Applying machine learning methods to psychosocial screening data to improve identification of prenatal depression: Implications for clinical practice and research.

We utilized machine learning (ML) methods on data from the PROMOTE, a novel psychosocial screening tool, to quantify risk for prenatal depression for individual patients and identify contributing factors that impart greater risk for depression. Random forest algorithms were used to predict likelihood for being at high risk for prenatal depression (Edinburgh Postnatal Depression Scale; EPDS ≥ 13 and/or positive self-injury item) using data from 1715 patients who completed the PROMOTE. Performance matrices were calculated to assess the ability of the PROMOTE to accurately classify patients. Probability for depression was calculated for individual patients. Finally, recursive feature elimination was used to evaluate the importance of each PROMOTE item in the classification of depression risk. PROMOTE data were successfully used to predict depression with acceptable performance matrices (accuracy = 0.80; sensitivity = 0.75; specificity = 0.81; positive predictive value = 0.79; negative predictive value = 0.97). Perceived stress, emotional problems, family support, age, major life events, partner support, unplanned pregnancy, current employment, lifetime abuse, and financial state were the most important PROMOTE items in the classification of depression risk. Results affirm the value of the PROMOTE as a psychosocial screening tool for prenatal depression and the benefit of using it in conjunction with ML methods. Using such methods can help detect underreported outcomes and identify what in patients' lives makes them more vulnerable, thus paving the way for effective individually tailored precision medicine.

Progesterone effects on vaginal cytokines in women with a history of preterm birth.

OBJECTIVE: To determine the effect of intramuscular progesterone on the vaginal immune response of pregnant women with a history of prior preterm birth. METHODS: A prospective, cohort study of women at 11-16 weeks gestation, ≥18 years of age, and carrying a singleton pregnancy was conducted from June 2016 to August 2017 after IRB approval. Women in the progesterone arm had a history of preterm birth and received weekly intramuscular 17-hydroxyprogesterone caproate. Controls comprised of women with healthy, uncomplicated pregnancies. Excluded were women with vaginitis, diabetes mellitus, hypertension, or other chronic diseases affecting the immune response. A vaginal wash was performed at enrollment, at 26-28 weeks, and at 35-36 weeks gestation. Samples underwent semi-quantitative detection of human inflammatory markers. Immunofluorescence pixel density data was analyzed and a P value <0.05 was considered significant. RESULTS: There were 39 women included, 10 with a prior preterm birth and 29 controls. The baseline demographics and pregnancy outcomes for both groups were similar in age, parity, race, BMI, gestational age at delivery, mode of delivery, and birth weight. Enrollment cytokines in women with a prior preterm birth, including IL-1 alpha (39.2±25.1% versus 26.1±13.2%; P = 0.04), IL-1 beta (47.9±26.4% versus 24.9±17%; P<0.01), IL-2 (16.7±9.3% versus 11.3±6.3%; P = 0.03), and IL-13 (16.9±12.4% versus 8.2±7.4%; P = 0.01) were significantly elevated compared to controls. In the third trimester the cytokine densities for IL-1 alpha (26.0±18.2% versus 22.3±12.0%; P = 0.49), IL-1 beta (31.8±15.9% versus 33.1±16.8%; P = 0.84), IL-2 (10.0±8.4% versus 10.9±5.9%; P = 0.71), and IL-13 (9.1±5.9% versus 10.0±6.5%; P = 0.71) were all statistically similar between the progesterone arm and controls, respectively. CONCLUSION: There is an increased cytokine presence in vaginal washings of women at risk for preterm birth which appears to be modified following the administration of 17- hydroxyprogesterone caproate to levels similar to healthy controls.

Comparison of Subcuticular Suture Type for Skin Closure After Cesarean Delivery: A Randomized Controlled Trial.

