Deep Learning for Lung Cancer Nodal Staging and Real-World Clinical Practice

Radiology ◽  
2021 ◽  
Author(s):  
Chang Min Park ◽  
Jong Hyuk Lee
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Clinical Practice ◽  
Real World ◽  
Nodal Staging

Efficacy and Safety of Lipegfilgrastim in Lung Cancer Patients Receiving Myelosuppressive Chemotherapy in a Real-World Setting: Results of an Analysis of Pooled Data from Two Non-Interventional European Studies

2021 ◽  
pp. 1-9
Author(s):  
Christian Gessner ◽  
Karin Potthoff ◽  
Nikolaj Frost
Keyword(s):  
Lung Cancer ◽  
Clinical Practice ◽  
Cancer Patients ◽  
Adverse Drug Reactions ◽  
Real World ◽  
Secondary Prophylaxis ◽  
Drug Reactions ◽  
Myelosuppressive Chemotherapy ◽  
Lung Cancer Patients ◽  
Chemotherapy Induced Neutropenia

<b><i>Background/Aim:</i></b> Chemotherapy-induced neutropenia is a common and serious complication in cancer patients receiving myelosuppressive chemotherapy. This analysis was undertaken to evaluate the effectiveness and safety of prophylaxis with lipegfilgrastim, a glycoPEGylated granulocyte colony-stimulating factor, in lung cancer patients undergoing chemotherapy in real-world clinical practice. <b><i>Methods:</i></b> Data from two European non-interventional studies (NIS NADIR and NIS LEOS) investigating lipegfilgrastim for primary and secondary prophylaxis were pooled. Outcomes included the incidence of chemotherapy-induced neutropenia and febrile neutropenia (FN), use of anti-infectives and antimycotics, and adverse events and their relationship to lipegfilgrastim. <b><i>Results:</i></b> The safety population included 361 patients with lung cancer (median age, 66 years [range, 36–88]), of whom 322 had received 2 or more consecutive cycles of lipegfilgrastim (efficacy population [primary prophylaxis, 75.5%; secondary prophylaxis, 16.5%]). Almost 40% of the patients were considered to have a high risk (&#x3e;20%) of FN, and around 60% had an intermediate risk (10–20%). For all cycles, FN was reported in 3 patients (0.9%), neutropenia in 14 (4.3%), and grade 4 neutropenia in 9 (2.8%). Anti-infectives were used in 27 patients (8.4%) and antimycotics in 6 (1.9%). The incidence rates were lower for the patients’ first cycle (FN, 0.4%; neutropenia, 0.8%; grade 4 neutropenia, 0.8%; anti-infectives, 0.6%; antimycotics, 0.6%). Adverse drug reactions considered lipegfilgrastim related were reported in 35 patients (9.7%), and serious adverse drug reactions in 10 (2.8%). None of the fatal events reported in 28 patients (7.8%) were lipegfilgrastim related. <b><i>Conclusion:</i></b> Lipegfilgrastim administered to patients with lung cancer undergoing chemotherapy in real-world clinical practice showed similar effectiveness and safety to that reported in published pivotal trials.

Artificial intelligence based on deep learning for differential diagnosis between benign and malignant pulmonary nodules: A real-world, multicenter, diagnostic study.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 9037-9037
Author(s):  
Tao Xu ◽  
Chuoji Huang ◽  
Yaoqi Liu ◽  
Jing Gao ◽  
Huan Chang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Lung Cancer ◽  
Deep Learning ◽  
Diagnostic Accuracy ◽  
Real World ◽  
Pulmonary Nodules ◽  
Ct Images ◽  
Test Method ◽  
Histopathological Diagnosis ◽  
Diagnostic Study

