Behzad Naderalvojoud

Background: Acute care use (ACU) represents a major economic burden in oncology, which can ideally be prevented. Existing models effectively predict such events. Objective: We aimed to quantify the cost savings achieved by implementing a model to predict ACU in oncology patients undergoing systemic therapy. Methods: This retrospective cohort study analyzed patients with cancer at an academic medical center from 2010 to 2022. We included patients who received systemic therapy and identified ACU events occurring after treatment initiation, excluding those with known death dates within the study period. Data on ACU-related expenses were gathered from Medicare claims and mapped to service codes in electronic health records, yielding average daily costs for each patient over 180 days following the start of therapy. The exposure was an ACU event. Results: The main outcome was the average daily cost per patient at the end of the first 180 days of systemic therapy. We observed that expense accumulation flattened earlier and more rapidly among non-ACU patients. This study included 20,556 patients, of whom 3820 (18.58%) experienced at least 1 ACU. The average daily cost per patient for those with and without ACU was US $94.62 (SD US $72.54; 95% CI US $92.32-$96.92) and US $53.28 (SD US $59.92; 95% CI US $52.37-$54.19), respectively. The average total cost per ACU and non-ACU patient was US $17,031.92 (SD US $13,056.63; 95% CI US $16,616.74-$17,445.09) and US $9591.06 (SD US $10,785.83; 95% CI US $9427.64-$9754.48), respectively. To estimate the long-term financial impact of deploying the predictive model, we conducted a cost-benefit analysis based on an annual cohort size of 2177 patients. In the first year alone, the model yielded projected savings of US $910,000. By year 6, projected savings grew to US $9.46 million annually. The cumulative avoided costs over a 6-year deployment period totaled approximately US $31.11 million. These estimates compared the baseline cost model to the intervention model assuming a prevention rate of 35% for preventable ACU events and an average ACU cost of US $17,031.92 (SD US $13,037). Conclusions: Predictive analytics can significantly reduce costs associated with ACU events, enhancing economic efficiency in cancer care. Further research is needed to explore potential health benefits.

Objectives: The growing use of machine learning (ML) in healthcare raises concerns about how data biases affect real-world model performance. While existing frameworks evaluate algorithmic fairness, they often overlook the impact of bias on generalizability and clinical utility, which are critical for safe deployment. Building on prior methods, this study extends bias analysis to include clinical utility, addressing a key gap between fairness evaluation and decision-making. Materials and Methods: We applied a 3-phase evaluation to a previously developed model predicting prolonged opioid use (POU), validated on Veterans Health Administration (VHA) data. The analysis included internal and external validation, model retraining on VHA data, and subgroup evaluation across demographic, vulnerable, risk, and comorbidity groups. We assessed performance using area under the receiver operating characteristic curve (AUROC), calibration, and decision curve analysis, incorporating standardized net-benefits to evaluate clinical utility alongside fairness and generalizability. Results: The internal cohort (N = 41 929) had a 14.7% POU prevalence, compared to 34.3% in the external VHA cohort (N = 397 150). The model’s AUROC decreased from 0.74 in the internal test cohort to 0.70 in the full external cohort. Subgroup-level performance averaged 0.69 (SD = 0.01), showing minimal deviation from the external cohort overall. Retraining on VHA data improved AUROCs to 0.82. Clinical utility analysis showed systematic shifts in net-benefit across threshold probabilities. Discussion: While the POU model showed generalizability and fairness internally, external validation and retraining revealed performance and utility shifts across subgroups. Conclusion: Population-specific biases affect clinical utility—an often-overlooked dimension in fairness evaluation—a key need to ensure equitable benefits across diverse patient groups.

