Use of Machine Learning for Early Detection of Maternal Cardiovascular Conditions: Retrospective Study Using Electronic Health Record Data.

BACKGROUND: Cardiovascular conditions (eg, cardiac and coronary conditions, hypertensive disorders of pregnancy, and cardiomyopathies) were the leading cause of maternal mortality between 2017 and 2019. The United States has the highest maternal mortality rate of any high-income nation, disproportionately impacting those who identify as non-Hispanic Black or Hispanic. Novel clinical approaches to the detection and diagnosis of cardiovascular conditions are therefore imperative. Emerging research is demonstrating that machine learning (ML) is a promising tool for detecting patients at increased risk for hypertensive disorders during pregnancy. However, additional studies are required to determine how integrating ML and big data, such as electronic health records (EHRs), can improve the identification of obstetric patients at higher risk of cardiovascular conditions. OBJECTIVE: This study aimed to evaluate the capability and timing of a proprietary ML algorithm, Healthy Outcomes for all Pregnancy Experiences-Cardiovascular-Risk Assessment Technology (HOPE-CAT), to detect maternal-related cardiovascular conditions and outcomes. METHODS: Retrospective data from the EHRs of a large health care system were investigated by HOPE-CAT in a virtual server environment. Deidentification of EHR data and standardization enabled HOPE-CAT to analyze data without pre-existing biases. The ML algorithm assessed risk factors selected by clinical experts in cardio-obstetrics, and the algorithm was iteratively trained using relevant literature and current standards of risk identification. After refinement of the algorithm's learned risk factors, risk profiles were generated for every patient including a designation of standard versus high risk. The profiles were individually paired with clinical outcomes pertaining to cardiovascular pregnancy conditions and complications, wherein a delta was calculated between the date of the risk profile and the actual diagnosis or intervention in the EHR. RESULTS: In total, 604 pregnancies resulting in birth had records or diagnoses that could be compared against the risk profile; the majority of patients identified as Black (n=482, 79.8%) and aged between 21 and 34 years (n=509, 84.4%). Preeclampsia (n=547, 90.6%) was the most common condition, followed by thromboembolism (n=16, 2.7%) and acute kidney disease or failure (n=13, 2.2%). The average delta was 56.8 (SD 69.7) days between the identification of risk factors by HOPE-CAT and the first date of diagnosis or intervention of a related condition reported in the EHR. HOPE-CAT showed the strongest performance in early risk detection of myocardial infarction at a delta of 65.7 (SD 81.4) days. CONCLUSIONS: This study provides additional evidence to support ML in obstetrical patients to enhance the early detection of cardiovascular conditions during pregnancy. ML can synthesize multiday patient presentations to enhance provider decision-making and potentially reduce maternal health disparities.

Multiinstitutional Evaluation of a Debate-Style Journal Club for Cardiothoracic Surgery Trainees.

BACKGROUND: Traditional journal clubs address individual articles and are limited in terms of breadth and depth of content covered. The present study describes the outcomes of a novel debate-style journal club in a multiinstitutional setting. METHODS: Participating institutions were recruited through the Thoracic Education Cooperative Group. The distributed curriculum included instructions, debate scenarios, suggested article lists, moderator slides, debate scoresheets, exams, and feedback surveys. RESULTS: Six institutions participated in the study (2015-2019), consisting of a total of 10 years' worth of cumulative debates. Cardiothoracic surgery trainees participated in 10 monthly debates over each academic year. Trainee performance on the written examination in the realm of evidence-based medicine and critical appraisal improved over the course of the academic year (beginning 55.2% vs end 76.3%; P = .040). Importantly, written examination after debates revealed a significant improvement in scores on questions relating to topics that were debated as compared with those that were not (+27.1% vs +2.5%; P = .006), emphasizing the importance of the debates as compared with other sources of knowledge gain. Surveys completed by trainees and faculty overall favored the debate-style journal club as compared with the traditional journal club in gaining familiarity with seminal literature in the field, improving on oral presentation skills, and applying published literature to questions encountered clinically. CONCLUSIONS: In this multiinstitutional prospective study, we demonstrate that the novel debate-style cardiothoracic surgery journal club is an effective educational intervention for cardiothoracic surgical trainees to acquire, retain, and gain practice in applying literature-based evidence to case-based scenarios.

