TY  - JOUR
AB  - OBJECTIVES: Post-therapy pneumonitis (PTP) is a relevant side effect of thoracic radiotherapy and immunotherapy with checkpoint inhibitors (ICI). The influence of the combination of both, including dose fractionation schemes on PTP development is still unclear. This study aims to improve the PTP risk estimation after radio(chemo)therapy (R(C)T) for lung cancer with and without ICI by investigation of the impact of dose fractionation on machine learning (ML)-based prediction. MATERIALS AND METHODS: Data from 100 patients who received fractionated R(C)T were collected. 39 patients received additional ICI therapy. Computed Tomography (CT), RT segmentation and dose data were extracted and physical doses were converted to 2-Gy equivalent doses (EQD2) to account for different fractionation schemes. Features were reduced using Pearson intercorrelation and the Boruta algorithm within 1000-fold bootstrapping. Six single (clinics, Dose Volume Histogram (DVH), ICI, chemotherapy, radiomics, dosiomics) and four combined models (radiomics + dosiomics, radiomics + DVH + Clinics, dosiomics + DVH + Clinics, radiomics + dosiomics + DVH + Clinics) were trained to predict PTP. Dose-based models were tested using physical dose and EQD2. Four ML-algorithms (random forest (rf), logistic elastic net regression, support vector machine, logitBoost) were trained and tested using 5-fold nested cross validation and Synthetic Minority Oversampling Technique (SMOTE) for resampling in R. Prediction was evaluated using the area under the receiver operating characteristic curve (AUC) on the test sets of the outer folds. RESULTS: The combined model of all features using EQD2 surpassed all other models (AUC = 0.77, Confidence Interval CI 0.76-0.78). DVH, clinical data and ICI therapy had minor impact on PTP prediction with AUC values between 0.42 and 0.57. All EQD2-based models outperformed models based on physical dose. CONCLUSIONS: Radiomics + dosiomics based ML models combined with clinical and dosimetric models were found to be suited best for PTP prediction after R(C)T and could improve pre-treatment decision making. Different RT dose fractionation schemes should be considered for dose-based ML approaches.
AU  - Kraus, K.M.
AU  - Oreshko, M.*
AU  - Schnabel, J.A.
AU  - Bernhardt, D.*
AU  - Combs, S.E.
AU  - Peeken, J.C.
C1  - 70039
C2  - 55373
CY  - Elsevier House, Brookvale Plaza, East Park Shannon, Co, Clare, 00000, Ireland
TI  - Dosiomics and radiomics-based prediction of pneumonitis after radiotherapy and immune checkpoint inhibition: The relevance of fractionation.
JO  - Lung Cancer
VL  - 189
PB  - Elsevier Ireland Ltd
PY  - 2024
SN  - 0169-5002
ER  - 

TY  - JOUR
AB  - Objectives: Studies from several countries reported socioeconomic inequalities in lung cancer survival. Hypothesized reasons are differences in cancer care or tumor characteristics. We investigated associations of small-area deprivation and lung cancer survival in Germany and the possible impact of differences in patient, tumor or treatment factors.Materials and Methods: Patients registered with a primary tumor of the lung between 2000-2015 in three German population-based clinical cancer registries were included. Area-based socioeconomic deprivation on municipality level was measured with the categorized German Index of Multiple Deprivation. Association of deprivation with overall survival was investigated with Cox regression models.Results: Overall, 22,905 patients were included. Five-year overall survival from the least to the most deprived quintile were 17.2%, 15.9%, 16.7%, 15.7%, and 14.4%. After adjustment for patient and tumor factors, the most deprived group had a lower survival compared to the least deprived group (Hazard Ratio (HR) 1.06, 95% confidence interval (CI) 1.01-1.11). Subgroup analyses revealed lower survival in the most deprived compared to the least deprived quintile in patients with stage I-III [HR: 1.14, 95% CI: 1.06-1.22]. The association persisted when restricting to patients receiving surgery but was attenuated for subgroups receiving either chemotherapy or radiotherapy.Conclusion: Our results indicate differences in lung cancer survival according to area deprivation in Germany, which were more pronounced in patients with I-III stage cancer. Future research should address in more detail the underlying reasons for the observed inequalities and possible approaches to overcome them.
AU  - Finke, I.*
AU  - Behrens, G.*
AU  - Schwettmann, L.
AU  - Gerken, M.*
AU  - Pritzkuleit, R.*
AU  - Holleczek, B.*
AU  - Brenner, H.*
AU  - Jansen, L.*
C1  - 58177
C2  - 48081
CY  - Elsevier House, Brookvale Plaza, East Park Shannon, Co, Clare, 00000, Ireland
SP  - 1-8
TI  - Socioeconomic differences and lung cancer survival in Germany: Investigation based on population-based clinical cancer registration.
JO  - Lung Cancer
VL  - 142
PB  - Elsevier Ireland Ltd
PY  - 2020
SN  - 0169-5002
ER  - 

