in the field. To learn from preexisting data, it has become important to capture maximum information related to disease type, stage, treatment, and outcomes. Medical imaging reports are rich in this kind of information but are only present as free text. The extraction of information from such unstructured text reports is labor-intensive. The use of Natural Language Processing (NLP) tools to extract information from radiology reports can make it less time-consuming as well as more effective. In this study, we have developed and compared different models for the classification of lung carcinoma reports using clinical concepts. This study was approved by the institutional ethics committee as a retrospective study with a waiver of informed consent. A clinical concept-based classification pipeline for lung carcinoma radiology reports was developed using rule-based as well as machine learning models and compared. The machine learning models used were XGBoost and two more deep learning model architectures with bidirectional long short-term neural networks. A corpus consisting of 1700 radiology reports including computed tomography (CT) and positron emission tomography/computed tomography (PET/CT) reports were used for development and testing. Five hundred one radiology reports from MIMIC-III Clinical Database version 1.4 was used for external validation. The pipeline achieved an overall F1 score of 0.94 on the internal set and 0.74 on external validation with the rule-based algorithm using expert input giving the best performance. Among the machine learning models, the Bi-LSTM_dropout model performed better than the ML model using XGBoost and the Bi-LSTM_simple model on internal set, whereas on external validation, the Bi-LSTM_simple model performed relatively better than other 2. This pipeline can be used for clinical concept-based classification of radiology reports related to lung carcinoma from a huge corpus and also for automated annotation of these reports.

Methodological quality of machine learning-based quantitative imaging analysis studies in esophageal cancer: a systematic review of clinical outcome prediction after concurrent chemoradiotherapy.

PURPOSE: Studies based on machine learning-based quantitative imaging techniques have gained much interest in cancer research. The aim of this review is to critically appraise the existing machine learning-based quantitative imaging analysis studies predicting outcomes of esophageal cancer after concurrent chemoradiotherapy in accordance with PRISMA guidelines. METHODS: A systematic review was conducted in accordance with PRISMA guidelines. The citation search was performed via PubMed and Embase Ovid databases for literature published before April 2021. From each full-text article, study characteristics and model information were summarized. We proposed an appraisal matrix with 13 items to assess the methodological quality of each study based on recommended best-practices pertaining to quality. RESULTS: Out of 244 identified records, 37 studies met the inclusion criteria. Study endpoints included prognosis, treatment response, and toxicity after concurrent chemoradiotherapy with reported discrimination metrics in validation datasets between 0.6 and 0.9, with wide variation in quality. A total of 30 studies published within the last 5 years were evaluated for methodological quality and we found 11 studies with at least 6 "good" item ratings. CONCLUSION: A substantial number of studies lacked prospective registration, external validation, model calibration, and support for use in clinic. To further improve the predictive power of machine learning-based models and translate into real clinical applications in cancer research, appropriate methodologies, prospective registration, and multi-institution validation are recommended.

Systematic review of radiomic biomarkers for predicting immune checkpoint inhibitor treatment outcomes.

BACKGROUND: Systemic therapy agents targeting immune checkpoint inhibitors have been approved for use since 2011. This type of therapy aims to trigger a patient's immune response to attack tumor cells, rather than acting against the tumor directly. Radiomics is an automated method of medical image analysis that is now being actively investigated for predictive markers of treatment response in immunotherapy. OBJECTIVE: To conduct an early systematic review determining the current status of radiomic features as potential predictive markers of immunotherapy response. Provide a detailed critical appraisal of methodological quality of models, as this informs the degree of confidence about current reports of model performance. In addition, to offer some recommendations for future studies that could establish robust evidence for radiomic features as immunotherapy response markers. METHOD: A PubMed citation search was conducted for publications up to and including April 2020, followed by full-text screening. A total of seven articles meeting the eligibility criteria were examined in detail for study characteristics, model information and methodological quality. The review was conducted in the Cochrane style but has not been prospectively registered. Results are reported following Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA) guidelines. RESULTS: A total of seven studies were examined in detail, comprising non-small cell lung cancer, metastatic melanoma and a diverse assortment of solid tumors. Methodological robustness of reviewed studies varied greatly. Principal shortcomings were lack of prospective registration, and deficiencies in feature selection and dimensionality reduction, model calibration, clinical utility and external validation. A few studies with overall moderate to good methodological quality were identified. These results suggest that current state-of-the-art performance of radiomics in regards to discrimination (area under the curve or concordance index) is in the vicinity of 0.7, but the very small number of studies to date prevents any conclusive remarks to be made. We recommended future improvements in regards to prospective study registration, clinical utility, methodological procedure and data sharing. CONCLUSIONS: Radiomics has a potentially significant role for predicting immunotherapy response. Additional multi-institutional studies with robust methodological underpinning and repeated external validations are required to establish the (added) value of radiomics within the pantheon of clinical tools for decision-making in immunotherapy.