Optimal timing of type A intramural hematoma repair.

Acute type A aortic intramural hematomas (IMHs) are often included under the spectrum of acute aortic syndromes. The classical definition is the presence of hematoma in the media without identifiable intimal tear. Dissection occurring within two weeks of presentation is defined as acute. Acute type A IMH remains a subject of debate, especially regarding its definition and management. The classical theory of pathogenesis of IMHs is ruptured vasa vasorum in the aortic media. However, the majority of IMHs are now detected with an intimal defect using high-resolution computed tomography and intravascular ultrasound, which implies that IMHs may be a subset of aortic dissections (ADs), with very limited flow in the false lumen. Much controversy remains regarding IMH differences in presentation, diagnosis, and risk for progression. Geographic location and ethnicity, especially Asian vs. Western, possibly affect the natural history and outcomes of acute type A IMH. In this review, we describe the pathophysiology and management strategies for acute type A IMHs.

Acute Type A Dissection Repair by High-Volume Vs Low-Volume Surgeons at a High-Volume Aortic Center.

BACKGROUND: Previous studies suggest improved outcomes for acute type A dissections (ATAAD) treated at high-volume centers. It is unclear if outcomes are a result of individual surgeon experience or inherent resources available at high-volume centers. To explore this question, we stratified outcomes for ATAAD repair by low-volume and high-volume surgeons at a high-volume center. METHODS: We reviewed our institutional experience with ATAAD between 1999 and 2016 (n = 580). To evaluate surgeon experience with ATAAD repair, we categorized surgeons as high-volume aortic surgeons (HVASs) (> 10 cases/year) or low-volume aortic surgeons (LVASs) (≤ 10 cases/year). Analysis was stratified according to the following: HVAS in primary and first assist roles, HVAS as primary with LVAS as first assist, LVAS as primary and HVAS as first assist, and LVAS in both roles. RESULTS: The total experience for HVAS and LVAS as primary surgeon for the study period was 513 and 67, respectively. Mean annual experience as primary surgeon was 15.2 cases for HVAS and 3.4 cases for LVAS. In-hospital mortality was 14.0% if an HVAS was present and 24.0% with an all-LVAS team (P = .27). After adjusting for preoperative factors, the mortality odds ratio (OR) for an all-LVAS team was 3.72 (P = .01). CONCLUSIONS: ATAAD repair by an all-LVAS team had nearly a 4-fold increase in-hospital mortality compared with an all-HVAS team. Improved outcomes at high-volume centers may be predominantly due to surgeon experience and not from center-specific resources. This study may have implications on call coverage for ATAAD repair at high-volume centers.

Novel Debate-Style Cardiothoracic Surgery Journal Club: Results of a Pilot Curriculum.

BACKGROUND: Traditional journal clubs addressing single articles are limited by the lack of a standardized process for conduct and evaluation. We developed a novel, debate-style journal club for trainees to use best available evidence to address controversial topics in cardiothoracic surgery through discussion of realistic patient scenarios. METHODS: After implementation of our new curriculum, trainee knowledge acquisition and retention were assessed by a summative test of published literature and standardized debate scoring. Feedback was additionally obtained by trainee and faculty surveys. RESULTS: Cardiothoracic surgery trainees (n = 4) participated in five debates each over 10 monthly sessions. Written examination results after debate revealed a nonsignificant improvement in scores on topics that were debated compared with topics that were not (+9.8% versus -4.2%, p = 0.105). Trainee ability to sway the debate position supported by the attendee strongly correlated with trainee use of supporting literature (r = 0.853), moderately correlated with persuasiveness (r = 0.465), and overall effect of the debate (r = 0.625). Surveys completed by trainees and faculty unanimously favored the debate-style journal club as compared to the traditional journal club in gaining familiarity and applying published literature to questions encountered clinically. CONCLUSIONS: Our novel debate-style cardiothoracic surgery journal club is an effective educational intervention for cardiothoracic surgery trainees to acquire, retain, and gain practice in applying specialty-specific literature-based evidence to controversial case-based issues. Evaluation by multi-institutional expansion is needed to validate our preliminary findings in this initial trainee cohort.

