Deep learning system for true- and pseudo-invasion in colorectal polyps.

Over 15 million colonoscopies were performed yearly in North America, during which biopsies were taken for pathological examination to identify abnormalities. Distinguishing between true- and pseudo-invasion in colon polyps is critical in treatment planning. Surgical resection of the colon is often the treatment option for true invasion, whereas observation is recommended for pseudo-invasion. The task of identifying true- vs pseudo-invasion, however, could be highly challenging. There is no specialized software tool for this task, and no well-annotated dataset is available. In our work, we obtained (only) 150 whole-slide images (WSIs) from the London Health Science Centre. We built three deep neural networks representing different magnifications in WSIs, mimicking the workflow of pathologists. We also built an online tool for pathologists to annotate WSIs to train our deep neural networks. Results showed that our novel system classifies tissue types with 95.3% accuracy and differentiates true- and pseudo-invasions with 83.9% accuracy. The system's efficiency is comparable to an expert pathologist. Our system can also be easily adjusted to serve as a confirmatory or screening tool. Our system (available at http://ai4path.ca ) will lead to better, faster patient care and reduced healthcare costs.

The Growing Economic and Clinical Burden of Nonalcoholic Steatohepatitis (NASH) in the United States.

Background: Nonalcoholic steatohepatitis (NASH) is a cause of chronic liver disease. Aim: Model the burden of NASH in the United States according to obesity. Methods: The discrete-time Markov model comprised adult NASH subjects moving through 9 health states and 3 absorbing death states (liver, cardiac, and other deaths) with 1-year cycles and a 20-year horizon. Given that reliable natural history data for NASH are not available, transition probabilities were estimated from the literature and population-based data. These rates were disaggregated to determine age-obesity group rates by applying estimated age-obesity patterns. The model considers 2019 prevalent NASH cases and new incident NASH cases (2020-2039), assuming that recent trends will continue. Annual per-patient costs by health state were based on published data. Costs were standardized to 2019 US dollars and inflated by 3% annually. Results: NASH cases in the United States are forecasted to increase by +82.6%, from 11.61 million (2020) to 19.53 million (2039). During the same period, cases of advanced liver disease increased +77.9%, from 1.51 million to 2.67 million, while its proportion remained stable (13.46%-13.05%). Similar patterns were observed in both obese and non-obese NASH. Among NASH, 18.71 million overall deaths, 6.72 million cardiac-specific deaths, and 1.71 million liver-specific deaths were observed by 2039. During this period, the projected cumulative direct healthcare costs were $1208.47 billion (obese NASH) and $453.88 billion (non-obese NASH). By 2039, the projected NASH attributable healthcare cost per patient increased from $3636 to $6968. Conclusions: There is a substantial and growing clinical and economic burden of NASH in the United States.

Cost-Effectiveness of Imipenem/Cilastatin/Relebactam Compared with Colistin in Treatment of Gram-Negative Infections Caused by Carbapenem-Non-Susceptible Organisms.

INTRODUCTION: Imipenem/cilastatin/relebactam (IMI/REL), a combination ß-lactam antibiotic (imipenem) with a novel ß-lactamase inhibitor (relebactam), is an efficacious and well-tolerated option for the treatment of hospitalized patients with gram-negative (GN) bacterial infections caused by carbapenem-non-susceptible (CNS) pathogens. This study examines cost-effectiveness of IMI/REL vs. colistin plus imipenem (CMS + IMI) for the treatment of infection(s) caused by confirmed CNS pathogens. METHODS: We developed an economic model comprised of a decision-tree depicting initial hospitalization, and a Markov model projecting long-term health and economic impacts following discharge. The decision tree, informed by clinical data from RESTORE-IMI 1 trial, modeled clinical outcomes (mortality, cure rate, and adverse events including nephrotoxicity) in the two comparison scenarios of IMI/REL versus CMS + IMI for patients with CNS GN infection. Subsequently, a Markov model translated these hospitalization stage outcomes (i.e., death or uncured infection) to long-term consequences such as quality-adjusted life years (QALYs). Sensitivity analyses were conducted to test the model robustness. RESULTS: IMI/REL compared to CMS + IMI demonstrated a higher cure rate (79.0% vs. 52.0%), lower mortality (15.2% vs. 39.0%), and reduced nephrotoxicity (14.6% vs. 56.4%). On average a patient treated with IMI/REL vs. CMS + IMI gained additional 3.7 QALYs over a lifetime. Higher drug acquisition costs for IMI/REL were offset by shorter hospital length of stay and lower AE-related costs, which result in net savings of $11,015 per patient. Sensitivity analyses suggested that IMI/REL has a high likelihood (greater than 95%) of being cost-effective at a US willingness-to-pay threshold of $100,000-150,000 per QALY. CONCLUSIONS: For patients with confirmed CNS GN infection, IMI/REL could yield favorable clinical outcomes and may be cost-saving-as the higher IMI/REL drug acquisition cost is offset by reduced nephrotoxicity-related cost-for the US payer compared to CMS + IMI.

