Since May 2022, over 64,000 Monkeypox cases have been confirmed globally up until September 2022. The United States leads the world in cases, with over 25,000 cases nationally. This recent escalation of the Monkeypox outbreak has become a severe and urgent worldwide public health concern. We aimed to develop an efficient forecasting tool that allows health experts to implement effective prevention policies for Monkeypox and shed light on the case development of diseases that share similar characteristics to Monkeypox. This research utilized five machine learning models, namely, ARIMA, LSTM, Prophet, NeuralProphet, and a stacking model, on the Monkeypox datasets from the CDC official website to forecast the next 7-day trend of Monkeypox cases in the United States. The result showed that NeuralProphet achieved the most optimal performance with a RMSE of 49.27 and R2 of 0.76. Further, the final trained NeuralProphet was employed to forecast seven days of out-of-sample cases. On the basis of cases, our model demonstrated 95% accuracy.

BackgroundDevelopment of severe immune-related adverse events (irAEs) is a major predicament to stop treatment with immune checkpoint inhibitors, even though tumor progression is suppressed. However, no effective early phase biomarker has been established to predict irAE until now.MethodThis study retrospectively used the data of four international, multi-center clinical trials to investigate the application of blood test biomarkers to predict irAEs in atezolizumab-treated advanced non-small cell lung cancer (NSCLC) patients. Seven machine learning methods were exploited to dissect the importance score of 21 blood test biomarkers after 1,000 simulations by the training cohort consisting of 80%, 70%, and 60% of the combined cohort with 1,320 eligible patients.ResultsXGBoost and LASSO exhibited the best performance in this study with relatively higher consistency between the training and test cohorts. The best area under the curve (AUC) was obtained by a 10-biomarker panel using the XGBoost method for the 8:2 training:test cohort ratio (training cohort AUC = 0.692, test cohort AUC = 0.681). This panel could be further narrowed down to a three-biomarker panel consisting of C-reactive protein (CRP), platelet-to-lymphocyte ratio (PLR), and thyroid-stimulating hormone (TSH) with a small median AUC difference using the XGBoost method [for the 8:2 training:test cohort ratio, training cohort AUC difference = −0.035 (p < 0.0001), and test cohort AUC difference = 0.001 (p=0.965)].ConclusionBlood test biomarkers currently do not have sufficient predictive power to predict irAE development in atezolizumab-treated advanced NSCLC patients. Nevertheless, biomarkers related to adaptive immunity and liver or thyroid dysfunction warrant further investigation.

BackgroundImmune checkpoint inhibitor (ICI) therapy is a major breakthrough for non-small cell lung cancer (NSCLC) treatment given its high efficacy and tolerable toxicity. Although pre-treatment PD-L1 expression levels and tumor mutation burden (TMB) may serve as prognostic biomarkers for patient stratification, effective predictive biomarkers are lacking. Blood cell count test (BCT) is a routine, regular blood test conducted before and during treatment to provide a direct overview of the immune landscape based on the counts of various types of immune cells (ICs). For instance, previous studies showed that neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) both indicate poor treatment outcomes of ICI therapy of NSCLC patients.MethodsThis study analyzed relevant combinations of IC counts from four international, multi-center clinical trials of OAK, BIRCH, POPLAR and FIR to conduct post-hoc analysis of NSCLC patients undergoing atezolizumab (anti-PD-L1) single-agent treatment (n = 1,479), while docetaxel single-agent treatment (n = 707) was used as control. BCT was conducted at three timepoints, T1 to T3, during pre-treatment and on the first day of treatment cycles 3 and 5, which correspond to baseline, 6, and 12 weeks on-treatment, respectively. Univariate and multivariate Cox regression analysis was conducted to identify NLR_T3, PLR_T3 and neutrophil-to-monocyte (NMR) at T2 as early BCT biomarkers that may predict ICI efficacy. Next, univariate and multivariate Cox proportional hazards regression analysis were used to identify any effective combination of BCT biomarkers and their absolute cutoff values that may serve as predictive biomarkers to predict atezolizumab treatment outcomes. Lastly, combinations of these BCT biomarkers were tested to optimize BCTscore model for clinical evaluation.ResultsThe final BCT biomarker combination, comprising of the BCT biomarkers of NLR and PLR at 12 weeks on-treatment (T3) and NMR at 6 weeks on-treatment (T2), was identified to be a strong predictive biomarker for atezolizumab (Ate)-treated NSCLC patients in comparison to docetaxel (Dtx)-treated patients regarding overall survival (OS) (BCTscore low-risk: HR Ate vs Dtx = 1.54 (95% CI: 1.04–2.27), P = 0.036; high-risk: HR Ate vs Dtx = 0.84 (95% CI: 0.62–1.12), P = 0.236). Our BCTscore model consistently exhibited better OS AUC in the OAK (AUC12month=0.696), BIRCH (AUC12month=0.672) and POPLAR+FIR studies (AUC12month=0.727) than that of each of the three BCT biomarkers in these three studies.ConclusionsThe BCTscore of NLR at 12 weeks, PLR at 12 weeks and NMR at 6 weeks is a strong efficacy predictive biomarker for atezolizumab-treated NSCLC patients.AcknowledgementsThe authors declare no conflict of interest. This publication is based on research using data from Genentech, Inc. (one of subsidiaries of Roche Group) that has been made available through Vivli, Inc (Data Request ID: 5935; Lead Investigator: Dr. Jian-Guo Zhou). Vivli has not contributed to or approved, and is not in any way responsible for, the contents of this publication.Trial RegistrationDeidentified individual participant data from the single-arm phase II studies of FIR study (NCT01846416; as of Janurary 7, 2015) [Spigel2018] and BIRCH (NCT02031458; as of May 28, 2015) [Peters2017], and the two-arm randomized controlled trials (RCT) of the POPLAR phase II study (NCT01903993; as of May 8, 2015) [Fehrenbacher2016] and the OAK phase III study (NCT02008227; as of July 7, 2016) [Rittmeyer2017] were made available by Genentech Inc. and accessed through the secure Vivli online platform.Ethics ApprovalBoth studies were approved by the respective national ethics committees and institutional review boards and written informed consent was obtained from all patients.