A Structured, Debate-Style Cardiothoracic Surgery Journal Club for Trainee Acquisition and Application of Seminal Literature.

INTRODUCTION: The acquisition of specialty-specific seminal literature and its application to daily, clinical patient-care decisions are critical components of clinical training. This structured, debate-style cardiothoracic surgery journal club module engages trainees in discussion of realistic patient scenarios, incorporating an extensive body of literature identified as the best evidence for the practice of cardiothoracic surgery. METHODS: We designed the structured, debate-style cardiothoracic surgery journal club and delivered it to University of Texas MD Anderson Cancer Center cardiothoracic surgery trainees. Overall assessment of knowledge acquisition consisted of both direct judging of debates by faculty facilitators and a year-end written test of trainee knowledge. Associated materials include guidelines and resources for faculty facilitators and trainees to prepare them for the journal club debate. Also included are cardiothoracic surgery patient cases, PowerPoint presentation slides, a debate score sheet, and multiple-choice knowledge tests with answer keys. RESULTS: Our structured, debate-style cardiothoracic surgery journal club is an effective educational intervention for cardiothoracic surgical trainees to gain practice in applying specialty-specific, literature-based evidence to particular patient problems. DISCUSSION: This resource may be used by course directors for surgery, for independent study by individuals planning to matriculate into surgical residencies, or as a review for those already in surgical training. Moreover, this curriculum can be delivered at other clinical training programs.

Missense mutations in FBN1 exons 41 and 42 cause Weill-Marchesani syndrome with thoracic aortic disease and Marfan syndrome.

Mutations in FBN1 cause a range of overlapping but distinct conditions including Marfan syndrome (MFS), Weill-Marchesani syndrome (WMS), familial thoracic aortic aneurysms/dissections (FTAAD), acromicric dysplasia (AD), and geleophysic dysplasia (GD). Two forms of acromelic dysplasia, AD and GD, characterized by short stature, brachydactyly, reduced joint mobility, and characteristic facies, result from heterozygous missense mutations occurring in exons 41 and 42 of FBN1; missense mutations in these exons have not been reported to cause MFS or other syndromes. Here we report on probands with MFS and WMS who have heterozygous FBN1 missense mutations in exons 41 and 42, respectively. The proband with WMS has ectopia lentis, short stature, thickened pinnae, tight skin, striae atrophicae, reduced extension of the elbows, contractures of the fingers and toes, and brachydactyly and has a missense mutation in exon 42 of FBN1 (c.5242T>C; p.C1748R). He also experienced a previously unreported complication of WMS, an acute thoracic aortic dissection. The second proband displays classic characteristics of MFS, including ectopia lentis, skeletal features, and aortic root dilatation, and has a missense mutation in exon 41 of FBN1 (c.5084G>A; p.C1695Y). These phenotypes provide evidence that missense mutations in exons 41 and 42 of FBN1 lead to MFS and WMS in addition to AD and GD and also suggest that all individuals with pathogenic FBN1 mutations in these exons should be assessed for thoracic aortic disease and ectopia lentis. Further studies are necessary to elucidate the factors responsible for the different phenotypes associated with missense mutations in these exons of FBN1.

Clinical practice guideline: adult sinusitis.