Objectives: Existing ophthalmology studies for clinical phenotypes identification in real-world datasets (RWD) rely exclusively on structured data elements (SDE). We evaluated the performance, generalizability, and fairness of multimodal ensemble models that integrate real-world SDE and free-text data compared to SDE-only models to identify patients with glaucoma. Materials and Methods: This is a retrospective cross-sectional study involving 2 health systems- University of Michigan (UoM) and Stanford University (SU). It involves 1728 patients visiting eye clinics during 2012-2021. Free-text embeddings extracted using BioClinicalBERT were combined with SDE. EditedNearestNeighbor (ENN) undersampling and Borderline-Synthetic Minority Over-sampling Technique (bSMOTE) addressed class imbalance. Lasso Regression (LR), Random Forest (RF), Support Vector Classifier (SVC) models were trained on UoM imbalanced (imb) and resampled data along with bagging ensemble method. Models were externally validated with SU data. Fairness was assessed using equalized odds difference (EOD) and Target Probability Difference (TPD). Results: Among 900 and 828 patients from UoM and SU, 10% and 23% respectively had glaucoma as confirmed by ophthalmologists. At UoM, multimodal LRimb (F1 = 76.60 [61.90-88.89]; AUROC = 95.41 [87.01-99.63]) outperformed unimodal RFimb (F1 = 69.77 [52.94-83.64]; AUROC = 97.72 [95.95-99.18]) and ICD-coding method (F1 = 53.01 [39.51-65.43]; AUROC = 90.10 [84.59-93.93]). Bagging (BM = LRENN + LRbSMOTE) improved performance achieving an F1 of 83.02 [70.59-92.86] and AUROC of 97.59 [92.98-99.88]. During external validation BM achieved the highest F1 (68.47 [62.61-73.75]), outperforming unimodal (F1 = 51.26 [43.80-58.13]) and multimodal LRimb (F1 = 62.46 [55.95-68.24]). BM EOD revealed lower disparities for sex (<0.1), race (<0.5) and ethnicity (<0.5), and had least uncertainty using TDP analysis as compared to traditional models. Discussion: Multimodal ensemble models integrating structured and unstructured EHR data outperformed traditional SDE models achieving fair predictions across demographic sub-groups. Among ensemble methods, bagging demonstrated better generalizability than stacking, particularly when training data is limited. Conclusion: This approach can enhance phenotype discovery to enable future research studies using RWD, leading to better patient management and clinical outcomes.

UNSTRUCTURED Acute care utilization (ACU) stands for a major economic burden in oncology, which can ideally be prevented. Existing models effectively predict such events. We aim to quantify the cost savings achieved by implementing a model to predict ACU in oncology patients undergoing systemic therapy. This retrospective cohort study analyzed 20,556 patients at an academic medical center from 2010 to 2022. We included patients whose treatment began on day one of therapy, excluding those with known death dates within study period. Data on ACU-related expenses were gathered from Medicare claims and mapped to service codes in electronic health records, yielding average daily costs for each patient over 180 days. The exposure was an ACU event. The main outcome was the average daily cost per patient by the end of the first year of systemic therapy. The study included 20,556 patients. The average daily cost per patient with ACU was US $94.62 ± 72.54 (92.32, 96.92) (mean ± SD, 95% CI) and without ACU was $53.28 ± 59.92 (92.32, 54.19). The average total cost per ACU patient was US $17,031.92 ± 13,056.63 (16,616.74, 17,445.09), and $9,591.06 ± 10,785.83 (9,427.64, 9,754.48) for those without an ACU. Based on an average of 2,177 patients annually, the model predicts a savings of $910,000 in the first year, growing to $9.46 million over six years, with cumulative savings of $31.11 million. Predictive analytics can significantly reduce costs associated with ACU events, enhancing economic efficiency in cancer care. Further research is needed to explore potential health benefits.

Predictive models show promise in healthcare, but their successful deployment is challenging due to limited generalizability. Current external validation often focuses on model performance with restricted feature use from the original training data, lacking insights into their suitability at external sites. Our study introduces an innovative methodology for evaluating features during both the development phase and the validation, focusing on creating and validating predictive models for post-surgery patient outcomes with improved generalizability. Electronic health records (EHRs) from 4 countries (United States, United Kingdom, Finland, and Korea) were mapped to the OMOP Common Data Model (CDM), 2008-2019. Machine learning (ML) models were developed to predict post-surgery prolonged opioid use (POU) risks using data collected 6 months before surgery. Both local and cross-site feature selection methods were applied in the development and external validation datasets. Models were developed using Observational Health Data Sciences and Informatics (OHDSI) tools and validated on separate patient cohorts. Model development included 41 929 patients, 14.6% with POU. The external validation included 31 932 (UK), 23 100 (US), 7295 (Korea), and 3934 (Finland) patients with POU of 44.2%, 22.0%, 15.8%, and 21.8%, respectively. The top-performing model, Lasso logistic regression, achieved an area under the receiver operating characteristic curve (AUROC) of 0.75 during local validation and 0.69 (SD = 0.02) (averaged) in external validation. Models trained with cross-site feature selection significantly outperformed those using only features from the development site through external validation (P < .05). Using EHRs across four countries mapped to the OMOP CDM, we developed generalizable predictive models for POU. Our approach demonstrates the significant impact of cross-site feature selection in improving model performance, underscoring the importance of incorporating diverse feature sets from various clinical settings to enhance the generalizability and utility of predictive healthcare models.

