Kathy L. MacLaughlin

Clinical decision support with automated text processing for cervical cancer screening.

Objective To develop a computerized clinical decision support system (CDSS) for cervical cancer screening that can interpret free-text Papanicolaou (Pap) reports. Materials and Methods The CDSS was constituted by two rulebases: the free-text rulebase for interpreting Pap reports and a guideline rulebase. The free-text rulebase was developed by analyzing a corpus of 49 293 Pap reports. The guideline rulebase was constructed using national cervical cancer screening guidelines. The CDSS accesses the electronic medical record (EMR) system to generate patient-specific recommendations. For evaluation, the screening recommendations made by the CDSS for 74 patients were reviewed by a physician. Results and Discussion Evaluation revealed that the CDSS outputs the optimal screening recommendations for 73 out of 74 test patients and it identified two cases for gynecology referral that were missed by the physician. The CDSS aided the physician to amend recommendations in six cases. The failure case was because human papillomavirus (HPV) testing was sometimes performed separately from the Pap test and these results were reported by a laboratory system that was not queried by the CDSS. Subsequently, the CDSS was upgraded to look up the HPV results missed earlier and it generated the optimal recommendations for all 74 test cases. Limitations Single institution and single expert study. Conclusion An accurate CDSS system could be constructed for cervical cancer screening given the standardized reporting of Pap tests and the availability of explicit guidelines. Overall, the study demonstrates that free text in the EMR can be effectively utilized through natural language processing to develop clinical decision support tools.

Formative evaluation of the accuracy of a clinical decision support system for cervical cancer screening

Objectives We previously developed and reported on a prototype clinical decision support system (CDSS) for cervical cancer screening. However, the system is complex as it is based on multiple guidelines and free-text processing. Therefore, the system is susceptible to failures. This report describes a formative evaluation of the system, which is a necessary step to ensure deployment readiness of the system. Materials and methods Care providers who are potential end-users of the CDSS were invited to provide their recommendations for a random set of patients that represented diverse decision scenarios. The recommendations of the care providers and those generated by the CDSS were compared. Mismatched recommendations were reviewed by two independent experts. Results A total of 25 users participated in this study and provided recommendations for 175 cases. The CDSS had an accuracy of 87% and 12 types of CDSS errors were identified, which were mainly due to deficiencies in the systems guideline rules. When the deficiencies were rectified, the CDSS generated optimal recommendations for all failure cases, except one with incomplete documentation. Discussion and conclusions The crowd-sourcing approach for construction of the reference set, coupled with the expert review of mismatched recommendations, facilitated an effective evaluation and enhancement of the system, by identifying decision scenarios that were missed by the systems developers. The described methodology will be useful for other researchers who seek rapidly to evaluate and enhance the deployment readiness of complex decision support systems.

Caring for the breast cancer survivor's health and well-being.

The breast cancer care continuum entails detection, diagnosis, treatment, and survivorship. During this time, focus on the whole woman and medical concerns beyond the breast cancer diagnosis itself is essential. In this comprehensive review, we critically review and evaluate recent evidence regarding several topics pertinent to and specific for the woman living with a prior history of breast cancer. More specifically, we discuss the most recent recommendations for contraceptive options including long-acting reversible contraception and emergency contraception, fertility and pregnancy considerations during and after breast cancer treatment, management of menopausal vasomotors symptoms and vulvovaginal atrophy which often occurs even in young women during treatment for breast cancer. The need to directly query the patient about these concerns is emphasized. Our focus is on non-systemic hormones and non-hormonal options. Our holistic approach to the care of the breast cancer survivor includes such preventive health issues as sexual and bone health,which are important in optimizing quality of life. We also discuss strategies for breast cancer recurrence surveillance in the setting of a prior breast cancer diagnosis. This review is intended for primary care practitioners as well as specialists caring for female breast cancer survivors and includes key points for evidence-based best practice recommendations.

Patient self-assessment factors predictive of persistent depressive symptoms 6 months after enrollment in collaborative care management.

