Integrating Multimodal Radiation Therapy Data into i2b2

Opportunities and Obstacles to the Development of Health Data Warehouses in Hospitals in France: The Recent Experience of Comprehensive Cancer Centers

Big Data and Artificial Intelligence can profoundly transform medical practices, particularly in oncology. Comprehensive Cancer Centers have a major role to play in this revolution. With the purpose of advancing our knowledge and accelerating cancer research, it is urgent to make this pool of data usable through the development of robust and effective data warehouses. Through the recent experience of Comprehensive Cancer Centers in France, this article shows that, while the use of hospital data warehouses can be a source of progress by taking into account multisource, multidomain and multiscale data for the benefit of knowledge and patients, it nevertheless raises technical, organizational and legal issues that still need to be addressed. The objectives of this article are threefold: 1. to provide insight on public health stakes of development in Comprehensive Cancer Centers to manage cancer patients comprehensively; 2. to set out a challenge of structuring the data from within them; 3. to outline the legal issues of implementation to carry out real-world evidence studies. To meet objective 1, this article firstly proposed a discussion on the relevance of an integrated approach to manage cancer and the formidable tool that data warehouses represent to achieve this. To address objective 2, we carried out a literature review to screen the articles published in PubMed and Google Scholar through the end of 2022 on the use of data warehouses in French Comprehensive Cancer Centers. Seven publications dealing specifically with the issue of data structuring were selected. To achieve objective 3, we presented and commented on the main aspects of French and European legislation and regulations in the field of health data, hospital data warehouses and real-world evidence.

Efficient and Reliable Data Extraction in Radiation Oncology using Python Programming Language: A Pilot Study

Background and Purpose

In recent years, data science approaches have entered health-care systems such as radiology, pathology, and radiation oncology. In our pilot study, we developed an automated data mining approach to extract data from a treatment planning system (TPS) with high speed, maximum accuracy, and little human interaction. We compared the amount of time required for manual data extraction versus the automated data mining technique.

Materials and Methods

A Python programming script was created to extract specified parameters and features pertaining to patients and treatment (a total of 25 features) from TPS. We successfully implemented automation in data mining, utilizing the application programming interface environment provided by the external beam radiation therapy equipment provider for the whole group of patients who were accepted for treatment.

Results

This in-house Python-based script extracted selected features for 427 patients in 0.28 ± 0.03 min with 100% accuracy at an astonishing rate of 0.04 s/plan. Comparatively, manual extraction of 25 parameters took an average of 4.5 ± 0.33 min/plan, along with associated transcriptional and transpositional errors and missing data information. This new approach turned out to be 6850 times faster than the conventional approach. Manual feature extraction time increased by a factor of nearly 2.5 if we doubled the number of features extracted, whereas for the Python script, it increased by a factor of just 1.15.

Conclusion

We conclude that our in-house developed Python script can extract plan data from TPS at a far higher speed (>6000 times) and with the best possible accuracy compared to manual data extraction.

A knowledge graph representation of baseline characteristics for the Dutch proton therapy research registry

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.

Noncurated Data Lead to Misinterpretation of Treatment Outcomes in Patients With Prostate Cancer After Salvage or Palliative Radiotherapy

PURPOSE

Clinical data warehouses (cDWHs) and cancer registry databases have enabled researchers to conduct clinical analytics with structured electronic health record data. However, these secondary electronic health record sources are often limited in scope because they do not capture the clinical information needed to understand complex clinical questions. Thus, we evaluated the effect of additional curation of data.

MATERIALS AND METHODS

Clinical data sets of 149 patients with prostate cancer with biochemical recurrence after radical prostatectomy treated with salvage or palliative radiotherapy between 2008 and 2017 from our institutional cDWH and Gießener Tumor Documentation System (GTDS) were linked (data warehouse [DWH] population) for analyzing treatment outcomes. The linked data sets were manually curated (manual postprocessing [MPP], eg, incorporate data from established urologists). The primary outcomes were the impact on data quality of treatment outcomes and the time spent on data curation.

RESULTS

We obtained significantly more information on disease progression and patient survival (nonsignificant) when using curated data; the biochemical progression-free survival rate at 5 years for the DWH and DWH plus MPP populations was 63% v 30% ( P ≤ .001) and the overall survival rate was 84% v 81% ( P = .479), respectively. The median deviation of completeness and the median concordance of clinical data values were 21.47% (range, 55.38%-100%) and 95.00% (range, 63.40%-100%), respectively. We spent 121 hours, 42 minutes on data curation, with most time required for laboratory values, accounting, for a total of 45 hours, 20 minutes (37.26%).

CONCLUSION

Our analysis indicates that time-to-event outcomes for patients with prostate cancer cannot be extracted using secondary data sources (cDWH plus GTDS) only. Outcomes data differed between the electronic data (DWH) and the second manual extraction (DWH plus MPP) because of a lack of follow-up data. When using such unique database resources, only baseline characteristics can reliably be extracted.

[Basis and perspectives of artificial intelligence in radiation therapy]

Artificial intelligence is a highly polysemic term. In computer science, with the objective of being able to solve totally new problems in new contexts, artificial intelligence includes connectionism (neural networks) for learning and logics for reasoning. Artificial intelligence algorithms mimic tasks normally requiring human intelligence, like deduction, induction, and abduction. All apply to radiation oncology. Combined with radiomics, neural networks have obtained good results in image classification, natural language processing, phenotyping based on electronic health records, and adaptive radiation therapy. General adversial networks have been tested to generate synthetic data. Logics based systems have been developed for providing formal domain ontologies, supporting clinical decision and checking consistency of the systems. Artificial intelligence must integrate both deep learning and logic approaches to perform complex tasks and go beyond the so-called narrow artificial intelligence that is tailored to perform some highly specialized task. Combined together with mechanistic models, artificial intelligence has the potential to provide new tools such as digital twins for precision oncology.

Deep Learning and Radiomics predict complete response after neo-adjuvant chemoradiation for locally advanced rectal cancer

Treatment of locally advanced rectal cancer involves chemoradiation, followed by total mesorectum excision. Complete response after chemoradiation is an accurate surrogate for long-term local control. Predicting complete response from pre-treatment features could represent a major step towards conservative treatment. Patients with a T2-4 N0-1 rectal adenocarcinoma treated between June 2010 and October 2016 with neo-adjuvant chemoradiation from three academic institutions were included. All clinical and treatment data was integrated in our clinical data warehouse, from which we extracted the features. Radiomics features were extracted from the tumor volume from the treatment planning CT Scan. A Deep Neural Network (DNN) was created to predict complete response, as a methodological proof-of-principle. The results were compared to a baseline Linear Regression model using only the TNM stage as a predictor and a second model created with Support Vector Machine on the same features used in the DNN. Ninety-five patients were included in the final analysis. There were 49 males (52%) and 46 females (48%). Median tumour size was 48 mm (15-130). Twenty-two patients (23%) had pathologic complete response after chemoradiation. One thousand six hundred eighty-three radiomics features were extracted. The DNN predicted complete response with an 80% accuracy, which was better than the Linear Regression model (69.5%) and the SVM model (71.58%). Our model correctly predicted complete response after neo-adjuvant rectal chemoradiotherapy in 80% of the patients of this multicenter cohort. Our results may help to identify patients who would benefit from a conservative treatment, rather than a radical resection.