TY  - JOUR
AB  - Objectives: In presence of lung cancer, the additional impact of comorbidity on survival is often neglected, although comorbidities are likely to be prevalent. Our study examines the comorbidity profile and the impact of distinct conditions on survival in German lung cancer patients.Material and methods: We investigated claims data from a large nationwide statutory health insurance fund of 16,202 patients initially diagnosed with lung cancer in 2009. We calculated the prevalence of comorbidities grouped according to an extension of the Elixhauser Comorbidity Index (EI). Effects of distinct comorbidities on 5-year survival were examined using multivariate Cox proportional hazards models, adjusted for sex, age and metastases at baseline. Ail analyses were stratified by initial lung cancer-related treatment regimen (Surgery, Chemotherapy/Radiotherapy, No treatment). Findings were visualized in the form of a comorbidome.Results: Our study population was predominantly male (70.6%) with a mean age of 68.6 years, and a mean EI score of 3.94. Patients without treatment were older (74.4 years), and their comorbidity burden was higher (mean EI = 4.59). Median survival varied by subgroup (Surgery: 24.4 months, Chemotherapy/Radiotherapy: 8.8 months, No treatment: 2.0 months), and so did the comorbidity profile and the impact of distinct conditions on survival. Generally, the effect of comorbidities on survival was detrimental and the negative association was most pronounced for 'Weight Loss' and' Paralysis'. In contrast, 'Lipid Metabolism Disorders' and 'Obesity' were positively associated with survival. Noteworthily, highly prevalent conditions tended not to show any significant association.Conclusion: We found specific comorbidity profiles within the distinct treatment regimens. Moreover, there were negative but also some positive associations with survival, and the strength of these effects varied by stratum. Particularly the positive effects of 'Obesity" and 'Lipid Metabolism Disorders' which were robust across strata need to be further investigated to elucidate potential biomedical explanations.
AU  - Murawski, M.
AU  - Walter, J.
AU  - Schwarzkopf, L.
C1  - 54869
C2  - 45843
CY  - Elsevier House, Brookvale Plaza, East Park Shannon, Co, Clare, 00000, Ireland
SP  - 122-129
TI  - Assessing the lung cancer comorbidome: An analysis of German claims data.
JO  - Lung Cancer
VL  - 127
PB  - Elsevier Ireland Ltd
PY  - 2018
SN  - 0169-5002
ER  - 

TY  - JOUR
AB  - Objectives: Although lung cancer is of high epidemiological relevance in Germany, evidence on its economic implications is scarce. Sound understanding of current care structures and associated expenditures is required to comprehensively judge the additional benefit of novel interventions in lung cancer care. Adopting a payer perspective, our study aims to analyze expenditures for individuals with incident lung cancer. Material and methods: Patients with an initial diagnosis of lung cancer (ICD-10 code C34) in 2009 were searched in a large, nationwide base of health insurance claims data and grouped according to initial treatment (Surgery, Chemotherapy/Radiotherapy, No specific treatment). All-cause SHI and lung cancer-related spending was assessed for a patient-individual three-year time frame after initial diagnosis. Expenditures per case and expenditures per year survived were calculated via Generalized Linear Gamma Models adjusted for age, gender, living region, baseline metastases, multiple tumors and initial treatment regimen using time under observation as a weighting factor. Results: 17,478 individuals were identified. Lung cancer-related expenditures peaked within the first six months after initial diagnosis. Following, they declined subsequently and so did their share in all-cause SHI spending. Lung cancer-related expenditures per case were estimated at €20,400 (53% of all-cause expenditures) with a huge variance according to initial treatment regimen [Surgery: €20,400, Chemotherapy/Radiotherapy: €26,300, No specific treatment: €4200]. Cost per year survived amounted to €15,500 (55% of all cause expenditures) [Surgery: €11,600, Chemotherapy/Radiotherapy: €20,200, No specific treatment: €7600]. Conclusion: Analyses of lung cancer-related expenditures need to take into account treatment strategies and survival. Our study is representative for a large share of the population and provides detailed, patient-level information on costs of care and their compilation. Results render estimates available for the cost of lung cancer e.g. for budget impact analyses, cost-effectiveness analyses of screening and prevention schemes, or prognostic models of life-time expenditures per lung cancer case.
AU  - Schwarzkopf, L.
AU  - Wacker, M.
AU  - Holle, R.
AU  - Leidl, R.
AU  - Günster, C.*
AU  - Adler, J.B.*
AU  - Huber, R.M.*
C1  - 46826
C2  - 37865
SP  - 274-280
TI  - Cost-components of lung cancer care within the first three years after initial diagnosis in context of different treatment regimens.
JO  - Lung Cancer
VL  - 90
IS  - 2
PY  - 2015
SN  - 0169-5002
ER  -