Collaborative care management (CCM) is effective for improving depression outcomes. However, a subset of patients will still have symptoms after 6 months. This study sought to determine whether routinely obtained baseline clinical, demographic, and self‐assessment variables would predict which patients endorse persistent depressive symptoms (PDS) after 6 months. By estimating the relative risk associated with the patient variables, we aimed to outline the combinations of factors predictive of PDS after CCM enrollment.

Age of Depressed Patient does Not Affect Clinical Outcome in Collaborative Care Management

Abstract Clinical response and remission for the treatment of depression has been shown to be improved utilizing collaborative care management (CCM). Prior studies have indicated that the presence of mental health comorbidities noted by self-rated screening tools at the intake for CCM are associated with worsening outcomes; few have examined directly the impact of age on clinical response and remission. The hypothesis was that when controlling for other mental health and demographic variables, the age of the patient at implementation of CCM does not significantly impact clinical outcome, and that CCM shows consistent efficacy across the adult age spectrum. We performed a retrospective chart analysis of a cohort of 574 patients with a clinical diagnosis of major depression (not dysthymia) treated in CCM who had 6 months of follow-up data. Using the age group as a categorical variable in logistic regression models demonstrated that while maintaining control of all other variables, age grouping remained a nonsignificant predictor of clinical response (P ≥ 0.1842) and remission (P ≥ 0.1919) after 6 months of treatment. In both models, a lower Generalized Anxiety Disorder-7 score and a negative Mood Disorder Questionnaire score were predictive of clinical response and remission. However, the initial Patient Health Questionnaire-9 score was a statistically significant predictor only for clinical remission (P = 0.0094), not for response (P = 0.0645), at 6 months. In a subset (n = 295) of the study cohort, clinical remission at 12 months was also not associated with age grouping (P ≥ 0.3355). The variables that were predictive of remission at 12 months were the presence of clinical remission at 6 months (odds ratio [OR], 7.4820; confidence interval [CI], 3.9301-14.0389; P < 0.0001), clinical response (with persistent symptoms) (OR, 2.7722; CI, 1.1950-6.4313; P = 0.0176), and a lower initial Patient Health Questionnaire-9 score (OR, 0.9121; CI, 0.8475-0.9816; P = 0.0140). Our study suggests that using CCM for depression treatment may transcend age-related differences in depression and result in positive outcomes regardless of age.

Contraception and Hormonal Management in the Perimenopause

This literature review focuses on contraception in perimenopausal women. As women age, their fecundity decreases but does not disappear until menopause. After age 40, 75% of pregnancies are unplanned and may result in profound physical and emotional impact. Clinical evaluation must be relied on to diagnose menopause, since hormonal levels fluctuate widely. Until menopause is confirmed, some potential for pregnancy remains; at age 45, womens sterility rate is 55%. Older gravidas experience higher rates of diabetes, hypertension, and death. Many safe and effective contraceptive options are available to perimenopausal women. In addition to preventing an unplanned and higher-risk pregnancy, perimenopausal contraception may improve abnormal uterine bleeding, hot flashes, and menstrual migraines. Long-acting reversible contraceptives, including the levonorgestrel intrauterine system (LNG-IUS), the etonogestrel subdermal implant (ESI), and the copper intrauterine device (Cu-IUD), provide high efficacy without estrogen. LNG-IUS markedly decreases menorrhagia commonly seen in perimenopause. Both ESI and LNG-IUS provide endometrial protection for women using estrogen for vasomotor symptoms. Women without cardiovascular risk factors can safely use combined hormonal contraception. The CDCs Medical Eligibility Criteria for Contraceptive Use informs choices for women with comorbidities. No medical contraindications exist for levonorgestrel emergency-contraceptive pills, though obesity does decrease efficacy. In contrast, the Cu-IUD provides reliable emergency and ongoing contraception regardless of body mass index (BMI).