Seasonal influenza is a leading cause of death in the U.S., causing significant morbidity, mortality, and economic burden. Despite the proven efficacy of vaccinations, rates remain notably low, especially among Medicaid enrollees. Leveraging Medicaid claims data, this study characterizes influenza vaccination rates among Medicaid enrollees and aims to elucidate factors influencing vaccine uptake, providing insights that might also be applicable to other vaccine-preventable diseases, including COVID-19. This study used Medicaid claims data from nine U.S. states (2016–2021], encompassing three types of claims: fee-for-service, major Medicaid managed care plan, and combined. We included Medicaid enrollees who had an in-person healthcare encounter during an influenza season in this period, excluding those under 6 months of age, over 65 years, or having telehealth-only encounters. Vaccination was the primary outcome, with secondary outcomes involving in-person healthcare encounters. Chi-square tests, multivariable logistic regression, and Fisher’s exact test were utilized for statistical analysis. A total of 20,868,910 enrollees with at least one healthcare encounter in at least one influenza season were included in the study population between 2016 and 2021. Overall, 15% (N = 3,050,471) of enrollees received an influenza vaccine between 2016 and 2021. During peri-COVID periods, there was an increase in vaccination rates among enrollees compared to pre-COVID periods, from 14% to 16%. Children had the highest influenza vaccination rates among all age groups at 29%, whereas only 17% were of 5–17 years, and 10% were of the 18–64 years were vaccinated. We observed differences in the likelihood of receiving the influenza vaccine among enrollees based on their health conditions and medical encounters. In a study of Medicaid enrollees across nine states, 15% received an influenza vaccine from July 2016 to June 2021. Vaccination rates rose annually, peaking during peri-COVID seasons. The highest uptake was among children (6 months–4 years), and the lowest was in adults (18–64 years). Female gender, urban residency, and Medicaid-managed care affiliation positively influenced uptake. However, mental health and substance abuse disorders decreased the likelihood. This study, reliant on Medicaid claims data, underscores the need for outreach services.

This paper investigates the effect of the architectural design of deep learning models in combination with a feature engineering approach considering the temporal variation in the features in the case of tropospheric ozone forecasting. Although deep neural network models have shown successful results by extracting features automatically from raw data, their performance in the domain of air quality forecasting is influenced by different feature analysis approaches and model architectures. This paper proposes a simple but effective analysis of tropospheric ozone time series data that can reveal temporal phases of the ozone evolution process and assist neural network models to reflect these temporal variations. We demonstrate that addressing the ozone evolution phases when developing the model architecture improves the performance of deep neural network models. As a result, we evaluated our approach on the CNN model and showed that not only does it improve the performance of the CNN model, but also that the CNN model in combination with our approach boosts the performance of the other deep neural network models such as LSTM. The development of the CNN, LSTM-CNN, and CNN-LSTM models using the proposed approach improved the prediction performance of the models by 3.58%, 1.68%, and 3.37%, respectively.

This paper proposes four novel term evaluation metrics to represent documents in the text categorization where class distribution is imbalanced. These metrics are achieved from the revision of the four common term evaluation metrics:chi-square,information gain,odds ratio, andrelevance frequency. While the common metrics require a balanced class distribution, our proposed metrics evaluate the document terms under an imbalanced distribution. They calculate the degree of relatedness of terms with respect to minor and major classes by considering their imbalanced distribution. Using these metrics in the document representation makes a better distinction between the documents of the minor and major classes and improves the performance of machine learning algorithms. The proposed metrics are assessed over three popular benchmarks (two subsets of Reuters-21578 and WebKB) by using four classification algorithms: support vector machines, naive Bayes, decision trees, and centroid-based classifiers. Our empirical results indicate that the proposed metrics outperform the common metrics in the imbalanced text categorization.