Clinician perspectives on clinical decision support systems in lung cancer: Implications for shared decision-making.

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.

Improving reproducibility and performance of radiomics in low-dose CT using cycle GANs.

BACKGROUND: As a means to extract biomarkers from medical imaging, radiomics has attracted increased attention from researchers. However, reproducibility and performance of radiomics in low-dose CT scans are still poor, mostly due to noise. Deep learning generative models can be used to denoise these images and in turn improve radiomics' reproducibility and performance. However, most generative models are trained on paired data, which can be difficult or impossible to collect. PURPOSE: In this article, we investigate the possibility of denoising low-dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets. METHODS AND MATERIALS: Two cycle GANs were trained: (1) from paired data, by simulating low-dose CTs (i.e., introducing noise) from high-dose CTs and (2) from unpaired real low dose CTs. To accelerate convergence, during GAN training, a slice-paired training strategy was introduced. The trained GANs were applied to three scenarios: (1) improving radiomics reproducibility in simulated low-dose CT images and (2) same-day repeat low dose CTs (RIDER dataset), and (3) improving radiomics performance in survival prediction. Cycle GAN results were compared with a conditional GAN (CGAN) and an encoder-decoder network (EDN) trained on simulated paired data. RESULTS: The cycle GAN trained on simulated data improved concordance correlation coefficients (CCC) of radiomic features from 0.87 (95%CI, [0.833,0.901]) to 0.93 (95%CI, [0.916,0.949]) on simulated noise CT and from 0.89 (95%CI, [0.881,0.914]) to 0.92 (95%CI, [0.908,0.937]) on the RIDER dataset, as well improving the area under the receiver operating characteristic curve (AUC) of survival prediction from 0.52 (95%CI, [0.511,0.538]) to 0.59 (95%CI, [0.578,0.602]). The cycle GAN trained on real data increased the CCCs of features in RIDER to 0.95 (95%CI, [0.933,0.961]) and the AUC of survival prediction to 0.58 (95%CI, [0.576,0.596]). CONCLUSION: The results show that cycle GANs trained on both simulated and real data can improve radiomics' reproducibility and performance in low-dose CT and achieve similar results compared to CGANs and EDNs.

Exploring Associations of Preoperative Physical Performance With Postoperative Outcomes After Lumbar Spinal Fusion: A Machine Learning Approach.

OBJECTIVE: To explore the association between preoperative physical performance with short- and long-term postoperative outcomes in patients undergoing lumbar spinal fusion (LSF). DESIGN: Retrospective cohort. SETTING: University hospital. PARTICIPANTS: Seventy-seven patients (N=77) undergoing elective LSF were preoperatively screened on patient demographics, patient-reported outcome measures, and physical performance measures (movement control, back muscle endurance strength and extensor strength, aerobic capacity, flexibility). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Associations between preoperative variables and inpatient functional recovery, hospital length of stay (LOS), and 1- to 2-year postoperative pain reduction were explored using random forest analyses assessing the relative influence of the variable on the outcome. RESULTS: Aerobic capacity was associated with fast functional recovery <4 days and prolonged functional recovery >5 days (median z scores=7.1 and 12.0). Flexibility (median z score=4.3) and back muscle endurance strength (median z score=7.8) were associated with fast functional recovery <4 days. Maximum back extensor strength was associated with prolonged functional recovery >5 days (median z score=8.6). Flexibility (median z score=5.1) and back muscle endurance strength (median z score=13.5) were associated with short LOS <5 days. Aerobic capacity (median z score=8.7) was associated with prolonged LOS >7 days. Maximum back extensor strength (median z score=3.8) was associated with 1- to 2-year postoperative pain reduction and aerobic capacity (median z score=2.8) was tentative. CONCLUSIONS: Physical performance measures were associated with both short- and long-term outcomes after LSF. Adding these measures to prediction models predicting outcomes after LSF may increase their accuracy.

