Physicians' Perceptions of and Satisfaction With Artificial Intelligence in Cancer Treatment: A Clinical Decision Support System Experience and Implications for Low-Middle-Income Countries.

As technology continues to improve, health care systems have the opportunity to use a variety of innovative tools for decision-making, including artificial intelligence (AI) applications. However, there has been little research on the feasibility and efficacy of integrating AI systems into real-world clinical practice, especially from the perspectives of clinicians who use such tools. In this paper, we review physicians' perceptions of and satisfaction with an AI tool, Watson for Oncology, which is used for the treatment of cancer. Watson for Oncology has been implemented in several different settings, including Brazil, China, India, South Korea, and Mexico. By focusing on the implementation of an AI-based clinical decision support system for oncology, we aim to demonstrate how AI can be both beneficial and challenging for cancer management globally and particularly for low-middle-income countries. By doing so, we hope to highlight the need for additional research on user experience and the unique social, cultural, and political barriers to the successful implementation of AI in low-middle-income countries for cancer care.

Implementation of enhanced recovery protocols reduces opioid use in pediatric laparoscopic Heller myotomy surgery.

BACKGROUND: Enhanced recovery protocols (ERPs) are effective means of standardizing and improving the quality of surgical care in adults. Our purpose was to retrospectively compare outcomes before and after implementation of ERPs in children undergoing laparoscopic Heller myotomy for achalasia. METHODS: A pediatric-specific ERP was used for children undergoing laparoscopic Heller myotomy starting July 2017 at two pediatric surgery centers within a single metropolitan healthcare system. A retrospective review of 8 patients undergoing Heller myotomies between July 2014 and July 2017 was performed as a control. This cohort was compared to 14 patients managed post-ERP implementation (2017-2020). Outcomes of interest investigated included opioid use during admission, narcotics at discharge, time to regular diet, length of stay (LOS), and readmissions. RESULTS: There was a significant decrease in opioid use both while in the hospital and at time of discharge. Mean morphine equivalent use was 4.50 mg in the pre-ERP cohort and 1.97 mg in the post-ERP cohort. Furthermore, 8 out of 14 (57%) patients in the post-ERP cohort received no opioids during the admission compared with only 2 out of 8 (25%) patients in the pre-ERP cohort. Only 1 out of 14 (7.14%) patients in the post-ERP cohort was discharged with a prescription for opioid medication while 6 out of 8 (75%) in the pre-ERP cohort were discharged with an opiate prescription. CONCLUSIONS: The use of ERP in children undergoing laparoscopic Heller myotomy surgery is safe and effective and leads to a reduction in opioid use during admission and at discharge. LEVELS OF EVIDENCE: Level III.

A Quality Improvement Intervention Leveraging a Safety Net Model for Surveillance Colonoscopy Completion.

Systems to address follow-up testing of clinically positive surveillance colonoscopy results are lacking. The impact of an ambulatory safety net (ASN) intervention on rates of colonoscopy completion was assessed. The ASN team identified patients using an electronic registry, conducted patient outreach, coordinated care, and tracked colonoscopy completion. In all, 701 patients were captured in the ASN program: 58.1% (407/701) had possible barriers to follow-up colonoscopy completion, with rates of 80.1% (236/294) if no barrier, and 40.9% (287/701) overall. Colonoscopy completion likelihood increased with prior polypectomy (odds ratio [OR], 1.6; 95% confidence interval [CI], 1.1-2.3), and decreased with White race (OR, 0.5; 95% CI, 0.3-0.9), increased inpatient visits (OR, 0.6; 95% CI, 0.4-0.9), more outreach attempts (OR, 0.6; 95% CI, 0.5-0.7), and fair/poor/inadequate preparation (OR, 0.4; 95% CI, 0.2-0.7) in logistic regression models. An ASN model for quality improvement promotes colonoscopy completion rates and identifies patient barriers.

Ambulatory Safety Nets to Reduce Missed and Delayed Diagnoses of Cancer.

