External Validation of Radiation-Induced Dyspnea Models on Esophageal Cancer Radiotherapy Patients

Benchmarking machine learning approaches to predict radiation-induced toxicities in lung cancer patients

Background and purpose

Radiation-induced toxicities are common adverse events in lung cancer (LC) patients undergoing radiotherapy (RT). An accurate prediction of these adverse events might facilitate an informed and shared decision-making process between patient and radiation oncologist with a clearer view of life-balance implications in treatment choices. This work provides a benchmark of machine learning (ML) approaches to predict radiation-induced toxicities in LC patients built upon a real-world health dataset based on a generalizable methodology for their implementation and external validation.

Materials and Methods

Ten feature selection (FS) methods were combined with five ML-based classifiers to predict six RT-induced toxicities (acute esophagitis, acute cough, acute dyspnea, acute pneumonitis, chronic dyspnea, and chronic pneumonitis). A real-world health dataset (RWHD) built from 875 consecutive LC patients was used to train and validate the resulting 300 predictive models. Internal and external accuracy was calculated in terms of AUC per clinical endpoint, FS method, and ML-based classifier under analysis.

Results

Best performing predictive models obtained per clinical endpoint achieved comparable performances to methods from state-of-the-art at internal validation (AUC ≥ 0.81 in all cases) and at external validation (AUC ≥ 0.73 in 5 out of 6 cases).

Conclusion

A benchmark of 300 different ML-based approaches has been tested against a RWHD achieving satisfactory results following a generalizable methodology. The outcomes suggest potential relationships between underrecognized clinical factors and the onset of acute esophagitis or chronic dyspnea, thus demonstrating the potential that ML-based approaches have to generate novel data-driven hypotheses in the field.

Pirfenidone for the prevention of radiation-induced lung injury in patients with locally advanced oesophageal squamous cell carcinoma: a protocol for a randomised controlled trial

INTRODUCTION

Radiation-induced lung injury (RILI) is one of the most clinically-challenging toxicities and dose-limiting factors during and/or after thoracic radiation therapy for oesophageal squamous cell carcinoma (ESCC). With limited effective protective drugs against RILI, the main strategy to reduce the injury is strict adherence to dose-volume restrictions of normal lungs. RILI can manifest as acute radiation pneumonitis with cellular injury, cytokine release and cytokine recruitment to inflammatory infiltrate, and subsequent chronic radiation pulmonary fibrosis. Pirfenidone inhibits the production of inflammatory cytokines, scavenges-free radicals and reduces hydroxyproline and collagen formation. Hence, pirfenidone might be a promising drug for RILI prevention. This study aims to evaluate the efficacy and safety of pirfenidone in preventing RILI in patients with locally advanced ESCC receiving chemoradiotherapy.

METHODS AND ANALYSIS

This study is designed as a randomised, placebo-controlled, double-blinded, single-centre phase 2 trial and will explore whether the addition of pirfenidone during concurrent chemoradiation therapy (CCRT) could prevent RILI in patients with locally advanced ESCC unsuitable for surgery. Eligible participants will be randomised at 1:1 to pirfenidone and placebo groups. The primary endpoint is the incidence of grade >2 RILI. Secondary endpoints include the incidence of any grade other than grade >2 RILI, time to RILI occurrence, changes in pulmonary function after CCRT, completion rate of CCRT, disease-free survival and overall survival. The follow-up period will be 1 year. In case the results meet the primary endpoint of this trial, a phase 3 multicentre trial with a larger sample size will be required to substantiate the evidence of the benefit of pirfenidone in RILI prevention.

ETHICS AND DISSEMINATION

This study was approved by the Ethics Committee of Fujian Union Hospital (No. 2021YF001-02). The findings of the trial will be disseminated through peer-reviewed journals, and national and international conference presentations.

TRIAL REGISTRATION NUMBER

ChiCTR2100043032.

Automatic Tumor Grading on Colorectal Cancer Whole-Slide Images: Semi-Quantitative Gland Formation Percentage and New Indicator Exploration

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.

Impact of Regional Lymph Node Irradiation on Reducing Lymph Node Recurrence in Esophageal Cancer Patients

BACKGROUND/AIM

To evaluate the preventive effects of regional lymph node irradiation on lymph node recurrence in esophageal cancer (EC).

PATIENTS AND METHODS

The study included 289 patients who received definitive radiotherapy for EC. The regional lymph node area of group 1 was determined as the area with the highest probability of lymph node metastasis and group 2 was determined as the area with the next highest probability of lymph node metastasis depending on the primary site of EC.

RESULTS

The patients in whom group 2 was completely included in the irradiated field had a significantly lower rate of recurrence of regional lymph node metastasis than those in whom group 2 was not or insufficiently included (p=0.0337). There was no significant difference in overall survival (p=0.4627) or disease-specific survival (p=0.6174) between the two groups.

CONCLUSION

Regional lymph node irradiation did not have survival-prolonging effects but significantly reduced regional lymph node recurrence.

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.

