Intrapartum electronic fetal heart rate monitoring to predict acidemia at birth with the use of deep learning.

BACKGROUND: Electronic fetal monitoring is used in most US hospital births but has significant limitations in achieving its intended goal of preventing intrapartum hypoxic-ischemic injury. Novel deep learning techniques can improve complex data processing and pattern recognition in medicine. OBJECTIVE: This study aimed to apply deep learning approaches to develop and validate a model to predict fetal acidemia from electronic fetal monitoring data. STUDY DESIGN: The database was created using intrapartum electronic fetal monitoring data from 2006 to 2020 from a large, multisite academic health system. Data were divided into training and testing sets with equal distribution of acidemic cases. Several different deep learning architectures were explored. The primary outcome was umbilical artery acidemia, which was investigated at 4 clinically meaningful thresholds: 7.20, 7.15, 7.10, and 7.05, along with base excess. The receiver operating characteristic curves were generated with the area under the receiver operating characteristic assessed to determine the performance of the models. External validation was performed using a publicly available Czech database of electronic fetal monitoring data. RESULTS: A total of 124,777 electronic fetal monitoring files were available, of which 77,132 had <30% missingness in the last 60 minutes of the electronic fetal monitoring tracing. Of these, 21,041 were matched to a corresponding umbilical cord gas result, of which 10,182 were time-stamped within 30 minutes of the last electronic fetal monitoring reading and composed the final dataset. The prevalence rates of the outcomes in the data were 20.9% with a pH of <7.2, 9.1% with a pH of <7.15, 3.3% with a pH of <7.10, and 1.3% with a pH of <7.05. The best performing model achieved an area under the receiver operating characteristic of 0.85 at a pH threshold of <7.05. When predicting the joint outcome of both pH of <7.05 and base excess of less than -10 meq/L, an area under the receiver operating characteristic of 0.89 was achieved. When predicting both pH of <7.20 and base excess of less than -10 meq/L, an area under the receiver operating characteristic of 0.87 was achieved. At a pH of <7.15 and a positive predictive value of 30%, the model achieved a sensitivity of 90% and a specificity of 48%. CONCLUSION: The application of deep learning methods to intrapartum electronic fetal monitoring analysis achieves promising performance in predicting fetal acidemia. This technology could help improve the accuracy and consistency of electronic fetal monitoring interpretation.

Insomnia.

Insomnia is highly prevalent in clinical practice, occurring in up to 50% of primary care patients. Insomnia can present independently or alongside other medical conditions or mental health disorders and is a risk factor for the development and exacerbation of these other disorders if not treated. In 2016, the American College of Physicians recommended that insomnia be specifically targeted for treatment. The recommended first-line treatment for insomnia, whether the underlying cause has been identified or not, is cognitive behavioural therapy for insomnia (CBT-I). Currently, there is no global consensus regarding which pharmacological treatment has the best efficacy or risk-benefit ratio. Both CBT-I and pharmacological intervention are thought to have similar acute effects, but only CBT-I has shown durable long-term effects after treatment discontinuation. Administering a combined treatment of CBT-I and medication could decrease the latency to treatment response, but might diminish the durability of the positive treatment effects of CBT-I.

Remote Blood Pressure Monitoring With Social Support for Patients With Hypertension: A Randomized Clinical Trial.

Importance: Hypertension management has traditionally been based on office visits. Integrating remote monitoring into routine clinical practices and leveraging social support might improve blood pressure (BP) control. Objective: To evaluate the effectiveness of a bidirectional text monitoring program focused on BP control and medication adherence with and without social support in adults with hypertension. Design, Setting, and Participants: This randomized clinical trial included adults aged 18 to 75 treated at an academic family medicine practice in Philadelphia in 2018 and 2019. Patients had been seen at least twice in the prior 24 months and had at least 2 elevated BP measurements (>150/90 mm Hg or >140/90 mm Hg for patients aged 18-59 years or with diabetes or chronic kidney disease) during visits. All participants had a cell phone with text messaging, offered at least 1 support partner, and were taking maintenance medications to treat hypertension. Patients were randomized 2:2:1 to remote monitoring of BP and medication adherence (RM), remote monitoring of BP and medication adherence with feedback provided to a social support partner (SS), or usual care (UC). Data were analyzed on an intention-to-treat basis between October 14, 2019, and May 30, 2020, and were revisited from May 23 through June 2, 2023. Interventions: The RM and SS groups received an automatic home BP monitor, 3 weekly texts requesting BP measurements, 1 weekly text inquiring about medication adherence, and a weekly text with feedback. In the SS arm, support partners received a weekly progress report. The UC group received UC through their primary care practice. Clinicians caring for the patients in the intervention groups received nudges via electronic health records to adjust medications when 3 of 10 reported BP measurements were elevated. Patients were followed up for 4 months. Main Outcomes and Measures: The primary outcome was systolic BP at 4 months measured during the final follow-up visit. Secondary outcomes included achievement of normotension and diastolic BP. Results: In all, 246 patients (mean [SD] age, 50.9 [11.4] years; 175 females [71.1%]; 223 Black individuals [90.7%] and 13 White individuals [5.3%]) were included in the intention-to-treat analysis: 100 patients in the RM arm, 97 in the SS arm, and 49 in the UC arm. Compared with the UC arm, there was no significant difference in systolic or diastolic BP at the 4-month follow-up visit in the RM arm (systolic BP adjusted mean difference, -5.25 [95% CI, -10.65 to 0.15] mm Hg; diastolic BP adjusted mean difference, -1.94 [95% CI, -5.14 to 1.27] mm Hg) or the SS arm (systolic BP adjusted mean difference, -0.91 [95% CI, -6.37 to 4.55] mm Hg; diastolic BP adjusted mean difference, -0.63 [95% CI, -3.77 to 2.51] mm Hg). Of the 206 patients with a final BP measurement at 4 months, BP was controlled in 49% (41 of 84) of patients in the RM arm, 31% (27 of 87) of patients in the SS arm, and 40% (14 of 35) of patients in the UC arm; these rates did not differ significantly between the intervention arms and the UC group. Conclusions and Relevance: In this randomized clinical trial, neither remote BP monitoring nor remote BP monitoring with social support improved BP control compared with UC in adults with hypertension. Additional efforts are needed to examine whether interventions directed at helping patients remember to take their BP medications can lead to improved BP control. Trial Registration: ClinicalTrials.gov Identifier: NCT03416283.