9037 Background: Lung cancer is the most common cancer worldwide. Artificial intelligence (AI) platform using deep learning algorithms have made a remarkable progress in improving diagnostic accuracy of lung cancer. But AI diagnostic performance in identifying benign and malignant pulmonary nodules still needs improvement. We aimed to validate a Pulmonary Nodules Artificial Intelligence Diagnostic System (PNAIDS) by analyzing computed tomography (CT) imaging data. Methods: This real-world, multicentre, diagnostic study was done in five different tier hospitals in China. The CT images of patients, who were aged over 18 years and never had previous anti-cancer treatments, were retrieved from participating hospitals. 534 eligible patients with 5-30mm diameter pulmonary nodules identified by CT were planning to confirm with histopathological diagnosis. The performance of PNAIDS was also compared with respiratory specialists and radiologists with expert or competent degrees of expertise as well as Mayo Clinic’s model by area under the curve (AUC) and evaluated differences by calculating the 95% CIs using the Z-test method. 11 selected participants were tested circulating genetically abnormal cells (CACs) before surgery with doctors suggested. Results: 611 lung CT images from 534 individuals were used to test PNAIDS. The diagnostic accuracy, valued by AUC, in identifying benign and malignant pulmonary nodules was 0.765 (95%CI [0.729 - 0.798]). The diagnostic sensitivity of PNAIDS is 0.630(0.579 – 0.679), specificity is 0.753 (0.693 – 0.807). PNAIDS achieved diagnostic accuracy similar to that of the expert respiratory specialists (AUC difference: 0.0036 [-0.0426 - 0.0497]; p = 0.8801) and superior when compared with Mayo Clinic’s model (0.120 [0.0649 - 0.176], p < 0·0001), expert radiologists (0.0620 [0.0124 - 0.112], p = 0.0142) and competent radiologists (0.0751 [0.0248 - 0.125], p = 0.0034). 11 selected participants were suggested negative in AI results but positive in respiratory specialists’ result. 8 of them were malignant in histopathological diagnosis with tested more than 3 CACs in their blood. Conclusions: PNAIDS achieved high diagnostic accuracy in differential diagnoses between benign and malignant pulmonary nodules, with diagnostic accuracy similar to that of expert respiratory specialists and was superior to that of Mayo Clinic’s model and radiologists. CACs may be able to assist CT-based AI in improving their effectiveness but it still need more data to be proved. Clinical trial information: ChiCTR1900026233.

Readiness of health care systems to generate RWE: Frequency of radiographic imaging of metastatic disease during first-line systemic therapy.

2020 ◽  
Vol 38 (29_suppl) ◽  
pp. 268-268
Author(s):  
Brandon Chan ◽  
David Cameron ◽  
Aria Shokoohi ◽  
Dean Regier ◽  
Howard John Lim ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Health Care ◽  
Clinical Practice ◽  
Metastatic Disease ◽  
Real World ◽  
Systemic Therapy ◽  
De Novo ◽  
Metastatic Breast ◽  
Ct Imaging ◽  
First Line

268 Background: Regulatory and Health Technology Assessment (HTA) agencies are increasingly using real world data (RWD) to support real world evidence (RWE), but the readiness of healthcare systems to reliably generate RWE is unknown. As a quality assurance measure we examined the preparedness of a single payer system to provide RWE by evaluating the frequency of CT imaging during standard first line metastatic systemic treatment of breast, colorectal (CRC) and lung cancer. Methods: A 1-year cohort of de novo metastatic breast, CRC, lung cancer patients treated with first line systemic therapy (excluding hormone therapy) referred to BC Cancer in 2016 was retrospectively reviewed. Duration of first line treatment was calculated from first to last dose of therapy. Baseline CT included imaging within 8 weeks prior to and 3 weeks after treatment initiation (first cycle). Last CT included imaging up to 8 weeks after the last dose of therapy. Results: A cohort of 675 patients was identified from the BC Cancer Registry. The distribution of de novo metastatic disease at diagnosis was lung (n = 379), CRC (n = 214) followed by breast cancer (n = 82). Conclusions: In our publicly funded health care system, baseline CT scans within 4 weeks prior to treatment ranged from 57-72%. The median CT imaging interval during first line metastatic treatment was ranged from 7.9-11.3 weeks. RWD from routine clinical practice differs significantly from clinical trials, the gold standard for regulatory and HTA assessments. Population-based data may contribute to RWE with caution due to limitations imposed by clinical practice. [Table: see text]

scholarly journals First-line afatinib for the treatment of EGFR mutation-positive non-small-cell lung cancer in the ‘real-world’ clinical setting

2019 ◽  
Vol 11 ◽  
pp. 175883591983637 ◽  
Author(s):  
Keunchil Park ◽  
Darren Wan-Teck Lim ◽  
Isamu Okamoto ◽  
James Chih-Hsin Yang
Keyword(s):  
Lung Cancer ◽  
Clinical Practice ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Real World ◽  
Clinical Studies ◽  
Egfr Mutation ◽  
Small Cell ◽  
Small Cell Lung ◽  
First Line

Afatinib is an ErbB family blocker that is approved for the treatment of epidermal growth factor receptor ( EGFR) mutation-positive non-small-cell lung cancer (NSCLC). Pivotal randomized clinical studies demonstrated that afatinib significantly prolonged progression-free survival compared with platinum-based chemotherapy (LUX-Lung 3, LUX-Lung 6), and with gefitinib (LUX-Lung 7), with manageable side effects. However, these results were derived from controlled studies conducted in selected patients and are not necessarily representative of real-world use of afatinib. To gain a broader understanding of the effectiveness and safety of first-line afatinib, we have undertaken a literature review of real-world studies that have assessed its use in a variety of patient populations. We focused on patients with uncommon EGFR mutations, brain metastases, or those of advanced age, as these patients are often excluded from clinical studies but are regularly seen in routine clinical practice. The available real-world studies suggest that afatinib has clinical activity, and is tolerable, in diverse patient populations in an everyday clinical practice setting. Moreover, consistent with LUX-Lung 7, several real-world comparative studies indicate that afatinib might confer better efficacy than first-generation EGFR tyrosine kinase inhibitors. Tolerability-guided dose adjustment, undertaken in 21–68% of patients in clinical practice, did not appear to reduce the efficacy of afatinib. Taken together, these findings provide further support for the use of afatinib as a treatment option in patients with EGFR mutation-positive NSCLC.

