Dataset Information

A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy.

ABSTRACT: PURPOSE:Individualization of therapeutic outcomes in NSCLC radiotherapy is likely to be compromised by the lack of proper balance of biophysical factors affecting both tumor local control (LC) and side effects such as radiation pneumonitis (RP), which are likely to be intertwined. Here, we compare the performance of separate and joint outcomes predictions for response-adapted personalized treatment planning. METHODS:A total of 118 NSCLC patients treated on prospective protocols with 32 cases of local progression and 20 cases of RP grade 2 or higher (RP2) were studied. Sixty-eight patients with 297 features before and during radiotherapy were used for discovery and 50 patients were reserved for independent testing. A multiobjective Bayesian network (MO-BN) approach was developed to identify important features for joint LC/RP2 prediction using extended Markov blankets as inputs to develop a BN predictive structure. Cross-validation (CV) was used to guide the MO-BN structure learning. Area under the free-response receiver operating characteristic (AU-FROC) curve was used to evaluate joint prediction performance. RESULTS:Important features including single nucleotide polymorphisms (SNPs), micro RNAs, pretreatment cytokines, pretreatment PET radiomics together with lung and tumor gEUDs were selected and their biophysical inter-relationships with radiation outcomes (LC and RP2) were identified in a pretreatment MO-BN. The joint LC/RP2 prediction yielded an AU-FROC of 0.80 (95% CI: 0.70-0.86) upon internal CV. This improved to 0.85 (0.75-0.91) with additional two SNPs, changes in one cytokine and two radiomics PET image features through the course of radiotherapy in a during-treatment MO-BN. This MO-BN model outperformed combined single-objective Bayesian networks (SO-BNs) during-treatment [0.78 (0.67-0.84)]. AU-FROC values in the evaluation of the MO-BN and individual SO-BNs on the testing dataset were 0.77 and 0.68 for pretreatment, and 0.79 and 0.71 for during-treatment, respectively. CONCLUSIONS:MO-BNs can reveal possible biophysical cross-talks between competing radiotherapy clinical endpoints. The prediction is improved by providing additional during-treatment information. The developed MO-BNs can be an important component of decision support systems for personalized response-adapted radiotherapy.

SUBMITTER: Luo Y

PROVIDER: S-EPMC6279602 | biostudies-literature | 2018 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy.

Luo Yi Y McShan Daniel L DL Matuszak Martha M MM Ray Dipankar D Lawrence Theodore S TS Jolly Shruti S Kong Feng-Ming FM Ten Haken Randall K RK El Naqa Issam I

Medical physics 20180604

<h4>Purpose</h4>Individualization of therapeutic outcomes in NSCLC radiotherapy is likely to be compromised by the lack of proper balance of biophysical factors affecting both tumor local control (LC) and side effects such as radiation pneumonitis (RP), which are likely to be intertwined. Here, we compare the performance of separate and joint outcomes predictions for response-adapted personalized treatment planning.<h4>Methods</h4>A total of 118 NSCLC patients treated on prospective protocols wi ...[more]

PMID: 29862533

Similar Datasets

Project description:BackgroundRadiation pneumonitis is a critical pulmonary toxicity after irradiation of the lung. Macrolides including clarithromycin (CAM) are antibiotics. They also have immunomodulatory properties and are used to treat respiratory inflammatory diseases. Radiation pneumonitis has similar pathology to them. Adverse reactions to macrolides are few and self-limited. We thus administered CAM to patients with high-risk factors for radiation pneumonitis, and retrospectively investigated whether CAM mitigated radiation pneumonitis following stereotactic body radiotherapy (SBRT).MethodsAmong consecutive patients treated with SBRT, we retrospectively examined lung cancer patients treated with a total dose of 40-60 Gy in 5-10 fractions and followed ≥6 months. Since January 2014, CAM has been administered in patients with pretreatment predictable radiation pneumonitis high-risk factors, including idiopathic interstitial pneumonias (IIPs), and elevated Krebs von den Lungen-6 (KL-6) and/or surfactant protein D (SP-D), and in patients developing early onset radiation pneumonitis.ResultsFive hundred and eighty eligible patients were identified and divided into 445 patients during the non-CAM-administration era (non-CAM-era) (before December 2013) and 136 patients during the CAM-administration era (CAM-era) (after January 2014). Median follow-up durations were 38.0 and 13.9 months, respectively. The rates of radiation pneumonitis ≥ grade 2 and ≥ grade 3 were significantly lower in CAM-era (grade ≥2, 16% vs. 9.6%, P=0.047; grade ≥3, 3.8% vs. 0.73%, P=0.037). For patients with the pretreatment predictable high-risk factors, the rate of radiation pneumonitis ≥ grade 3 was significantly lower, and that of grade ≥2 had a lower tendency (grade ≥3, 7.2% vs. 0%, P=0.011; grade ≥2, 21% vs. 9.6%, P=0.061). For patients developing early onset radiation pneumonitis, the rate of radiation pneumonitis ≥ grade 3 was also significantly lower (23% vs. 0%, P<0.05). Multivariate analysis revealed that dose-volumetric factor, the pretreatment predictable high-risk factors and non-CAM-administration era were significantly associated with or trended toward radiation pneumonitis ≥ grade 2 and ≥ grade 3.ConclusionsCAM mitigated radiation pneumonitis following SBRT. The efficacy of CAM should be conﬁrmed in prospective studies.

