scholarly journals Improving lung cancer risk stratification leveraging whole transcriptome RNA sequencing and machine learning across multiple cohorts

2020 ◽  
Vol 13 (S10) ◽  
Author(s):  
Yoonha Choi ◽  
Jianghan Qu ◽  
Shuyang Wu ◽  
Yangyang Hao ◽  
Jiarui Zhang ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Risk ◽  
Positive Predictive Value ◽  
Predictive Value ◽  
Smoking History ◽  
Sample Collection ◽  
Gene Expressions ◽  
Post Test ◽  
The Impact ◽  
Inhaled Medication

Abstract Background Bronchoscopy for suspected lung cancer has low diagnostic sensitivity, rendering many inconclusive results. The Bronchial Genomic Classifier (BGC) was developed to help with patient management by identifying those with low risk of lung cancer when bronchoscopy is inconclusive. The BGC was trained and validated on patients in the Airway Epithelial Gene Expression in the Diagnosis of Lung Cancer (AEGIS) trials. A modern patient cohort, the BGC Registry, showed differences in key clinical factors from the AEGIS cohorts, with less smoking history, smaller nodules and older age. Additionally, we discovered interfering factors (inhaled medication and sample collection timing) that impacted gene expressions and potentially disguised genomic cancer signals. Methods In this study, we leveraged multiple cohorts and next generation sequencing technology to develop a robust Genomic Sequencing Classifier (GSC). To address demographic composition shift and interfering factors, we synergized three algorithmic strategies: 1) ensemble of clinical dominant and genomic dominant models; 2) development of hierarchical regression models where the main effects from clinical variables were regressed out prior to the genomic impact being fitted in the model; and 3) targeted placement of genomic and clinical interaction terms to stabilize the effect of interfering factors. The final GSC model uses 1232 genes and four clinical covariates – age, pack-years, inhaled medication use, and specimen collection timing. Results In the validation set (N = 412), the GSC down-classified low and intermediate pre-test risk subjects to very low and low post-test risk with a specificity of 45% (95% CI 37–53%) and a sensitivity of 91% (95%CI 81–97%), resulting in a negative predictive value of 95% (95% CI 89–98%). Twelve percent of intermediate pre-test risk subjects were up-classified to high post-test risk with a positive predictive value of 65% (95%CI 44–82%), and 27% of high pre-test risk subjects were up-classified to very high post-test risk with a positive predictive value of 91% (95% CI 78–97%). Conclusions The GSC overcame the impact of interfering factors and achieved consistent performance across multiple cohorts. It demonstrated diagnostic accuracy in both down- and up-classification of cancer risk, providing physicians actionable information for many patients with inconclusive bronchoscopy.

scholarly journals Artificial neural networks improve LDCT lung cancer screening: a comparative validation study

BMC Cancer ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Yin-Chen Hsu ◽  
Yuan-Hsiung Tsai ◽  
Hsu-Huei Weng ◽  
Li-Sheng Hsu ◽  
Ying-Huang Tsai ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Risk ◽  
Positive Predictive Value ◽  
Prediction Model ◽  
Negative Predictive Value ◽  
Validation Study ◽  
Predictive Value ◽  
Prospective Cohort ◽  
Lung Cancer Risk ◽  
Comparative Validation

Abstract Background This study proposes a prediction model for the automatic assessment of lung cancer risk based on an artificial neural network (ANN) with a data-driven approach to the low-dose computed tomography (LDCT) standardized structure report. Methods This comparative validation study analysed a prospective cohort from Chiayi Chang Gung Memorial Hospital, Taiwan. In total, 836 asymptomatic patients who had undergone LDCT scans between February 2017 and August 2018 were included, comprising 27 lung cancer cases and 809 controls. A derivation cohort of 602 participants (19 lung cancer cases and 583 controls) was collected to construct the ANN prediction model. A comparative validation of the ANN and Lung-RADS was conducted with a prospective cohort of 234 participants (8 lung cancer cases and 226 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models. Results At the cut-off of category 3, the Lung-RADS had a sensitivity of 12.5%, specificity of 96.0%, positive predictive value of 10.0%, and negative predictive value of 96.9%. At its optimal cut-off value, the ANN had a sensitivity of 75.0%, specificity of 85.0%, positive predictive value of 15.0%, and negative predictive value of 99.0%. The area under the ROC curve was 0.764 for the Lung-RADS and 0.873 for the ANN (P = 0.01). The two most important predictors used by the ANN for predicting lung cancer were the documented sizes of partially solid nodules and ground-glass nodules. Conclusions Compared to the Lung-RADS, the ANN provided better sensitivity for the detection of lung cancer in an Asian population. In addition, the ANN provided a more refined discriminative ability than the Lung-RADS for lung cancer risk stratification with population-specific demographic characteristics. When lung nodules are detected and documented in a standardized structured report, ANNs may better provide important insights for lung cancer prediction than conventional rule-based criteria.