Deep Learning Automated Segmentation for Muscle and Adipose Tissue from Abdominal Computed Tomography in Polytrauma Patients.

Manual segmentation of muscle and adipose compartments from computed tomography (CT) axial images is a potential bottleneck in early rapid detection and quantification of sarcopenia. A prototype deep learning neural network was trained on a multi-center collection of 3413 abdominal cancer surgery subjects to automatically segment truncal muscle, subcutaneous adipose tissue and visceral adipose tissue at the L3 lumbar vertebral level. Segmentations were externally tested on 233 polytrauma subjects. Although after severe trauma abdominal CT scans are quickly and robustly delivered, with often motion or scatter artefacts, incomplete vertebral bodies or arms that influence image quality, the concordance was generally very good for the body composition indices of Skeletal Muscle Radiation Attenuation (SMRA) (Concordance Correlation Coefficient (CCC) = 0.92), Visceral Adipose Tissue index (VATI) (CCC = 0.99) and Subcutaneous Adipose Tissue Index (SATI) (CCC = 0.99). In conclusion, this article showed an automated and accurate segmentation system to segment the cross-sectional muscle and adipose area L3 lumbar spine level on abdominal CT. Future perspectives will include fine-tuning the algorithm and minimizing the outliers.

Characterisation and classification of oligometastatic disease: a European Society for Radiotherapy and Oncology and European Organisation for Research and Treatment of Cancer consensus recommendation.

Oligometastatic disease has been proposed as an intermediate state between localised and systemically metastasised disease. In the absence of randomised phase 3 trials, early clinical studies show improved survival when radical local therapy is added to standard systemic therapy for oligometastatic disease. However, since no biomarker for the identification of patients with true oligometastatic disease is clinically available, the diagnosis of oligometastatic disease is based solely on imaging findings. A small number of metastases on imaging could represent different clinical scenarios, which are associated with different prognoses and might require different treatment strategies. 20 international experts including 19 members of the European Society for Radiotherapy and Oncology and European Organisation for Research and Treatment of Cancer OligoCare project developed a comprehensive system for characterisation and classification of oligometastatic disease. We first did a systematic review of the literature to identify inclusion and exclusion criteria of prospective interventional oligometastatic disease clinical trials. Next, we used a Delphi consensus process to select a total of 17 oligometastatic disease characterisation factors that should be assessed in all patients treated with radical local therapy for oligometastatic disease, both within and outside of clinical trials. Using a second round of the Delphi method, we established a decision tree for oligometastatic disease classification together with a nomenclature. We agreed oligometastatic disease as the overall umbrella term. A history of polymetastatic disease before diagnosis of oligometastatic disease was used as the criterion to differentiate between induced oligometastatic disease (previous history of polymetastatic disease) and genuine oligometastatic disease (no history of polymetastatic disease). We further subclassified genuine oligometastatic disease into repeat oligometastatic disease (previous history of oligometastatic disease) and de-novo oligometastatic disease (first time diagnosis of oligometastatic disease). In de-novo oligometastatic disease, we differentiated between synchronous and metachronous oligometastatic disease. We did a final subclassification into oligorecurrence, oligoprogression, and oligopersistence, considering whether oligometastatic disease is diagnosed during a treatment-free interval or during active systemic therapy and whether or not an oligometastatic lesion is progressing on current imaging. This oligometastatic disease classification and nomenclature needs to be prospectively evaluated by the OligoCare study.