Real-world cost-effectiveness of etonogestrel implants compared to long-term and short term reversible contraceptive methods in France.

BACKGROUND: To estimate the cost-effectiveness (CE) of etonogestrel implants compared to other long-term and short-term reversible contraceptive methods available in France. RESEARCH DESIGN AND METHODS: A 6-year Markov model compared effectiveness between the implant and six other contraceptive methods in sexually active, not-pregnancy-seeking French females of reproductive age. Contraception efficacy, switch rates and outcomes were based on French current medical practice. Incremental CE ratios (ICERs) were calculated as incremental cost per unintended pregnancy (UP) avoided. Efficiency frontier was plotted to identify cost-effective methods. Uncertainty was explored through sensitivity analyses. RESULTS: The implant was on the efficiency frontier along with combined oral contraceptive pill (COC) and copper IUD. Implant avoids between 0.75% and 3.53% additional UP per person-year compared to copper IUD and second generation COC, respectively, with an ICER of €2,221 per UP avoided compared to copper IUD. For the 240,000 French women currently using the implant, up to 8,475 UPs and up to 1,992 abortions may be prevented annually. CONCLUSION: With more unintended pregnancies avoided and comparable costs to copper IUD, the implant is a cost-effective option among long-term and short-term reversible contraceptive methods.

Cost Effectiveness of Ceftolozane/Tazobactam Compared with Meropenem for the Treatment of Patients with Ventilated Hospital-Acquired Bacterial Pneumonia and Ventilator-Associated Bacterial Pneumonia.

INTRODUCTION: The clinical efficacy and safety of ceftolozane/tazobactam for the treatment of ventilated hospital-acquired bacterial pneumonia (vHABP) and ventilator-associated bacterial pneumonia (VABP) has been demonstrated in the phase III randomised controlled trial ASPECT-NP. However, there are no published data on the cost-effectiveness of ceftolozane/tazobactam for vHABP/VABP. These nosocomial infections are associated with high rates of morbidity and mortality, and are increasingly complicated by growing rates of resistance and the inappropriate use of antimicrobials. This study is to assess the cost-effectiveness of ceftolozane/tazobactam compared with meropenem for the treatment of vHABP/VABP in a US hospital setting. METHODS: A short-term decision tree followed by a long-term Markov model was developed to estimate lifetime costs and quality-adjusted life-years associated with ceftolozane/tazobactam and meropenem in the treatment of patients with vHABP/VABP. Pathogen susceptibility and clinical efficacy were informed by the Program to Assess Ceftolozane/Tazobactam Susceptibility (PACTS) database and ASPECT-NP, respectively. A US healthcare sector perspective was adopted, capturing direct costs borne by third-party payers or integrated health systems, and direct health effects for patients. RESULTS: In the confirmed treatment setting (post-susceptibility results), the incremental cost-effectiveness ratio for ceftolozane/tazobactam compared to meropenem was US$12,126 per quality-adjusted life-year (QALY); this reduced when used in the early treatment setting (before susceptibility results) at $4775/QALY. CONCLUSION: Ceftolozane/tazobactam represents a highly cost-effective treatment option for patients with vHABP/VABP versus meropenem when used in either the confirmed or early treatment setting; with increased cost-effectiveness shown in the early setting.

Cost-effectiveness analysis of cytomegalovirus prophylaxis in allogeneic hematopoietic cell transplant recipients from a US payer perspective.