scholarly journals Artificial neural networks improve LDCT lung cancer screening: A comparative validation study

2020 ◽  
Author(s):  
Yin-Chen Hsu ◽  
Yuan-Hsiung Tsai ◽  
Hsu-Huei Weng ◽  
Li-Sheng Hsu ◽  
Ying-Huang Tsai ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Risk ◽  
Positive Predictive Value ◽  
Prediction Model ◽  
Negative Predictive Value ◽  
Validation Study ◽  
Predictive Value ◽  
Prospective Cohort ◽  
Lung Cancer Risk ◽  
Comparative Validation

Abstract Background: This study proposes a prediction model for the automatic assessment of lung cancer risk based on an artificial neural network (ANN) with a data-driven approach to the low-dose computed tomography (LDCT) standardized structure report.Methods: This comparative validation study analysed a prospective cohort from Chiayi Chang Gung Memorial Hospital, Taiwan. In total, 836 asymptomatic patients who had undergone LDCT scans between February 2017 and August 2018 were included, comprising 27 lung cancer cases and 809 controls. A derivation cohort of 602 participants (19 lung cancer cases and 583 controls) was collected to construct the ANN prediction model. A comparative validation of the ANN and Lung-RADS was conducted with a prospective cohort of 234 participants (8 lung cancer cases and 226 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models.Results: At the cut-off of category 3, the Lung-RADS had a sensitivity of 12.5%, specificity of 96.0%, positive predictive value of 10.0%, and negative predictive value of 96.9%. At its optimal cut-off value, the ANN had a sensitivity of 75.0%, specificity of 85.0%, positive predictive value of 15.0%, and negative predictive value of 99.0%. The area under the ROC curve was 0.764 for the Lung-RADS and 0.873 for the ANN (P=0.01). The heatmap plot demonstrates the leading items, i.e., solid nodules, partially solid nodules, and ground-glass nodules, as the significant predictors of malignant outcomes.Conclusions: Compared to the Lung-RADS, the ANN provided better sensitivity for the detection of lung cancer in an Asian population. In addition, the ANN provided a more refined discriminative ability than the Lung-RADS for lung cancer risk stratification with population-specific demographic characteristics. When lung nodules are detected and documented in a standardized structured report, ANNs may better provide important insights for lung cancer prediction than conventional rule-based criteria.Trial registrationNot applicable.

scholarly journals Artificial neural networks improve LDCT lung cancer screening: A comparative validation study

2020 ◽  
Author(s):  
Yin-Chen Hsu ◽  
Yuan-Hsiung Tsai ◽  
Hsu-Huei Weng ◽  
Li-Sheng Hsu ◽  
Ying-Huang Tsai ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Risk ◽  
Positive Predictive Value ◽  
Prediction Model ◽  
Negative Predictive Value ◽  
Validation Study ◽  
Predictive Value ◽  
Prospective Cohort ◽  
Lung Cancer Risk ◽  
Comparative Validation