OBJECTIVE: This guideline provides evidence-based recommendations on managing sinusitis, defined as symptomatic inflammation of the paranasal sinuses. Sinusitis affects 1 in 7 adults in the United States, resulting in about 31 million individuals diagnosed each year. Since sinusitis almost always involves the nasal cavity, the term rhinosinusitis is preferred. The guideline target patient is aged 18 years or older with uncomplicated rhinosinusitis, evaluated in any setting in which an adult with rhinosinusitis would be identified, monitored, or managed. This guideline is intended for all clinicians who are likely to diagnose and manage adults with sinusitis. PURPOSE: The primary purpose of this guideline is to improve diagnostic accuracy for adult rhinosinusitis, reduce inappropriate antibiotic use, reduce inappropriate use of radiographic imaging, and promote appropriate use of ancillary tests that include nasal endoscopy, computed tomography, and testing for allergy and immune function. In creating this guideline the American Academy of Otolaryngology-Head and Neck Surgery Foundation selected a panel representing the fields of allergy, emergency medicine, family medicine, health insurance, immunology, infectious disease, internal medicine, medical informatics, nursing, otolaryngology-head and neck surgery, pulmonology, and radiology. RESULTS: The panel made strong recommendations that 1) clinicians should distinguish presumed acute bacterial rhinosinusitis (ABRS) from acute rhinosinusitis caused by viral upper respiratory infections and noninfectious conditions, and a clinician should diagnose ABRS when (a) symptoms or signs of acute rhinosinusitis are present 10 days or more beyond the onset of upper respiratory symptoms, or (b) symptoms or signs of acute rhinosinusitis worsen within 10 days after an initial improvement (double worsening), and 2) the management of ABRS should include an assessment of pain, with analgesic treatment based on the severity of pain. The panel made a recommendation against radiographic imaging for patients who meet diagnostic criteria for acute rhinosinusitis, unless a complication or alternative diagnosis is suspected. The panel made recommendations that 1) if a decision is made to treat ABRS with an antibiotic agent, the clinician should prescribe amoxicillin as first-line therapy for most adults, 2) if the patient worsens or fails to improve with the initial management option by 7 days, the clinician should reassess the patient to confirm ABRS, exclude other causes of illness, and detect complications, 3) clinicians should distinguish chronic rhinosinusitis (CRS) and recurrent acute rhinosinusitis from isolated episodes of ABRS and other causes of sinonasal symptoms, 4) clinicians should assess the patient with CRS or recurrent acute rhinosinusitis for factors that modify management, such as allergic rhinitis, cystic fibrosis, immunocompromised state, ciliary dyskinesia, and anatomic variation, 5) the clinician should corroborate a diagnosis and/or investigate for underlying causes of CRS and recurrent acute rhinosinusitis, 6) the clinician should obtain computed tomography of the paranasal sinuses in diagnosing or evaluating a patient with CRS or recurrent acute rhinosinusitis, and 7) clinicians should educate/counsel patients with CRS or recurrent acute rhinosinusitis regarding control measures. The panel offered as options that 1) clinicians may prescribe symptomatic relief in managing viral rhinosinusitis, 2) clinicians may prescribe symptomatic relief in managing ABRS, 3) observation without use of antibiotics is an option for selected adults with uncomplicated ABRS who have mild illness (mild pain and temperature <38.3 degrees C or 101 degrees F) and assurance of follow-up, 4) the clinician may obtain nasal endoscopy in diagnosing or evaluating a patient with CRS or recurrent acute rhinosinusitis, and 5) the clinician may obtain testing for allergy and immune function in evaluating a patient with CRS or recurrent acute rhinosinusitis. DISCLAIMER: This clinical practice guideline is not intended as a sole source of guidance for managing adults with rhinosinusitis. Rather, it is designed to assist clinicians by providing an evidence-based framework for decision-making strategies. It is not intended to replace clinical judgment or establish a protocol for all individuals with this condition, and may not provide the only appropriate approach to diagnosing and managing this problem.

Comparison of multidetector 64-slice computed tomographic angiography to coronary angiography to assess the patency of coronary artery bypass grafts.