BACKGROUND: An ambulatory safety net (ASN) is an innovative organizational intervention for addressing patient safety related to missed and delayed diagnoses of abnormal test results. ASNs consist of a set of tools, reports and registries, and associated work flows to create a high-reliability system for abnormal test result management. METHODS: Two ASNs implemented at an academic medical center are described, one focusing on colon cancer and the other on lung cancer. Data from electronic registries and chart reviews were used to evaluate the effectiveness of the ASNs, which were defined as follows: colon cancer-the proportion of patients who were scheduled for or completed a colonoscopy following safety net team outreach to the patient; lung cancer-the proportion of patients for whom the safety net was able to identify and implement appropriate follow-up, as defined by scheduled or completed chest CT. RESULTS: The effectiveness of the colon cancer ASN was 44.0%, and the effectiveness of the lung cancer ASN was 56.9%. The ASNs led to the development of registries to address patient safety, fostered collaboration among interdisciplinary teams of clinicians and administrative staff, and created new work flows for patient outreach and tracking. CONCLUSION: Two ASNs were successfully implemented at an academic medical center to address missed and delayed recognition of abnormal test results related to colon cancer and lung cancer. The ASNs are providing a framework for development of additional safety nets in the organization.

Identifying unrecognized peripheral arterial disease among asymptomatic patients in the primary care setting.

National initiatives to enhance recognition of the detrimental impact of peripheral arterial disease on the health of adult Americans have been advocated. The objective of this study was to evaluate a strategy for identifying patients with unrecognized peripheral arterial disease from among persons without known atherosclerotic disease in the primary care setting. A cross-sectional design was used. Participants were patients receiving care from a multispecialty group practice in Massachusetts between July 2002 and July 2003, with a scheduled appointment with a primary care physician. Persons 70 years of age or older who were not already known to have atherosclerotic disease were enrolled. In addition, persons aged 50-69 with a diagnosis of diabetes mellitus, dyslipidemia, hypertension, and/or smoking based on information derived from administrative databases, and not known to have atherosclerotic disease, were enrolled. Before the scheduled appointment, potential study participants completed a telephone interview to ascertain their medical history. The ankle-brachial index (ABI) of eligible patients was measured at the time of the scheduled primary care office visit. Peripheral arterial disease was diagnosed if 1 or both legs had an ABI of or=70 years, 45 (12.5%) were diagnosed with peripheral arterial disease. Nine (2.5%) of 358 subjects aged 50-69 years were diagnosed with peripheral arterial disease. The average total time (n = 52) for ABI testing was 13.7 (SD: +/-3.3) minutes. Patients aged >or=70 years required more time for ABI testing compared to those aged 50-69 (mean: 15.0 vs 13.0 minutes, p=0.04). Unrecognized asymptomatic peripheral arterial disease can be commonly detected among patients in the primary care setting who are not already known to have atherosclerotic disease. The yield from screening is substantially greater among unselected older patients compared with younger patients specifically identified as having risk factors for PAD. These findings should help inform the development and implementation of new initiatives to enhance the early detection of peripheral arterial disease among asymptomatic patients in the primary care setting.

Compliance with pharmacologic therapy for osteoporosis.

There is little information available concerning compliance with pharmacologic therapy for osteoporosis in the usual care setting. We evaluated 176 consecutive, previously untreated women whose physicians initiated treatment for osteoporosis following a bone mineral density (BMD) test obtained as part of routine medical practice. All patients were contacted >/=1 year after the initial BMD test and offered a follow-up BMD. Compliance with therapy was defined as the percent of time that a patient filled a prescription for osteoporosis treatment. Ninety-three (53%) patients received estrogen (ERT), 93 (53%) bisphosphonates, 8 (5%) calcitonin, and 17 (10%) received more than one therapy. Ninety-one of the 176 (52%) agreed to a follow-up BMD at a mean of 590 days after the first study (participants); 85 declined a follow-up BMD (refusers). Participants and refusers were similar for age, treatment patterns, and compliance with therapy. For all patients, compliance for those given bisphosphonate was similar to those given ERT (70.7% (95% CI 63.5-77.9%) versus 69.2% (95% CI 61.7-76.8%). For participants, the change in spine BMD was similar for those treated with bisphosphonate [mean increase 3.53 (+/-2.64)%/year (mean+/-SD)] and those treated with ERT [mean increase 3.00 (+/-2.75)%/year]. For those participants whose compliance with therapy was >/=66%, the mean increase in spine bone density was 3.80 (+/-2.59)%/year compared to 2.11 (+/-2.64)%/year ( p<0.005) for those whose compliance was <66%. Compliance with ERT and bisphosphonate therapy initiated in routine practice after a BMD was similar over a mean of 590 days. Compliance less than 66% with drug treatment results in suboptimal improvement in bone density.