Building an Artificial Intelligence Laboratory Based on Real World Data: The Experience of Gemelli Generator

The problem of transforming Real World Data into Real World Evidence is becoming increasingly important in the frameworks of Digital Health and Personalized Medicine, especially with the availability of modern algorithms of Artificial Intelligence high computing power, and large storage facilities.Even where Real World Data are well maintained in a hospital data warehouse and are made available for research purposes, many aspects need to be addressed to build an effective architecture enabling researchers to extract knowledge from data.We describe the first year of activity at Gemelli Generator RWD, the challenges we faced and the solutions we put in place to build a Real World Data laboratory at the service of patients and health researchers. Three classes of services are available today: retrospective analysis of existing patient data for descriptive and clustering purposes; automation of knowledge extraction, ranging from text mining, patient selection for trials, to generation of new research hypotheses; and finally the creation of Decision Support Systems, with the integration of data from the hospital data warehouse, apps, and Internet of Things.

Risk prediction models for the development of oral-mucosal pressure injuries in intubated patients in intensive care units: A prospective observational study

PURPOSE

Oral-mucosal pressure injury (PI) is the most commonly encountered medical device-related PIs. This study was performed to identify risk factors and construct a risk prediction model for oral-mucosal PI development in intubated patients in the intensive care unit.

METHODS

The study design was prospective, observational with medical record review. The inclusion criteria stipulated that 1) participants should be > 18 years of age, 2) there should be ETT use with holding methods including adhesive tape, gauze tying, and commercial devices. Data of 194 patient-days were analysed. The identification and validation of risk model development was performed using SPSS and the SciKit learn platform.

RESULTS

The risk prediction logistic models were composed of three factors (bite-block/airway, commercial ETT holder, and corticosteroid use) for lower oral-mucosal PI development and four factors (commercial ETT holder, vasopressor use, haematocrit, and serum albumin level) for upper oral-mucosal PI development among 10 significant input variables. The sensitivity and specificity for lower oral-mucosal PI development were 85.2% and 76.0%, respectively, and those for upper oral-mucosal PI development were 60.0% and 89.1%, respectively. Based on the results of the machine learning, the upper oral-mucosal PI development model had an accuracy of 79%, F1 score of 88%, precision of 86%, and recall of 91%.

CONCLUSIONS

The development of lower oral-mucosal PIs is affected by immobility-related factors and corticosteroid use, and that of upper oral-mucosal PIs by undernutrition-related factors and ETT holder use. The high sensitivities of the two logit models comprise important minimum data for positively predicting oral-mucosal PIs.

FAIR-compliant clinical, radiomics and DICOM metadata of RIDER, interobserver, Lung1 and head-Neck1 TCIA collections

Purpose

One of the most frequently cited radiomics investigations showed that features automatically extracted from routine clinical images could be used in prognostic modeling. These images have been made publicly accessible via The Cancer Imaging Archive (TCIA). There have been numerous requests for additional explanatory metadata on the following datasets — RIDER, Interobserver, Lung1, and Head–Neck1. To support repeatability, reproducibility, generalizability, and transparency in radiomics research, we publish the subjects’ clinical data, extracted radiomics features, and digital imaging and communications in medicine (DICOM) headers of these four datasets with descriptive metadata, in order to be more compliant with findable, accessible, interoperable, and reusable (FAIR) data management principles.

Acquisition and validation methods

Overall survival time intervals were updated using a national citizens registry after internal ethics board approval. Spatial offsets of the primary gross tumor volume (GTV) regions of interest (ROIs) associated with the Lung1 CT series were improved on the TCIA. GTV radiomics features were extracted using the open‐source Ontology‐Guided Radiomics Analysis Workflow (O‐RAW). We reshaped the output of O‐RAW to map features and extraction settings to the latest version of Radiomics Ontology, so as to be consistent with the Image Biomarker Standardization Initiative (IBSI). Digital imaging and communications in medicine metadata was extracted using a research version of Semantic DICOM (SOHARD, GmbH, Fuerth; Germany). Subjects’ clinical data were described with metadata using the Radiation Oncology Ontology. All of the above were published in Resource Descriptor Format (RDF), that is, triples. Example SPARQL queries are shared with the reader to use on the online triples archive, which are intended to illustrate how to exploit this data submission.

Data format

The accumulated RDF data are publicly accessible through a SPARQL endpoint where the triples are archived. The endpoint is remotely queried through a graph database web application at http://sparql.cancerdata.org. SPARQL queries are intrinsically federated, such that we can efficiently cross‐reference clinical, DICOM, and radiomics data within a single query, while being agnostic to the original data format and coding system. The federated queries work in the same way even if the RDF data were partitioned across multiple servers and dispersed physical locations.

Potential applications

The public availability of these data resources is intended to support radiomics features replication, repeatability, and reproducibility studies by the academic community. The example SPARQL queries may be freely used and modified by readers depending on their research question. Data interoperability and reusability are supported by referencing existing public ontologies. The RDF data are readily findable and accessible through the aforementioned link. Scripts used to create the RDF are made available at a code repository linked to this submission: https://gitlab.com/UM‐CDS/FAIR‐compliant_clinical_radiomics_and_DICOM_metadata.