To maximize the accuracy and efficiency of the USMLE Step 2 clinical skills examination evaluation process, we proposed an ensemble model that helps automatically score patient notes written by test takers instead of physician raters manually scoring them by appropriate features. This research used DeBERTa-base, DeBERTa-large, and DeBERTa-v3-large as three base models and ensembled them with two different approaches: Note-based and Character-based. We concluded that LSTM Note-based ensemble topped the overall performance with an F1-score of 0.81747 on the validation data, 48% higher than the F1-score of the most effective base model (DeBERTa-v3-large). Furthermore, the performance is robust when breakdown by clinical cases and folds and applied to the testing set (0.88737 accuracy). Finally, the ensemble approach to different base models (BERT-base-uncased and BERT-large-uncased) achieved a 32% F-1 score boost. We demonstrated the ensemble model has excellent potential to improve performance in general Natural Language Understanding tasks.

Introduction Immune checkpoint inhibitor (ICI) therapy is a major breakthrough in non-small cell lung cancer (NSCLC) treatment. However, valid predictive biomarkers are lacking. Blood cell count test (BCT) provides a direct quantification of various types of immune cells (ICs) to reveal the immune landscape to predict ICI treatment. Methods This study analyzed four international, multi-center clinical trials (OAK, BIRCH, POPLAR and FIR trials) to conduct post-hoc analyses of NSCLC patients undergoing atezolizumab (anti-PD-L1) single-agent treatment (n = 1,479) or docetaxel single-agent treatment (n = 707). BCT was conducted at three timepoints: pre-treatment (T1), the first day of treatment cycle 3 (T2), and first day of treatment cycle 5 (T3). Univariate and multivariate Cox regression analyses were conducted to identify early BCT biomarkers to predict atezolizumab treatment outcomes in NSCLC patients. Results The BCT biomarkers of neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) at timepoint T3 and neutrophil-to-monocyte ratio (NMR) at timepoint T2 were identified as strong predictive biomarkers for atezolizumab (Ate)-treated NSCLC patients in comparison to docetaxel (Dtx)-treated patients regarding overall survival (OS) (BCTscore low-risk: HR Ate vs Dtx = 1.54 (95% CI: 1.04-2.27), P = 0.036; high-risk: HR Ate vs Dtx = 0.84 (95% CI: 0.62-1.12), P = 0.236). This identified BCTscore model showed better OS AUC in the OAK (AUC12month=0.696), BIRCH (AUC12month=0.672) and POPLAR+FIR studies (AUC12month=0.727) than that of each of the three single BCT biomarkers. Conclusion The BCTscore model is a valid predictive and prognostic biomarker for atezolizumab-treated NSCLC patients.