Surveillance and Care of the Gynecologic Cancer Survivor

Abstract Background: Care of the gynecologic cancer survivor extends beyond cancer treatment to encompass promotion of sexual, cardiovascular, bone, and brain health; management of fertility, contraception, and vasomotor symptoms; and genetic counseling. Methods: This is a narrative review of the data and guidelines regarding care and surveillance of the gynecologic cancer survivor. We searched databases including PubMed, Cochrane, and Scopus using the search terms gynecologic cancer, cancer surveillance, and cancer survivor and reached a consensus for articles chosen for inclusion in the review based on availability in the English language and publication since 2001, as well as key older articles, consensus statements, and practice guidelines from professional societies. However, we did not undertake an extensive systematic search of the literature to identify all potentially relevant studies, nor did we utilize statistical methods to summarize data. We offer clinical recommendations for the management of gynecologic cancer survivors based on review of evidence and our collective clinical experience. Results: Key messages include the limitations of laboratory studies, including CA-125, and imaging in the setting of gynecologic cancer surveillance, hormonal and non-hormonal management of treatment-related vasomotor symptoms and genitourinary syndrome of menopause, as well as recommendations for general health screening, fertility preservation, and contraception. Conclusions: A holistic approach to care extending beyond cancer treatment alone benefits gynecologic cancer survivors. In addition to surveillance for cancer recurrence and late treatment side effects, survivors benefit from guidance on hormonal, contraceptive, and fertility management and promotion of cardiovascular, bone, brain, and sexual health.

Repeat retail clinic visits: impact of insurance coverage and age of patient.

As retail clinics provide a less costly alternative for health care, it would be reasonable to expect an increase in multiple (repeat) retail visits by those patients who may have expenses for receiving primary care. If costs were not a significant factor, then repeat visits should not be significantly different between these patients and those with coverage for primary care visits. The hypothesis for this study was that patients with the potential for out-of-pocket expenses would have a higher frequency of repeat retail clinic visits within 180 days compared to those with primary care coverage. A retrospective chart review was conducted of 5703 patients utilizing a retail clinic in Rochester, Minnesota from January 1, 2009 through June 30, 2009. The first visit to the retail clinic was considered the index visit and the chart was reviewed for repeat retail clinic visits within the next 180 days. Using a multiple logistic regression model, the odds of a pediatric patient (N=2344) having a repeat retail visit within 180 days of the index visit were not significantly impacted by insurance coverage (P=0.4209). Of the 3359 adult patients, those with unknown coverage had a 25.6% higher odds ratio of repeat retail clinic visits than those with insurance coverage (odds ratio 1.2557, confidence interval 1.0421-1.5131). This study suggested that when cost is an issue, the adult patient may favor retail clinics for episodic, low-acuity health care. In contrast, the pediatric population did not, suggesting that other factors, such as convenience, may play more of a role in the choice of episodic health care for this age group.

Increased Anxiety and Length of Treatment Associated With Depressed Patients Who are Readmitted to Collaborative Care

In 2008, the Institute for Clinical Systems Improvement (ICSI) in Minnesota implemented a model of collaborative care management (CCM) for treatment of depression in primary care. This resulted in significant improvements on both clinical response and remission over usual care, although an increase in utilization metrics has been observed. Mental health comorbidities have previously been significantly associated with an increased likelihood of not responding to initial treatment. This retrospective study hypothesized that patients with mental health comorbidities are more likely to be associated with patients who were readmitted into CCM with recurrent depression. A total of 145 patients who had completed CCM were studied; of these, 32 were diagnosed with recurrent depression and were readmitted to CCM, and 113 were in remission for at least 4 months. There were no statistically significant demographic differences between the 2 groups. The initial screening GAD-7 score for anxiety was significantly increased in the readmission group (12.81 vs 9.20, P = .001) as was the average length of treatment from initial diagnosis to remission (168.09 vs 120.99 days, P = .002). All other initial screening tests were not different between the groups. When controlling for the independent variables by multiple logistic regression, the odds ratio for GAD-7 was 1.1156 (CI = 1.0.192 to 1.2212, P = .0177) and for days of treatment in CCM was 1.0123 (CI = 1.0041 to 1.0206, P = .0033). Patients who are readmitted to CCM for recurrent depression have a statistically increased risk of associated anxiety and a longer treatment course than those who have remained in remission for at least 4 months.

Current Diagnosis and Treatment in Family Medicine

Type and Scope of Book: A multiauthored practical review of the diagnosis and treatment of conditions commonly seen in family medicine.