Natural Language Processing in Dutch Free Text Radiology Reports: Challenges in a Small Language Area Staging Pulmonary Oncology.

Reports are the standard way of communication between the radiologist and the referring clinician. Efforts are made to improve this communication by, for instance, introducing standardization and structured reporting. Natural Language Processing (NLP) is another promising tool which can improve and enhance the radiological report by processing free text. NLP as such adds structure to the report and exposes the information, which in turn can be used for further analysis. This paper describes pre-processing and processing steps and highlights important challenges to overcome in order to successfully implement a free text mining algorithm using NLP tools and machine learning in a small language area, like Dutch. A rule-based algorithm was constructed to classify T-stage of pulmonary oncology from the original free text radiological report, based on the items tumor size, presence and involvement according to the 8th TNM classification system. PyContextNLP, spaCy and regular expressions were used as tools to extract the correct information and process the free text. Overall accuracy of the algorithm for evaluating T-stage was 0,83 in the training set and 0,87 in the validation set, which shows that the approach in this pilot study is promising. Future research with larger datasets and external validation is needed to be able to introduce more machine learning approaches and perhaps to reduce required input efforts of domain-specific knowledge. However, a hybrid NLP approach will probably achieve the best results.

Development and validation of a patient decision aid for prostate Cancer therapy: from paternalistic towards participative shared decision making.

BACKGROUND: Patient decision aids (PDAs) can support the treatment decision making process and empower patients to take a proactive role in their treatment pathway while using a shared decision-making (SDM) approach making participatory medicine possible. The aim of this study was to develop a PDA for prostate cancer that is accurate and user-friendly. METHODS: We followed a user-centered design process consisting of five rounds of semi-structured interviews and usability surveys with topics such as informational/decisional needs of users and requirements for PDAs. Our user-base consisted of 8 urologists, 4 radiation oncologists, 2 oncology nurses, 8 general practitioners, 19 former prostate cancer patients, 4 usability experts and 11 healthy volunteers. RESULTS: Informational needs for patients centered on three key factors: treatment experience, post-treatment quality of life, and the impact of side effects. Patients and clinicians valued a PDA that presents balanced information on these factors through simple understandable language and visual aids. Usability questionnaires revealed that patients were more satisfied overall with the PDA than clinicians; however, both groups had concerns that the PDA might lengthen consultation times (42 and 41%, respectively). The PDA is accessible on http://beslissamen.nl/ . CONCLUSIONS: User-centered design provided valuable insights into PDA requirements but challenges in integrating diverse perspectives as clinicians focus on clinical outcomes while patients also consider quality of life. Nevertheless, it is crucial to involve a broad base of clinical users in order to better understand the decision-making process and to develop a PDA that is accurate, usable, and acceptable.

A prediction model for early death in non-small cell lung cancer patients following curative-intent chemoradiotherapy.

BACKGROUND: Early death after a treatment can be seen as a therapeutic failure. Accurate prediction of patients at risk for early mortality is crucial to avoid unnecessary harm and reducing costs. The goal of our work is two-fold: first, to evaluate the performance of a previously published model for early death in our cohorts. Second, to develop a prognostic model for early death prediction following radiotherapy. MATERIAL AND METHODS: Patients with NSCLC treated with chemoradiotherapy or radiotherapy alone were included in this study. Four different cohorts from different countries were available for this work (N = 1540). The previous model used age, gender, performance status, tumor stage, income deprivation, no previous treatment given (yes/no) and body mass index to make predictions. A random forest model was developed by learning on the Maastro cohort (N = 698). The new model used performance status, age, gender, T and N stage, total tumor volume (cc), total tumor dose (Gy) and chemotherapy timing (none, sequential, concurrent) to make predictions. Death within 4 months of receiving the first radiotherapy fraction was used as the outcome. RESULTS: Early death rates ranged from 6 to 11% within the four cohorts. The previous model performed with AUC values ranging from 0.54 to 0.64 on the validation cohorts. Our newly developed model had improved AUC values ranging from 0.62 to 0.71 on the validation cohorts. CONCLUSIONS: Using advanced machine learning methods and informative variables, prognostic models for early mortality can be developed. Development of accurate prognostic tools for early mortality is important to inform patients about treatment options and optimize care.