This study prospectively evaluated the diagnostic accuracy of 64-slice computed tomographic angiography (CTA) in assessing the patency of coronary artery bypass grafts compared with invasive coronary angiography. In total 147 bypass grafts (100 venous grafts and 47 mammary artery grafts) were evaluated in 50 consecutive patients. Contrast-enhanced 64-slice CTA was performed and compared with invasive angiography. The computed tomographic angiographic scan protocol used 64- x 0.5-mm slice collimation and 0.33-second gantry rotation time during simultaneous electrocardiographic gating. Patients with a heart rate >65 beats/min received beta blockers. Overall 145 of 147 bypass grafts (98.6%) were detected by CTA; 2 nonvisualized grafts were occluded at the time of invasive angiography. Of the grafts visualized, 28 were totally occluded, 103 were patent, and 14 had significant stenoses that were confirmed by invasive angiography. Ninety-five percent (111 of 117) of patent grafts demonstrated good run-off distal to anastomoses but without an ability to accurately evaluate the presence of retrograde flow; 83% (97 of 117) of distal anastomoses were adequately evaluated, whereas the remaining 17% (20 of 117) were not well visualized due to vascular clips and/or calcification artifacts. Two grafts were not demonstrated by invasive angiography but were detected by CTA and found to be widely patent. In conclusion, multidetector 64-slice CTA is a valuable tool for direct visualization of coronary bypass grafts and assessment of their patency. Dysfunctional bypass grafts can be detected with high diagnostic accuracy.

General medical and pharmacy claims expenditures in users of behavioral health services.

OBJECTIVE: To quantify the magnitude of general medical and/or pharmacy claims expenditures for individuals who use behavioral health services and to assess future claims when behavioral service use persists. DESIGN: Retrospective cost trends and 24-month cohort analyses. SETTING: A Midwest health plan. PARTICIPANTS: Over 250,000 health plan enrollees during 2000 and 2001. MEASUREMENTS: Claims expenditures for behavioral health services, general medical services, and prescription medications. MAIN RESULTS: Just over one tenth of enrollees (10.7%) in 2001 had at least 1 behavioral health claim and accounted for 21.4% of total general medical, behavioral health, and pharmacy claims expenditures. Costs for enrollees who used behavioral health services were double that for enrollees who did not use such services. Almost 80% of health care costs were for general medical services and medications, two thirds of which were not psychotropics. Total claims expenditures in enrollees with claims for both substance use and mental disorders in 2000 were 4 times that of those with general medical and/or pharmacy claims only. These expenditures returned to within 15% of nonbehavioral health service user levels in 2001 when clinical need for behavioral health services was no longer required but increased by another 37% between 2000 and 2001 when both chemical dependence and mental health service needs persisted. CONCLUSIONS: The majority of total claims expenditures in patients who utilize behavioral health services are for medical, not behavioral, health benefits. Continued service use is associated with persistently elevated total general medical and pharmacy care costs. These findings call for studies that better delineate: 1) the interaction of general medical, pharmacy, and behavioral health service use and 2) clinical and/or administrative approaches that reverse the high use of general medical resources in behavioral health patients.

Usefulness of database studies as applied to managed care.

Benchmarking, an industry comparison tool and a well-known business technology, offers health care a method of establishing standards for health care use with clinical governance. Benchmarking can lead to practice innovations necessary for survival in a managed care environment that has a need for decreasing cost and increasing quality. Information gleaned from the benchmarking dataset can be used to determine where limited resources for disease management programs should be directed. It can also be used to help decision makers manage a drug formulary by providing a basic knowledge about the environment in which a drug will be used and prescribed. This article describes the relationship of database studies and benchmarking and the usefulness as applied to managed care.

A phase II trial of ISIS 3521 in patients with metastatic colorectal cancer.