To evaluate the cost-effectiveness of letermovir versus no prophylaxis for the prevention of cytomegalovirus infection and disease in adult cytomegalovirus-seropositive allogeneic hematopoietic cell transplantation (allo-HCT) recipients. A decision model for 100 patients was developed to estimate the probabilities of cytomegalovirus infection, cytomegalovirus disease, various other complications, and death in patients receiving letermovir versus no prophylaxis. The probabilities of clinical outcomes were based on the pivotal phase 3 trial of letermovir use for cytomegalovirus prophylaxis versus placebo in adult cytomegalovirus-seropositive recipients of an allo-HCT. Costs of prophylaxis with letermovir and of each clinical outcome were derived from published sources or the trial clinical study reports. Incremental cost-effectiveness ratios (ICERs) in terms of cost per quality-adjusted life year (QALY) gained were used in the model. One-way and probabilistic sensitivity analyses were conducted to explore uncertainty around the base-case analysis. In this model, the use of letermovir prophylaxis would lead to an increase of QALYs (619) and direct medical cost ($1 733 794) compared with no prophylaxis (578 QALYs; $710 300) in cytomegalovirus-seropositive recipients of an allo-HCT. Letermovir use for cytomegalovirus prophylaxis was a cost-effective option versus no prophylaxis with base-case analysis ICER $25 046/QALY gained. One-way sensitivity analysis showed the most influential parameter was mortality rate. The probabilistic sensitivity analysis showed a 92% probability of letermovir producing an ICER below the commonly accepted willingness-to-pay threshold of $100 000/QALY gained. Based on this model, letermovir use for cytomegalovirus prophylaxis was a cost-effective option in adult cytomegalovirus-seropositive recipients of an allo-HCT.

Healthcare Resource Utilization of Ceftolozane/Tazobactam Versus Meropenem for Ventilated Nosocomial Pneumonia from the Randomized, Controlled, Double-Blind ASPECT-NP Trial.

INTRODUCTION: Hospital-acquired and ventilator-associated bacterial pneumonia (HABP and VABP) are associated with significant healthcare resource utilization (HCRU). This a priori, exploratory, secondary analysis from the ASPECT-NP clinical trial evaluated resource utilization among patients with ventilated HABP (vHABP)/VABP treated with ceftolozane/tazobactam or meropenem. METHODS: This analysis used data from the randomized, double-blind, noninferiority phase 3 ASPECT-NP trial of patients with vHABP/VABP randomized to receive ceftolozane/tazobactam 3 g (ceftolozane 2 g/tazobactam 1 g) or meropenem 1 g for 8-14 days. Day 28 outcomes included hospital length of stay (LOS), intensive care unit (ICU) LOS, and time to mechanical ventilation extubation in the microbiological intention-to-treat (mITT) population and in an HCRU population. The HCRU population, a subset of patients from the mITT population that were alive at day 28, was used to remove resource use bias influenced by mortality rates. RESULTS: Ceftolozane/tazobactam-treated versus meropenem-treated patients, respectively, had fewer deaths (20.1% vs. 25.5%), fewer hospital discharges (30.7% vs. 32.4%), and higher ICU discharges (60.0% vs. 58.3%) and extubations (51.9% vs. 48.2%) by day 28. In the HCRU population, adjusted LOS differences (95% confidence intervals) for ceftolozane/tazobactam compared with meropenem were 0.1 (- 1.4 to 1.6) hospitalization days, - 1.4 (- 2.9 to 0.2) ICU days, and - 0.9 (- 2.4 to 0.7) mechanical ventilation days. Patterns were similar among the VABP and Pseudomonas aeruginosa subgroups. CONCLUSION: Similar 28-day resource utilization outcomes were observed between ceftolozane/tazobactam and meropenem in the mITT population of patients from ASPECT-NP with vHABP/VABP due to gram-negative pathogens. ASPECT-NP was not powered to detect differences in resource utilization outcomes between treatment groups; however, numerical differences in ICU LOS and duration of mechanical ventilation were noted. Further study is needed to assess resource utilization in the real-world practice setting, especially among patients excluded from ASPECT-NP, including those with resistant P. aeruginosa infections. TRIAL REGISTRATIONS: ClinicalTrials.gov: NCT02070757, registered February 25, 2014; EudraCT: 2012-002862-11.