Integration of longitudinal deep-radiomics and clinical data improves the prediction of durable benefits to anti-PD-1/PD-L1 immunotherapy in advanced NSCLC patients

BACKGROUND

Identifying predictive non-invasive biomarkers of immunotherapy response is crucial to avoid premature treatment interruptions or ineffective prolongation. Our aim was to develop a non-invasive biomarker for predicting immunotherapy clinical durable benefit, based on the integration of radiomics and clinical data monitored through early anti-PD-1/PD-L1 monoclonal antibodies treatment in patients with advanced non-small cell lung cancer (NSCLC).

METHODS

In this study, 264 patients with pathologically confirmed stage IV NSCLC treated with immunotherapy were retrospectively collected from two institutions. The cohort was randomly divided into a training (n = 221) and an independent test set (n = 43), ensuring the balanced availability of baseline and follow-up data for each patient. Clinical data corresponding to the start of treatment was retrieved from electronic patient records, and blood test variables after the first and third cycles of immunotherapy were also collected. Additionally, traditional radiomics and deep-radiomics features were extracted from the primary tumors of the computed tomography (CT) scans before treatment and during patient follow-up. Random Forest was used to implementing baseline and longitudinal models using clinical and radiomics data separately, and then an ensemble model was built integrating both sources of information.

RESULTS

The integration of longitudinal clinical and deep-radiomics data significantly improved clinical durable benefit prediction at 6 and 9 months after treatment in the independent test set, achieving an area under the receiver operating characteristic curve of 0.824 (95% CI: [0.658,0.953]) and 0.753 (95% CI: [0.549,0.931]). The Kaplan-Meier survival analysis showed that, for both endpoints, the signatures significantly stratified high- and low-risk patients (p-value< 0.05) and were significantly correlated with progression-free survival (PFS6 model: C-index 0.723, p-value = 0.004; PFS9 model: C-index 0.685, p-value = 0.030) and overall survival (PFS6 models: C-index 0.768, p-value = 0.002; PFS9 model: C-index 0.736, p-value = 0.023).

CONCLUSIONS

Integrating multidimensional and longitudinal data improved clinical durable benefit prediction to immunotherapy treatment of advanced non-small cell lung cancer patients. The selection of effective treatment and the appropriate evaluation of clinical benefit are important for better managing cancer patients with prolonged survival and preserving quality of life.

Fine-tuning characterization of patients with interstitial pneumonia and an underlying autoimmune disease in real-world practice: We get closer with Nailfold videocapillaroscopy

Objectives

To assess performance of interstitial pneumonia (IP) with autoimmune features (IPAF) criteria in clinical practice and describe the utility of additional workup in identifying patients with underlying connective tissue diseases (CTD).

Methods

We set a retrospective study of our patients with autoimmune IP, who were allocated to CTD-IP, IPAF or undifferentiated autoimmune IP (uAIP) subgroups according to the updated classification criteria. Presence of the process-related variables comprising IPAF defining domains was scrutinized in all patients, and, when available, the results of nailfold videocapillaroscopy (NVC) were recorded.

Results

Thirty nine out of 118 patients, accounting for 71% of former undifferentiated cases, fulfilled IPAF criteria. Arthritis and Raynaud's phenomenon were prevalent in this subgroup. While systemic sclerosis-specific autoantibodies were restricted to CTD-IP patients, anti-tRNA synthetase antibodies were also present in IPAF. In contrast, rheumatoid factor, anti-Ro antibodies and ANA nucleolar patterns could be found in all subgroups. Usual interstitial pneumonia (UIP) / possible UIP were the most frequently observed radiographic patterns Therefore, the presence of thoracic multicompartimental findings as also performance of open lung biopsies were useful in characterizing as IPAF those UIP cases lacking a clinical domain. Interestingly, we could observe NVC abnormalities in 54% of IPAF and 36% of uAIP tested patients, even though many of them did not report Raynaud's phenomenon.

Conclusion

Besides application of IPAF criteria, distribution of IPAF defining variables along with NVC exams help identify more homogeneous phenotypic subgroups of autoimmune IP of potential relevance beyond clinical diagnosis.

Deep learning-based lesion subtyping and prediction of clinical outcomes in COVID-19 pneumonia using chest CT

The main objective of this work is to develop and evaluate an artificial intelligence system based on deep learning capable of automatically identifying, quantifying, and characterizing COVID-19 pneumonia patterns in order to assess disease severity and predict clinical outcomes, and to compare the prediction performance with respect to human reader severity assessment and whole lung radiomics. We propose a deep learning based scheme to automatically segment the different lesion subtypes in nonenhanced CT scans. The automatic lesion quantification was used to predict clinical outcomes. The proposed technique has been independently tested in a multicentric cohort of 103 patients, retrospectively collected between March and July of 2020. Segmentation of lesion subtypes was evaluated using both overlapping (Dice) and distance-based (Hausdorff and average surface) metrics, while the proposed system to predict clinically relevant outcomes was assessed using the area under the curve (AUC). Additionally, other metrics including sensitivity, specificity, positive predictive value and negative predictive value were estimated. 95% confidence intervals were properly calculated. The agreement between the automatic estimate of parenchymal damage (%) and the radiologists' severity scoring was strong, with a Spearman correlation coefficient (R) of 0.83. The automatic quantification of lesion subtypes was able to predict patient mortality, admission to the Intensive Care Units (ICU) and need for mechanical ventilation with an AUC of 0.87, 0.73 and 0.68 respectively. The proposed artificial intelligence system enabled a better prediction of those clinically relevant outcomes when compared to the radiologists' interpretation and to whole lung radiomics. In conclusion, deep learning lesion subtyping in COVID-19 pneumonia from noncontrast chest CT enables quantitative assessment of disease severity and better prediction of clinical outcomes with respect to whole lung radiomics or radiologists' severity score.