This phase II study was designed to characterize the clinical activity of ISIS 3521 in patients with metastatic colorectal cancer (CRC). Sixteen patients with pretreated or refractory CRC were treated with ISIS 3521. Eleven patients were given a dose of 2.0 mg/kg per day, and 5 patients received 3.0 mg/kg per day given over 21 days followed by a 7-day rest period. Patients continued with study until evidence of disease progression or unacceptable toxicity was detected. Patients underwent baseline tumor biopsies followed by a second biopsy during the last week of the first 21-day infusion. All 16 patients underwent baseline tumor biopsies, and 12 of the 16 patients underwent on-study tumor biopsies. No evidence of tumor response was observed. One patient had stable disease after 2 cycles and remained on for 1 additional cycle only to demonstrate progression of disease at that time. No dose-limiting or other significant toxicities were observed at both dosages, which could not be explained by progression of disease. Fatigue was common in all patients treated but was not dose limiting, and there was no evidence of coagulopathy. Analysis of the tumor biopsies obtained from the 11 evaluable samples showed marked uptake of ISIS 3521 in the normal liver parenchyma. However, there was minimal uptake within the tumor cells. In addition, no evidence of any alteration in protein kinase C-a within the tumors or any downstream effects leading to apoptosis were observed. ISIS 3521 demonstrated no clinical activity or target modulation in refractory metastatic CRC.

Building the case for asthma as a disease management program.

Asthma is a common disease that affects between 5.5% and 7.0% of the population. It is an example of a disease where good guidelines and an accepted model of treatment exist, but have not been fully implemented. In the latter part of 2000, Blue Cross Blue Shield of Minnesota (BCBSM) had existing and successful disease management (DM) programs for diabetes and heart disease and was looking to expand the concept to other diseases. Asthma was one of the conditions under consideration. This study, done in conjunction with PharMetrics, Inc. of Watertown, MA was done to establish the opportunity present to help Blue Cross members with the disease, and to help decide whether developing such a program made sense for the health plan. In addition, if the answer to the second question were yes, the study would lay the groundwork for that program. Using 2 years of BCBSM claims data, the study identified, stratified, and analyzed the cohort of BCBSM members with a diagnosis of asthma according to severity of illness, individual drug or drug combination treatment, emergency room usage, hospitalization, and total episode costs for asthma. Health plan results were bench-marked against the experience of others across the country represented in the (then) 20+ million managed care lives in PharMetrics' Integrated Outcomes Database. The results showed that in some of the recommended guidelines for asthma care BCBSM members led the nation in compliance, but that there was ample opportunity for improvement thus justifying moving forward in developing a disease management program. The results also seemed to validate many of the recommendations for asthma care expressed in the Expert Panel Report 2 on the diagnosis and treatment of asthma from the National Heart Lung and Blood Institute of the National Institutes of Health.

Improving the toxicity of irinotecan/5-FU/leucovorin: a 21-day schedule.

Irinotecan (CPT-11, Camptosar) is one of the new generation of chemotherapeutic agents that has activity in advanced colorectal cancer. It has antitumor efficacy as a single agent, and also has been combined with fluorouracil (5-FU) and leucovorin (IFL) to treat these patients. Randomized studies have confirmed the superiority of IFL to 5-FU and leucovorin alone with regard to patient survival, time to progression, and tumor response rate. The optimal schedule for combining these agents remains uncertain, but in the United States, the schedule of IFL weekly for 4 consecutive weeks repeated every 6 weeks, according to the schedule reported by Saltz et al, has been widely used, although with some toxicity (especially myelosuppression and diarrhea). In an attempt to improve the tolerability of IFL, some have advocated modifying the schedule of IFL to weekly for 2 weeks, with repeated cycles every 21 days. Twenty-three patients with advanced colorectal cancer have been treated on this schedule at a single institution. Therapy was well tolerated, with 35% of patients experiencing grade 3/4 neutropenia, two of whom had episodes of febrile neutropenia, and 9% with grade 3/4 diarrhea. The median relative dose intensity of irinotecan administered in the first 18 patients treated with this regimen was 94%. These data support the hypothesis that modifying the schedule of administration of IFL improves the tolerability and ability to deliver the regimen, but must be confirmed by randomized prospective studies, which may also attempt to evaluate the role of bolus 5-FU in the treatment of advanced colorectal cancer.