Fractal-based radiomic approach to predict complete pathological response after chemo-radiotherapy in rectal cancer.

The aim of this study was to propose a methodology to investigate the tumour heterogeneity and evaluate its ability to predict pathologically complete response (pCR) after chemo-radiotherapy (CRT) in locally advanced rectal cancer (LARC). This approach consisted in normalising the pixel intensities of the tumour and identifying the different sub-regions using an intensity-based thresholding. The spatial organisation of these subpopulations was quantified using the fractal dimension (FD). This approach was implemented in a radiomic workflow and applied to 198 T2-weighted pre-treatment magnetic resonance (MR) images of LARC patients. Three types of features were extracted from the gross tumour volume (GTV): morphological, statistical and fractal features. Feature selection was performed using the Wilcoxon test and a logistic regression model was calculated to predict the pCR probability after CRT. The model was elaborated considering the patients treated in two institutions: Fondazione Policlinico Universitario "Agostino Gemelli" of Rome (173 cases, training set) and University Medical Centre of Maastricht (25 cases, validation set). The results obtained showed that the fractal parameters of the subpopulations have the highest performance in predicting pCR. The predictive model elaborated had an area under the curve (AUC) equal to 0.77 ± 0.07. The model reliability was confirmed by the validation set (AUC = 0.79 ± 0.09). This study suggests that the fractal analysis can play an important role in radiomics, providing valuable information not only about the GTV structure, but also about its inner subpopulations.

Standardized data collection to build prediction models in oncology: a prototype for rectal cancer.

The advances in diagnostic and treatment technology are responsible for a remarkable transformation in the internal medicine concept with the establishment of a new idea of personalized medicine. Inter- and intra-patient tumor heterogeneity and the clinical outcome and/or treatment's toxicity's complexity, justify the effort to develop predictive models from decision support systems. However, the number of evaluated variables coming from multiple disciplines: oncology, computer science, bioinformatics, statistics, genomics, imaging, among others could be very large thus making traditional statistical analysis difficult to exploit. Automated data-mining processes and machine learning approaches can be a solution to organize the massive amount of data, trying to unravel important interaction. The purpose of this paper is to describe the strategy to collect and analyze data properly for decision support and introduce the concept of an 'umbrella protocol' within the framework of 'rapid learning healthcare'.

Modern clinical research: How rapid learning health care and cohort multiple randomised clinical trials complement traditional evidence based medicine.

BACKGROUND: Trials are vital in informing routine clinical care; however, current designs have major deficiencies. An overview of the various challenges that face modern clinical research and the methods that can be exploited to solve these challenges, in the context of personalised cancer treatment in the 21st century is provided. AIM: The purpose of this manuscript, without intending to be comprehensive, is to spark thought whilst presenting and discussing two important and complementary alternatives to traditional evidence-based medicine, specifically rapid learning health care and cohort multiple randomised controlled trial design. Rapid learning health care is an approach that proposes to extract and apply knowledge from routine clinical care data rather than exclusively depending on clinical trial evidence, (please watch the animation: http://youtu.be/ZDJFOxpwqEA). The cohort multiple randomised controlled trial design is a pragmatic method which has been proposed to help overcome the weaknesses of conventional randomised trials, taking advantage of the standardised follow-up approaches more and more used in routine patient care. This approach is particularly useful when the new intervention is a priori attractive for the patient (i.e. proton therapy, patient decision aids or expensive medications), when the outcomes are easily collected, and when there is no need of a placebo arm. DISCUSSION: Truly personalised cancer treatment is the goal in modern radiotherapy. However, personalised cancer treatment is also an immense challenge. The vast variety of both cancer patients and treatment options makes it extremely difficult to determine which decisions are optimal for the individual patient. Nevertheless, rapid learning health care and cohort multiple randomised controlled trial design are two approaches (among others) that can help meet this challenge.