Abstract Background: This study proposes a prediction model for the automatic assessment of lung cancer risk based on an artificial neural network (ANN) with a data-driven approach to the low-dose computed tomography (LDCT) standardized structure report.Methods: This comparative validation study analysed a prospective cohort from Chiayi Chang Gung Memorial Hospital, Taiwan. In total, 836 asymptomatic patients who had undergone LDCT scans between February 2017 and August 2018 were included, comprising 27 lung cancer cases and 809 controls. A derivation cohort of 602 participants (19 lung cancer cases and 583 controls) was collected to construct the ANN prediction model. A comparative validation of the ANN and Lung-RADS was conducted with a prospective cohort of 234 participants (8 lung cancer cases and 226 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models.Results: At the cut-off of category 3, the Lung-RADS had a sensitivity of 12.5%, specificity of 96.0%, positive predictive value of 10.0%, and negative predictive value of 96.9%. At its optimal cut-off value, the ANN had a sensitivity of 75.0%, specificity of 85.0%, positive predictive value of 15.0%, and negative predictive value of 99.0%. The area under the ROC curve was 0.764 for the Lung-RADS and 0.873 for the ANN (P=0.01). The two most important predictors used by the ANN for predicting lung cancer were the documented sizes of partially solid nodules and ground-glass nodules.Conclusions: Compared to the Lung-RADS, the ANN provided better sensitivity for the detection of lung cancer in an Asian population. In addition, the ANN provided a more refined discriminative ability than the Lung-RADS for lung cancer risk stratification with population-specific demographic characteristics. When lung nodules are detected and documented in a standardized structured report, ANNs may better provide important insights for lung cancer prediction than conventional rule-based criteria.

scholarly journals Artificial Neural Networks Improve LDCT Lung Cancer Screening: A Comparative Validation Study

2020 ◽  
Author(s):  
Yin-Chen Hsu ◽  
Yuan-Hsiung Tsai ◽  
Hsu-Huei Weng ◽  
Li-Sheng Hsu ◽  
Ying-Huang Tsai ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Risk ◽  
Positive Predictive Value ◽  
Prediction Model ◽  
Negative Predictive Value ◽  
Validation Study ◽  
Predictive Value ◽  
Prospective Cohort ◽  
Lung Cancer Risk ◽  
Comparative Validation

Abstract Background: This study proposes a prediction model for the automatic assessment of lung cancer risk based on an artificial neural network (ANN) with a data-driven approach to the low-dose computed tomography (LDCT) standardized structure report. Methods: This comparative validation study analysed a prospective cohort from Chiayi Chang Gung Memorial Hospital, Taiwan. In total, 836 asymptomatic patients who had undergone LDCT scans between February 2017 and August 2018 were included, comprising 27 lung cancer cases and 809 controls. A derivation cohort of 602 participants (19 lung cancer cases and 583 controls) was collected to construct the ANN prediction model. A comparative validation of the ANN and Lung-RADS was conducted with a prospective cohort of 234 participants (8 lung cancer cases and 226 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models. Results: At the cut-off of category 3, the Lung-RADS had a sensitivity of 12.5%, specificity of 96.0%, positive predictive value of 10.0%, and negative predictive value of 96.9%. At its optimal cut-off value, the ANN had a sensitivity of 75.0%, specificity of 85.0%, positive predictive value of 15.0%, and negative predictive value of 99.0%. The area under the ROC curve was 0.764 for the Lung-RADS and 0.873 for the ANN (P=0.01). The heatmap plot demonstrates the leading items, i.e., solid nodules, partially solid nodules, and ground-glass nodules, as the significant predictors of malignant outcomes.Conclusions: Compared to the Lung-RADS, the ANN provided better sensitivity for the detection of lung cancer in an Asian population. In addition, the ANN provided a more refined discriminative ability than the Lung-RADS for lung cancer risk stratification with population-specific demographic characteristics. When lung nodules are detected and documented in a standardized structured report, ANNs may better provide important insights for lung cancer prediction than conventional rule-based criteria.Trial registration: Not applicable.

scholarly journals Artificial neural networks improve LDCT lung cancer screening: A comparative validation study

2020 ◽  
Author(s):  
Yin-Chen Hsu ◽  
Yuan-Hsiung Tsai ◽  
Hsu-Huei Weng ◽  
Li-Sheng Hsu ◽  
Ying-Huang Tsai ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Risk ◽  
Positive Predictive Value ◽  
Prediction Model ◽  
Negative Predictive Value ◽  
Validation Study ◽  
Predictive Value ◽  
Prospective Cohort ◽  
Lung Cancer Risk ◽  
Comparative Validation