OBJECTIVE: To compare the rate of wound complications among women who underwent cesarean delivery through a Pfannenstiel skin incision followed by subcuticular closure with either poliglecaprone 25 suture or polyglactin 910 suture. METHODS: Patients undergoing nonemergent cesarean delivery at or beyond 37 weeks of gestation were randomized to undergo subcuticular skin closure with either poliglecaprone 25 or polyglactin 910. The primary outcome was a wound composite outcome of one or more of the following: surgical site infection, wound separation, hematoma, or seroma within the first 30 days postpartum. To detect a reduction in the primary outcome rate from 12% to 4%, with a power of 0.90 and a two-tailed α of 0.05, 237 women per study group were required. Analysis was performed according to the intent-to-treat principle. RESULTS: From May 28, 2015, to August 5, 2016, 275 women were randomized to poliglecaprone 25 and 275 to polyglactin 910, of whom 520 (95%) were included in the final analysis: 263 in the poliglecaprone 25 group [of whom 231 (88%) actually underwent poliglecaprone 25 closure) and 257 in the polyglactin 910 group [of whom 209 (81%) actually underwent polyglactin 910 closure]. The groups were similar in demographic characteristics, medical comorbidities, and perioperative characteristics. Poliglecaprone 25 was associated with a significantly decreased rate of overall wound complications when compared with polyglactin 910, 8.8% compared with 14.4% (relative risk 0.61, 95% CI 0.37-0.99; P=.04). CONCLUSION: Closure of the skin after cesarean delivery with poliglecaprone 25 suture decreases the rate of wound complications compared with polyglactin 910 suture. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov, NCT02459093.

Unilateral adrenal infarction in pregnancy.

A 25-year-old pregnant woman at 28 weeks gestational age presented with increasing abdominal pain and was found to have a unilateral adrenal infarction on a CT scan of the abdomen. Her medical history was unremarkable. There was no evidence of adrenal insufficiency with normal cortisol and adenocorticotropic hormone levels for pregnancy. Evaluation of thrombophilia disorders established the patient to be heterozygous for methylenetetrahydrofolatereductase C677T gene mutation as the only finding. The patient was anticoagulated to prevent contralateral thrombosis. At 32 weeks she experienced spontaneous rupture of membranes. One week later she delivered vaginally and remained anticoagulated for the puerperium.

Outcomes after an excisional procedure for cervical intraepithelial neoplasia in HIV-infected women.

OBJECTIVE: To determine predictors of treatment failure and recurrence after surgical excisional procedures for CIN in HIV-infected women. METHODS: A retrospective cohort study was conducted in which 136 eligible HIV-infected women treated for CIN between 1999 and 2005 were included. Data were abstracted from charts and computer databases. Treatment failures were defined as the presence of CIN 1+ at initial follow-up. Recurrences were defined as the presence of CIN 1+ subsequent to initial normal follow-up. RESULTS: Treatment failure at initial follow-up was common, occurring in 51% of CIN 1 and 55% of CIN 2+. Most lesions detected at treatment failure were high grade (>70%), regardless of the grade of initial lesion. Significant risk factors for treatment failure were loop electrosurgical excision procedure (LEEP) compared to cold knife conization (RR=1.76; 95% CI: 1.15-2.64), and low CD4+ count (p=0.04). Among those with an initial normal clinical evaluation, 55% eventually recurred. As with treatment failure, most lesions detected at recurrence were high grade. Risk factors for recurrence included use of LEEP (hazard ratio [HR]=3.38; 95% CI: 1.55-7.39), higher HIV RNA level, and the presence of positive margins at treatment (HR=6.12; 95% CI: 1.90-19.73). CONCLUSIONS: Most CIN treatment of HIV-infected women studied either failed or resulted in recurrence. Of particular concern, many of these subsequent lesions were high grade. Conization, however, was associated with significantly less failure/recurrence than LEEP. Clinicians treating CIN in HIV-infected women should avoid raising expectations of cure and instead focus on the achievable goal of cancer prevention until there are better therapies for this patient population.