Project description:PurposeWhilst survival benefits of thoracic radiotherapy (TRT) followed by immune checkpoint inhibitor (ICI) have been reported in patients with lung cancer, the potential high risk of treatment-related pneumonitis remains a concern. Asians may be more sensitive to lung toxicity than other races. This retrospective study intended to provide a comprehensive pneumonitis profile of TRT followed by ICI and investigate the risk factors from a Chinese cohort of lung cancer.Methods and materialsFrom January 2016 to July 2021, 196 patients with lung cancer who received TRT prior to ICI were retrospectively analyzed. Treatment-related pneumonitis, including checkpoint inhibitor pneumonitis (CIP), radiation pneumonitis (RP), and radiation recall pneumonitis (RRP), were recorded and graded through medical records and chest computed tomography. Characteristics predictive of pneumonitis were assessed using logistic regression models, and the receiver operating characteristic analyses were performed to identify optimal cut points for quantitative variables.ResultsWith a median follow-up of 18 months, a total of 108 patients (55.1%) developed treatment-related pneumonitis during ICI therapy, with an incidence of 25.5% for grade 2 or higher (G2+) and 4.1% for G3+. The overall rates of CIP, RP and RRP were 8.2% (n=16), 46.9% (n=92) and 7.1% (n=14), respectively. With a total mortality rate of 1.5%, vast majority of the patients recovered from pneumonitis or remained stable. No patients died of RRP. Half of the patients with G2+ RP who withheld ICI therapy restarted ICI safely after resolution of RP. The history of chronic pulmonary diseases (P=0.05), mean lung dose (MLD, P=0.038), percent volume of lung receiving ≥5 Gy (V5, P=0.012) and percent volume of lung receiving ≥20 Gy (V20, P=0.030) predicted the occurrence of RRP in univariate analyses. Interval between TRT and ICI less than 3 months was an independent predictor for G2+ treatment-related pneumonitis in a multivariate model (Odds ratio OR=2.787, P=0.004).ConclusionsTreatment-related pneumonitis, especially RRP, is acceptable and manageable in the setting of TRT followed by ICI in this Asian population. Dosimetric parameters MLD, V5 and V20 may improve the predictions of RRP in clinical practice.

Project description:BackgroundPneumonitis is a possible side effect of radiotherapy for lung cancer. Since it can occur up to several months following treatment, symptoms may not be associated with previous radiotherapy, and pneumonitis can become severe before diagnosed. This study aimed to develop a symptom-based scoring system to contribute to earlier detection of radiation pneumonitis requiring medical intervention (grade ≥ 2).MethodsPatients irradiated for lung cancer complete a paper-based questionnaire (symptom-based score) during and up to 24 weeks following radiotherapy. Patients rate symptoms potentially associated with pneumonitis, and scoring points are assigned to severity of these symptoms. Sum scores are used to identify radiation pneumonitis. If radiation pneumonitis is suspected, patients undergo standard diagnostic procedures. If grade ≥ 2 pneumonitis is confirmed, medical intervention is indicated. The discriminative power of the score will be assessed by calculating the area under the receiver operating characteristic curve (AUC). If statistical significance of the AUC is reached, the optimal sum score to predict radiation pneumonitis will be established, which is defined as a cut-off value with sensitivity ≥90% and specificity ≥80%. Assuming a ratio between patients without and with pneumonitis of 3.63, a sample size of 93 patients is required in the full analysis set to yield statistical significance at the level of 5% with a power of 90% if the AUC under the alternative hypothesis is at least 0.9. Considering potential drop-outs, 98 patients should be recruited. If > 20% of patients are not satisfied with the score, modification is required. If the dissatisfaction rate is > 40%, the score is considered not useful. In 10 patients, functionality of a mobile application will be tested in addition to the paper-based questionnaire.DiscussionIf an optimal cut-off score resulting in sufficiently high sensitivity and specificity can be identified and the development of a symptom-based scoring system is successful, this tool will contribute to better identification of patients experiencing pneumonitis after radiotherapy for lung cancer.Trial registrationClinicaltrials.gov ( NCT04335409 ); registered on 2nd of April, 2020.

Project description:The purpose of this study was to examine the characteristics and treatment plans of patients who experienced fatal radiation pneumonitis after stereotactic body radiation therapy for primary or oligometastatic lung cancer. Records of 1789 patients treated with stereotactic body radiation therapy for primary or oligometastatic lung cancer were retrospectively reviewed to identify those who developed fatal radiation pneumonitis. Twenty-three (1.3%; 18 men and 5 women) patients developed fatal radiation pneumonitis after stereotactic body radiation therapy for lung cancer; their median age was 74 years. The mean Krebs von den Lungen-6 level and percent vital capacity were 1320 U/mL and 82%, respectively. Prestereotactic body radiation therapy computed tomography revealed pulmonary interstitial change in 14 (73.7%) of 19 patients in whom computed tomography data could be reviewed. Seven (30.4%) of 23 patients had regularly used steroids. The median time duration between stereotactic body radiation therapy commencement and pneumonia symptom appearance was 75 (range: 14-204) days. Median survival time following pneumonia symptom appearance was 53 (range: 4-802) days. The 6- and 12-month overall survival rates were 34.8% and 13.0%, respectively. The 6-month overall survival rates in patients with and without heart disease were 50.0%, 16.7%, and 46.7% for heart disease existence, respectively. There were 4 patients in whom fatal radiation pneumonitis occurred within 2 months after stereotactic body radiation therapy and who died within 1 month. Three of them had no pulmonary interstitial change before stereotactic body radiation therapy, but had heart disease. In summary, the survival time in this case series was generally short but varied widely. More than half of the patients had pulmonary interstitial change before stereotactic body radiation therapy, although immediately progressive fatal radiation pneumonitis was also observed in patients without pulmonary interstitial change. True risk factors for fatal radiation pneumonitis should be examined in a prospective study with a larger cohort.

Dataset Information

A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy.

Publications

A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets