Improving the health of Oklahomans through clinical prevention. Part 1: Counseling to decrease major risk factors

Compared to other states, Oklahomans suffer higher levels of morbidity and mortality from several common conditions--coronary heart disease, chronic lung disease, stroke and injury. Unhealthy personal behaviors contribute significantly to each of these conditions, thus rendering them at least partially preventable by changing those behaviors. Research has shown that many patients will modify unhealthy behaviors as a result of services provided by physicians or staff in their offices, often with briefly delivered messages. In this report we will discuss the most common preventable illnesses suffered by Oklahomans and the risk factors associated with those illnesses. Physicians should make maximum use of their ability to promote healthy behaviors by their patients, with emphasis on the risk factors associated with significant morbidity in the state. They should also focus on those risk factors patients are likely to change following physician counseling, as determined by prevention research and described in the U.S. Preventive Services Task Force document Guide to Clinical Preventive Services. In general, physicians should consistently deliver messages that address tobacco products, alcohol and other drugs, the use of seat belts, and diet and exercise. Also, they should recommend that all women of childbearing age who are capable of becoming pregnant take a multivitamin containing folic acid daily.     

Improving the health of Oklahomans through clinical prevention, part II: Screening to identify early-stage disease and risk factors

The purpose of screening is to identify asymptomatic disease, or risk factors for disease, so that interventions can occur as early as possible in the disease process. The primary goal is to decrease the morbidity the patient experiences from the disease. For infectious diseases, screening can benefit not only the individual with the disease but also the community, since infectious persons can be identified and treated prior to transmitting the disease to others. Although screening can be very beneficial to the individual and to the community, it can also have adverse outcomes if not used appropriately. In this article we will discuss current recommendations for the use of screening tests and their role in addressing the leading causes of morbidity and mortality in Oklahoma. In general, physicians should consistently screen for the risk factors for cardiovascular disease and stroke (hypertension, high cholesterol, obesity and diabetes) and for early-stage cancers of the colon, breast, and cervix. They should also consider screening Native Americans for diabetes and persons at increased risk for certain infectious diseases, particularly sexually transmitted diseases.     

Improving the health of Oklahomans: status and goals of adult immunization

This article will discuss the prevalence and impact of the infectious diseases affecting adult Oklahomans for which vaccines are available. Evidence for vaccine utilization and the present status and future aspirations for population-wide immunization rates in Oklahoma will also be reviewed. The information and data herein are taken mainly from recommendations established by the US Preventive Services Task Force (USPSTF); the Centers for Disease Control (CDC) publication Epidemiology and Prevention of Vaccine-Preventable Disease; the findings of the Advisory Committee on Immunization Practices (ACIP) as published in the CDC's Morbidity and Mortality Weekly Report; the Oklahoma State Department of Health (OSDH) State of the State's Health Report; and the Behavioral Risk Factor Surveillance System (BRFSS), a telephone survey conducted by the CDC.     

Engaging patients and clinicians through a wellness portal to improve the health of Oklahomans

Patient-centeredness is one of the key dimensions of the patient-centered medical home model, yet it is still not uniformly understood. A goal-directed care approach that incorporates active preparation and comprehensive patient visits has been suggested to empower patients and improve health outcomes by various resources, including patient-side health IT (e.g. portals). In the context of a recent randomized controlled trial funded by the Agency of Healthcare Research and Quality, we developed a patient Wellness Portal that was linked to a previously designed and implemented clinician-portal. A six-month pilot implementation study was followed by a 12-month randomized controlled trial to determine the impact of the Portal on patient and practice-level outcomes. Results indicate that the Wellness Portal was easy to use, well received by patients, helped users educate themselves about their conditions, gauge their health status, and create a longitudinal wellness plan for discussion during an annual wellness visit. A preliminary analysis also showed that a greater proportion of patients received preventive services in the Portal intervention group than in the control group.     

Improving completeness of electronic problem lists through clinical decision support: a randomized, controlled trial

Background

Accurate clinical problem lists are critical for patient care, clinical decision support, population reporting, quality improvement, and research. However, problem lists are often incomplete or out of date.

Objective

To determine whether a clinical alerting system, which uses inference rules to notify providers of undocumented problems, improves problem list documentation.

Study Design and Methods

Inference rules for 17 conditions were constructed and an electronic health record-based intervention was evaluated to improve problem documentation. A cluster randomized trial was conducted of 11 participating clinics affiliated with a large academic medical center, totaling 28 primary care clinical areas, with 14 receiving the intervention and 14 as controls. The intervention was a clinical alert directed to the provider that suggested adding a problem to the electronic problem list based on inference rules. The primary outcome measure was acceptance of the alert. The number of study problems added in each arm as a pre-specified secondary outcome was also assessed. Data were collected during 6-month pre-intervention (11/2009–5/2010) and intervention (5/2010–11/2010) periods.

Results

17 043 alerts were presented, of which 41.1% were accepted. In the intervention arm, providers documented significantly more study problems (adjusted OR=3.4, p<0.001), with an absolute difference of 6277 additional problems. In the intervention group, 70.4% of all study problems were added via the problem list alerts. Significant increases in problem notation were observed for 13 of 17 conditions.

Conclusion

Problem inference alerts significantly increase notation of important patient problems in primary care, which in turn has the potential to facilitate quality improvement.

Trial Registration

ClinicalTrials.gov: {"type":"clinical-trial","attrs":{"text":"NCT01105923","term_id":"NCT01105923"}}NCT01105923.     

Improving the quality of cancer care in America through health information technology

A recent report from the Institute of Medicine titled Delivering High-Quality Cancer Care: Charting a New Course for a System in Crisis, identifies improvement in information technology (IT) as essential to improving the quality of cancer care in America. The report calls for implementation of a learning healthcare IT system: a system that supports patient–clinician interactions by providing patients and clinicians with the information and tools necessary to make well informed medical decisions and to support quality measurement and improvement. While some elements needed for a learning healthcare system are already in place for cancer, they are incompletely implemented, have functional deficiencies, and are not integrated in a way that creates a true learning healthcare system. To achieve the goal of a learning cancer care delivery system, clinicians, professional organizations, government, and the IT industry will have to partner, develop, and incentivize participation.     

Cancer of the female breast. Improving the public's health through early detection

Decision makers who represent the public need to understand the extent of the breast cancer problem, the potential for improvement, and the actions needed to achieve this potential. Informed, dedicated physicians, individually and collectively, are instrumental and can be most effective leaders in this process. There are several evidences of the fine tradition of the medical profession to advocate practices and policies in the interest of the best health of our patients. The North Carolina Medical Society recently adopted a position statement encouraging the provision of screening mammograms and pap smears by both private and self-insured third party payors; the North Carolina Academy of Family Practice recently adopted a position statement urging priority be placed on allocating resources for efficacious preventive services; the multiple specialty organizations developed the widely recognized national guidelines for early breast cancer detection; and the ACR continues its efforts to assure quality mammography services. To the end that this paper has informed and stimulated further sharing, discussion or debate about the extent of the breast cancer problem, the potential for improvement, and the actions needed to achieve this potential, it has accomplished its purpose. To the end that the physician community acts to improve early breast cancer detection, we will have fulfilled the common purpose that binds us as physicians to one another and to the people we are privileged and bound to serve.     

Improving domain adaptation in de-identification of electronic health records through self-training

ObjectiveDe-identification is a fundamental task in electronic health records to remove protected health information entities. Deep learning models have proven to be promising tools to automate de-identification processes. However, when the target domain (where the model is applied) is different from the source domain (where the model is trained), the model often suffers a significant performance drop, commonly referred to as domain adaptation issue. In de-identification, domain adaptation issues can make the model vulnerable for deployment. In this work, we aim to close the domain gap by leveraging unlabeled data from the target domain.Materials and MethodsWe introduce a self-training framework to address the domain adaptation issue by leveraging unlabeled data from the target domain. We validate the effectiveness on 4 standard de-identification datasets. In each experiment, we use a pair of datasets: labeled data from the source domain and unlabeled data from the target domain. We compare the proposed self-training framework with supervised learning that directly deploys the model trained on the source domain.ResultsIn summary, our proposed framework improves the F1-score by 5.38 (on average) when compared with direct deployment. For example, using i2b2-2014 as the training dataset and i2b2-2006 as the test, the proposed framework increases the F1-score from 76.61 to 85.41 (+8.8). The method also increases the F1-score by 10.86 for mimic-radiology and mimic-discharge.ConclusionOur work demonstrates an effective self-training framework to boost the domain adaptation performance for the de-identification task for electronic health records.     

Promoting health at the workplace: challenges of prevention, productivity, and program implementation

In the current complex employment landscape providing employer-sponsored benefits involves much more than offering financial protection when employee illness drives a need for costly medical treatment. The transitions in work from product/service production to knowledge generation, along with the transitions in the predominant health and disease conditions from acute illness to preventable chronic disease, require employers to recognize the need to manage their health investment more strategically. This includes the more recent requirement to maximize their investment by ensuring that provisions for maintaining and improving employee health status are incorporated into their health benefits approach. Meanwhile employee health improvement, a highly active but emerging field, is in the process of incorporating experience, research, and more effective methods that result in favorable and demonstrable employee health (and corporate cost-benefit) outcomes.