Jagpreet Chhatwal

Probabilistic Computer Model Developed from Clinical Data in National Mammography Database Format to Classify Mammographic Findings

PURPOSE To determine whether a Bayesian network trained on a large database of patient demographic risk factors and radiologist-observed findings from consecutive clinical mammography examinations can exceed radiologist performance in the classification of mammographic findings as benign or malignant. MATERIALS AND METHODS The institutional review board exempted this HIPAA-compliant retrospective study from requiring informed consent. Structured reports from 48 744 consecutive pooled screening and diagnostic mammography examinations in 18 269 patients from April 5, 1999 to February 9, 2004 were collected. Mammographic findings were matched with a state cancer registry, which served as the reference standard. By using 10-fold cross validation, the Bayesian network was tested and trained to estimate breast cancer risk by using demographic risk factors (age, family and personal history of breast cancer, and use of hormone replacement therapy) and mammographic findings recorded in the Breast Imaging Reporting and Data System lexicon. The performance of radiologists compared with the Bayesian network was evaluated by using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. RESULTS The Bayesian network significantly exceeded the performance of interpreting radiologists in terms of AUC (0.960 vs 0.939, P = .002), sensitivity (90.0% vs 85.3%, P < .001), and specificity (93.0% vs 88.1%, P < .001). CONCLUSION On the basis of prospectively collected variables, the evaluated Bayesian network can predict the probability of breast cancer and exceed interpreting radiologist performance. Bayesian networks may help radiologists improve mammographic interpretation.

Optimal Breast Biopsy Decision-Making Based on Mammographic Features and Demographic Factors

Breast cancer is the most common non-skin cancer affecting women in the United States, where every year more than 20 million mammograms are performed. Breast biopsy is commonly performed on the suspicious findings on mammograms to confirm the presence of cancer. Currently, 700,000 biopsies are performed annually in the U.S.; 55%-85% of these biopsies ultimately are found to be benign breast lesions, resulting in unnecessary treatments, patient anxiety, and expenditures. This paper addresses the decision problem faced by radiologists: When should a woman be sent for biopsy based on her mammographic features and demographic factors? This problem is formulated as a finite-horizon discrete-time Markov decision process. The optimal policy of our model shows that the decision to biopsy should take the age of patient into account; particularly, an older patients risk threshold for biopsy should be higher than that of a younger patient. When applied to the clinical data, our model outperforms radiologists in the biopsy decision-making problem. This study also derives structural properties of the model, including sufficiency conditions that ensure the existence of a control-limit type policy and nondecreasing control-limits with age.

Informatics in Radiology: Comparison of Logistic Regression and Artificial Neural Network Models in Breast Cancer Risk Estimation

Computer models in medical diagnosis are being developed to help physicians differentiate between healthy patients and patients with disease. These models can aid in successful decision making by allowing calculation of disease likelihood on the basis of known patient characteristics and clinical test results. Two of the most frequently used computer models in clinical risk estimation are logistic regression and an artificial neural network. A study was conducted to review and compare these two models, elucidate the advantages and disadvantages of each, and provide criteria for model selection. The two models were used for estimation of breast cancer risk on the basis of mammographic descriptors and demographic risk factors. Although they demonstrated similar performance, the two models have unique characteristics-strengths as well as limitations-that must be considered and may prove complementary in contributing to improved clinical decision making.

Hepatitis C Disease Burden in the United States in the era of oral direct-acting antivirals