Preoperative lymph node assessment in surgically resected pathologic T1 lung cancer patients: Real world clinical practice in China.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e20016-e20016
Author(s):  
Xu Jinming ◽  
Xingpeng Han ◽  
Lunxu Liu ◽  
Xiangning Fu ◽  
Yin Li ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Lymph Node ◽  
Clinical Practice ◽  
Cancer Patients ◽  
Real World ◽  
Kappa Index ◽  
Lung Cancer Patients ◽  
Lymph Node Assessment ◽  
N Stage ◽  
N Staging

e20016 Background: Accurate lymph node assessment is crucial for clinical patient management and prognostic prediction. However, the procedures may not always be performed preoperatively due to time, cost or risk of procedure itself. Present study aimed to investigate the real world clinical practice of preoperative N staging in surgically resected pathologic T1 lung cancer patients in China. Methods: This is a multicenter retrospective study. Real world data on clinical and pathologic N staging was retrieved from electronic medical records in 10 thoracic surgery centers (LinkDoc Database). Kappa index was calculated to determine the agreement between clinical and pathologic N stage. Results: A total of 11360 patients who underwent surgical resection for pT1 lung cancer were identified during January 2014 to September 2017. Clinical N staging was available for 6057 (53.3%) patients. Of which, 959 (15.8%) patients were achieved by invasive procedures. Considering the 5795 patients with clinical and pathologic N staging data, the overall agreement was 89.0% with a kappa index of 0.4220 (95%CI: 0.3842-0.4598). This was 96.4% for N0, 22.1% for N1 and 39.8% for N2 when considering pathologic N stage as gold standard (Table). In general, upstaging (7.3%) was more common in our population. Conclusions: Over 50% of pathologic T1 patients had preoperative N staging in our clinical practice. Clinical N staging showed low accuracy for predicting lymph node status. The findings of our study highlight the increasing attention on clinical N staging and procedure optimization in China. [Table: see text]

PD-1/PD-L1 immunotherapy for advanced lung cancer: An electronic medical database based real world study in China.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e20543-e20543
Author(s):  
Xiao Zhao ◽  
Qiong Sun ◽  
Sheng Jie Sun ◽  
Weiwei Shi ◽  
Shun Chang Jiao
Keyword(s):  
Lung Cancer ◽  
Overall Survival ◽  
Clinical Practice ◽  
Adverse Events ◽  
Cancer Patients ◽  
Real World ◽  
Progression Free Survival ◽  
Advanced Lung Cancer ◽  
Free Survival ◽  
Lung Cancer Patients

e20543 Background: Immunotherapy has shown promising results for clinical management of various cancers. We reported our real world experience with PD-1 or PD-L1 immunotherapy in management of advanced lung cancer patients in China. Methods: This is a single-center retrospective study based on the de-identified electronic medical data collected in routine clinical practice. A total of 198 advanced lung cancer (stage IIIA-IV) patients who underwent anti-PD-1/PD-L1 therapy at Chinese People's Liberation Army General Hospital between 2015 and 2018 were included. Progression free survival and overall survival of patients were estimated by Kaplan-Meier methods. The treatment-related adverse events were also analyzed. Results: Median age of patients was 60.0 years (33.0-88.0 years). Most patients were male (150, 75.8%), smokers (116, 61.7%) and had a KPS score ≥70 (169, 97.7%). Of 198 patients, 106 (53.5%) had adenocarcinoma and 54 (17.3%) had squamous cell carcinoma. Thirty-one (15.7%) patients had CNS metastases. Seventy-one (38.8%) patients received two or more prior therapies. Estimated progression free survival was 5.6 months and overall survival was 24.5 months. One-hundred twenty-seven (64.1%) patients had documented to suffer adverse events, most commonly gastrointestinal adverse events and liver damage (Table). Conclusions: Our study showed survival benefits of PD-1/PD-L1 immunotherapy in advanced NSCLC patients in clinical practice. Safety profile was comparable to the previous studies. Our study supports the benefits of PD-1/PD-L1 immunotherapy in clinical management of advanced lung cancer patients. [Table: see text]

Sign in / Sign up

Export Citation Format

Share Document