Abstract Background: This study proposes a prediction model for the automatic assessment of lung cancer risk based on an artificial neural network (ANN) with a data-driven approach to the low-dose computed tomography (LDCT) standardized structure report. Methods: This comparative validation study analysed a prospective cohort from Chiayi Chang Gung Memorial Hospital, Taiwan. In total, 836 asymptomatic patients who had undergone LDCT scans between February 2017 and August 2018 were included, comprising 27 lung cancer cases and 809 controls. A derivation cohort of 602 participants (19 lung cancer cases and 583 controls) was collected to construct the ANN prediction model. A comparative validation of the ANN and Lung-RADS was conducted with a prospective cohort of 234 participants (8 lung cancer cases and 226 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models. Results: At the cut-off of category 3, the Lung-RADS had a sensitivity of 12.5%, specificity of 96.0%, positive predictive value of 10.0%, and negative predictive value of 96.9%. At its optimal cut-off value, the ANN had a sensitivity of 75.0%, specificity of 85.0%, positive predictive value of 15.0%, and negative predictive value of 99.0%. The area under the ROC curve was 0.764 for the Lung-RADS and 0.873 for the ANN ( P =0.01). The two most important predictors used by the ANN for predicting lung cancer were the documented sizes of partially solid nodules and ground-glass nodules. Conclusions: Compared to the Lung-RADS, the ANN provided better sensitivity for the detection of lung cancer in an Asian population. In addition, the ANN provided a more refined discriminative ability than the Lung-RADS for lung cancer risk stratification with population-specific demographic characteristics. When lung nodules are detected and documented in a standardized structured report, ANNs may better provide important insights for lung cancer prediction than conventional rule-based criteria.

Successful treatment of pulmonary lymphangitic carcinomatosis by anlotinib in 14 Chinese patients with advanced non-small cell lung cancer.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e21064-e21064
Author(s):  
Shencun Fang ◽  
Wanwan Cheng ◽  
Yingming Zhang ◽  
Haitao Zhang ◽  
Si Li ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Lymphatic Metastasis ◽  
Small Cell ◽  
Smoking History ◽  
Wild Type ◽  
Small Cell Lung ◽  
The Impact ◽  
Lymphangitic Carcinomatosis

e21064 Background: Pulmonary lymphangitic carcinomatosis (PLC) occurs in 6%-8% of intrathoracic metastases among malignant tumor. The median survival was only 2.0 months from time of pulmonary symptoms to death in cases during 2000-2018, which is a poor prognosis. Effective interventions were needed besides standard chemotherapy and symptomatic support. Anlotinib showed a critical effect on lymphangiogenesis, and lymphatic metastasis in mouse models of lung adenocarcinoma, it might be a therapeutic option for tumor lymphatic metastasis. In this study, we retrospectively analyzed the efficacy and safety of anlotinib for PLC in patients with Non-small Cell Lung Cancer (NSCLC). Methods: We retrospectively investigated NSCLC patients with PLC at our hospital between May 2018 and November 2020, who received anlotinib monotherapy or combined therapy for PLC. Data were analyzed for progression-free survival (PFS), overall survival (OS), objective response rate(ORR), disease control rate(DCR) and adverse events (AE). The impact of clinical and genomic factors on PFS and OS were also assessed. Results: A total of 14 patients were enrolled with a median age of 64 years. 10(71.4%) were male, 4(28.6%) has smoking history, 10(71.4%) of patients had a performance status of 2-3. 9, 3, 2 patients had TP53 mutation, EGFR mutation, ALK fusion respectively. 9(64.3%) patients received anlotinib monotherapy. Of 14 patients, 8 achieved partial response (PR), 5 presented stable disease (SD), 1 had progressed disease. The ORR and DCR were 57.1% and 92.9% respectively. The median PFS was 3.1 months (95% CI: 2.0-4.2), the median OS for 1, 2, ≥3 line were 13 months, 7.2 months, 5.2 months, respectively. Median PFS and OS (≥3 line) were significantly longer for patients with TP53-mutant tumors compared with those with TP53–wild-type tumors (median PFS: 7 vs. 1.1 months, median OS (≥3 line): 6.8 vs. 1.9 months). No difference of PFS and OS (≥3 line) was found between EGFR or ALK alteration and the corresponding wild type patients. The most frequently reported AEs were high blood pressure (11, 78.6%), hand foot syndrome (6, 42.9%), diarrhea (5, 35.7%), fatigue (4, 28.6%), hoarseness (3, 21.4%), proteinuria (2, 14.3%) and stomatitis (2, 14.3%). Conclusions: Anlotinib presented favorable efficacy in patients with pulmonary lymphangitic carcinomatosis and conferred considerable survival benefit compared with previous studies, especially in patients harboring TP53 mutations. The AEs were manageable. These indicated that anlotinib can be a promising therapeutic treatment of PLC. More clinical data is needed to validate this finding.