Oral direct‐acting antivirals (DAAs) represent a major advance in hepatitis C virus (HCV) treatment. Along with recent updates in HCV screening policy and expansions in insurance coverage, treatment demand in the United States is changing rapidly. Our objective was to project the characteristics and number of people needing antiviral treatment and HCV‐associated disease burden in the era of oral DAAs. We used a previously developed and validated Hepatitis C Disease Burden Simulation model (HEP‐SIM). HEP‐SIM simulated the actual clinical management of HCV from 2001 onward, which included antiviral treatment with pegylated interferon (Peg‐IFN)‐based therapies as well as the recent oral DAAs, risk‐based and birth‐cohort HCV screening, and the impact of the Affordable Care Act. We also simulated two hypothetical scenarios—no treatment and treatment with Peg‐IFN‐based therapies only. We estimated that in 2010, 2.5 (95% confidence interval [CI], 1.9‐3.1) million noninstitutionalized people were viremic, which dropped to 1.9 (95% CI, 1.4‐2.6) million in 2015, and projected to drop below 1 million by 2020. A total of 1.8 million HCV patients will receive HCV treatment from the launch of oral DAAs in 2014 until 2030. Based on current HCV management practices, it will take 4‐6 years to treat the majority of patients aware of their disease. However, 560,000 patients would still remain unaware by 2020. Even in the oral DAA era, 320,000 patients will die, 157,000 will develop hepatocellular carcinoma, and 203,000 will develop decompensated cirrhosis in the next 35 years. Conclusions: HCV‐associated disease burden will still remain substantial in the era of oral DAAs. Increasing HCV screening and treatment capacity is essential to further decreasing HCV burden in the United States. (Hepatology 2016;64:1442‐1450)

Cost-effectiveness of boceprevir in patients previously treated for chronic hepatitis C genotype 1 infection in the United States.

OBJECTIVES The phase 3 trial, Serine Protease Inhibitor Boceprevir and PegIntron/Rebetol-2 (RESPOND-2), demonstrated that the addition of boceprevir (BOC) to peginterferon-ribavirin (PR) resulted in significantly higher rates of sustained virologic response (SVR) in previously treated patients with chronic hepatitis C virus (HCV) genotype-1 infection as compared with PR alone. We evaluated the cost-effectiveness of treatment with BOC in previously treated patients with chronic hepatitis C in the United States using treatment-related data from RESPOND-2 and PROVIDE studies. METHODS We developed a Markov cohort model to project the burden of HCV disease, lifetime costs, and quality-adjusted life-years associated with PR and two BOC-based therapies-response-guided therapy (BOC/RGT) and fixed-duration therapy for 48 weeks (BOC/PR48). We estimated treatment-related inputs (efficacy, adverse events, and discontinuations) from clinical trials and obtained disease progression rates, costs, and quality-of-life data from published studies. We estimated the incremental cost-effectiveness ratio (ICER) for BOC-based regimens as studied in RESPOND-2, as well as by patients prior response to treatment and the IL-28B genotype. RESULTS BOC-based regimens were projected to reduce the lifetime incidence of liver-related complications by 43% to 53% in comparison with treatment with PR. The ICER of BOC/RGT in comparison with that of PR was

Economic Burden of Chronic Lymphocytic Leukemia in the Era of Oral Targeted Therapies in the United States

30,200, and the ICER of BOC/PR48 in comparison with that of BOC/RGT was

Breast cancer risk estimation with artificial neural networks revisited: discrimination and calibration.

91,500. At a willingness-to-pay threshold of

Optimal timing of hepatitis C treatment for patients on the liver transplant waiting list

50,000, the probabilities of BOC/RGT and BOC/PR48 being the preferred option were 0.74 and 0.25, respectively. CONCLUSIONS In patients previously treated for chronic HCV genotype-1 infection, BOC was projected to increase quality-adjusted life-years and reduce the lifetime incidence of liver complications. In addition, BOC-based therapies were projected to be cost-effective in comparison with PR alone at commonly used willingness-to-pay thresholds.

Direct-Acting Antiviral Agents for Patients With Hepatitis C Virus Genotype 1 Infection Are Cost-Saving

Purpose Oral targeted therapies represent a significant advance for the treatment of patients with chronic lymphocytic leukemia (CLL); however, their high cost has raised concerns about affordability and the economic impact on society. Our objective was to project the future prevalence and cost burden of CLL in the era of oral targeted therapies in the United States. Methods We developed a simulation model that evaluated the evolving management of CLL from 2011 to 2025: chemoimmunotherapy (CIT) as the standard of care before 2014, oral targeted therapies for patients with del(17p) and relapsed CLL from 2014, and for first-line treatment from 2016 onward. A comparator scenario also was simulated where CIT remained the standard of care throughout. Disease progression and survival parameters for each therapy were based on published clinical trials. Results The number of people living with CLL in the United States is projected to increase from 128,000 in 2011 to 199,000 by 2025 (55% increase) due to improved survival; meanwhile, the annual cost of CLL management will increase from

Are high drug prices for hematologic malignancies justified? A critical analysis.

0.74 billion to