The impact of HIV-related neuropsychological dysfunction on driving behavior

2000 ◽  
Vol 6 (7) ◽  
pp. 854-854 ◽  
Author(s):  
THOMAS D. MARCOTTE ◽  
ROBERT K. HEATON ◽  
TANYA WOLFSON ◽  
MICHAEL J. TAYLOR ◽  
OMAR ALHASSOON ◽  
...  
Keyword(s):  
Traumatic Brain Injury ◽  
Positive Predictive Value ◽  
Predictive Value ◽  
Visual Inspection ◽  
Driving Behavior ◽  
Personality Change ◽  
Impaired Consciousness ◽  
Neuropsychological Dysfunction ◽  
Gcs Score ◽  
The Impact

The following is a correction for an error that occurred in the Journal of the International Neuropsychological Society, Vol. 6, No. 3. The error occurred in the article titled “Personality change disorder in children and adolescents following traumatic brain injury,” pp. 279–289, by Max et al. On page 285, under the subheading “Injury Factors,” beginning with the second sentence in the first paragraph, the statement should read:Visual inspection of the distribution of PC relative to lowest post-resuscitation GCS scores revealed that a cut-off of lowest post-resuscitation GCS score of 4 or less versus more than 4 yielded a sensitivity for a diagnosis of persistent PC of 9/14 (64.3%), specificity of 18/23 (78.3%), and a positive predictive value of 0.64 (9.14).A cut-off of duration of impaired consciousness of 100 hr or less versus more than 100 hr yielded a sensitivity for a diagnosis of persistent PC of 11/14 (78.6%), specificity of 20/23 (87.0%), and a positive predictive value (PPV) of 0.79 (11/14).

Time-dependent effect of intensity of smoking and of occupational exposure to asbestos on the risk of lung cancer: results from the ICARE case–control study

2018 ◽  
Vol 75 (8) ◽  
pp. 586-592 ◽  
Author(s):  
Emilie Lévêque ◽  
Aude Lacourt ◽  
Danièle Luce ◽  
Marie-Pierre Sylvestre ◽  
Pascal Guénel ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Occupational Exposure ◽  
Case Control Study ◽  
Asbestos Exposure ◽  
Case Control ◽  
Smoking History ◽  
Air Concentration ◽  
Exposure History ◽  
The Impact ◽  
Control Study

ObjectiveTo estimate the impact of intensity of both smoking and occupational exposure to asbestos on the risk of lung cancer throughout the whole exposure history.MethodsData on 2026 male cases and 2610 male controls came from the French ICARE (Investigation of occupational and environmental causes of respiratory cancers) population-based, case–control study. Lifetime smoking history and occupational history were collected from standardised questionnaires and face-to-face interviews. Occupational exposure to asbestos was assessed using a job exposure matrix. The effects of annual average daily intensity of smoking (reported average number of cigarettes smoked per day) and asbestos exposure (estimated average daily air concentration of asbestos fibres at work) were estimated using a flexible weighted cumulative index of exposure in logistic regression models.ResultsIntensity of smoking in the 10 years preceding diagnosis had a much stronger association with the risk of lung cancer than more distant intensity. By contrast, intensity of asbestos exposure that occurred more than 40 years before diagnosis had a stronger association with the risk of lung cancer than more recent intensity, even if intensity in the 10 years preceding diagnosis also had a significant effect.ConclusionOur results illustrate the dynamic of the effect of intensity of both smoking and occupational exposure to asbestos on the risk of lung cancer. They confirm that the timing of exposure plays an important role, and suggest that standard analytical methods assuming equal weights of intensity over the whole exposure history may be questionable.

Sign in / Sign up

Export Citation Format

Share Document