Why Treat Insomnia?

"Why treat insomnia?" This question grows out of the perspective that insomnia is a symptom that should only receive targeted treatment when temporary relief is needed or until more comprehensive gains may be achieved with therapy for the parent or precipitating medical or psychiatric disorders. This perspective, however, is untenable given recent data regarding the prevalence, course, consequences, and costs of insomnia. Further, the emerging data that the treatment of insomnia may promote better medical and mental health (alone or in combination with other therapies) strongly suggests that the question is no longer "why treat insomnia," but rather "when isn't insomnia treatment indicated?" This perspective was recently catalyzed with the American College of Physicians' recommendation that chronic insomnia should be treated and that the first line treatment should be cognitive-behavioral therapy for insomnia (CBT-I).

Effect of Financial Incentives on Patient Use of Mailed Colorectal Cancer Screening Tests: A Randomized Clinical Trial.

Importance: Mailing fecal immunochemical test (FIT) kits to patients' homes has been shown to boost colorectal cancer screening rates, but response rates remain limited, and organized programs typically require repeated outreach attempts. Behavioral economics has shown that offering salient financial incentives to patients may increase participation in preventive health. Objective: To compare the impact of different financial incentives for mailed FIT outreach. Design, Setting, and Participants: This 4-parallel-arm randomized clinical trial included patients aged 50 to 75 years who had an established primary care clinician, at least 2 visits in the prior 2 years, and were eligible for colorectal cancer screening and not up-to-date. This study was conducted at urban primary care practices at an academic health system from December 2015 to February 2018. Data analysis was conducted from March 2018 to September 2018. Interventions: Eligible patients received a letter from their primary care clinician that included a mailed FIT kit and instructions for use. They were randomized in a 1:1:1:1 ratio to receive (1) no financial incentive; (2) an unconditional $10 incentive included with the mailing; (3) a $10 incentive conditional on FIT completion; or (4) a conditional lottery with a 1-in-10 chance of winning $100 after FIT completion. Main Outcomes and Measures: Fecal immunochemical test completion within 2 and 6 months of initial outreach. Results: A total of 897 participants were randomized, with a median age of 57 years (interquartile range, 52-62 years); 56% were women, and 69% were black. The overall completion rate across all arms was 23.5% at 2 months. The completion rate at 2 months was 26.0% (95% CI, 20.4%-32.3%) in the no incentive arm, 27.2% (95% CI, 21.5%-33.6%) in the unconditional incentive arm, 23.2% (95% CI, 17.9%-29.3%) in the conditional incentive arm, and 17.7% (95% CI, 13.0%-23.3%) in the lottery incentive arm. None of the arms with an incentive were statistically superior to the arm without incentive. The overall FIT completion rate across all arms was 28.9% at 6 months, and there was also no difference by arm. The completion rate at 6 months was 32.7% (95% CI, 26.6%-39.3%) in the no incentive arm, 31.7% (95% CI, 25.7%-38.2%) in the unconditional incentive arm, 26.8% (95% CI, 21.1%-33.1%) in the conditional incentive arm, and 24.3% (95% CI, 18.9%-30.5%) in the lottery incentive arm. Conclusions and Relevance: Mailed FIT resulted in high colorectal cancer screening response rates in this population, but different forms of financial incentives of the same expected value ($10) did not incrementally increase FIT completion rates. The incentive value may have been too small or financial incentives may not be effective in this context. Trial Registration: ClinicalTrials.gov Identifier: NCT02594150.

Safe Passage: Improving the Transition of Care Between Triage and Labor and Delivery.

OBJECTIVE: The multifaceted nature of the transition of care from the triage unit to labor and delivery has historically led to confusion, delays, and errors in care. This study evaluated the effect of standardization of roles and communication on improving this transition. METHODS: A multidisciplinary team was assembled to define and standardize roles of team members. A huddle safety board was created as a visual aid to promote closed-loop communication during an admission bedside huddle. The primary metrics collected were duration of time from the admission decision in the triage unit to when the admission huddle was completed on labor and delivery, duration of time from the admission decision in the triage unit to initiation of the plan of care and documented completion of the admission huddle. RESULTS: There was a 66-minute reduction in time from the admission decision to the huddle completion between the preintervention and postintervention periods. There was a 93-minute reduction in the time from the admission decision to when the plan of care was initiated between the preintervention and post-intervention periods. The weekly huddle compliance rate improved from 48% to 84% by the postintervention period. CONCLUSIONS: The implementation of standardized roles and processes facilitating closed-loop communication decreases delays in communication and initiation of care in pregnant women transferred from the triage unit to labor and delivery.

Improving Staff Communication and Transitions of Care Between Obstetric Triage and Labor and Delivery.

OBJECTIVE: To improve staff perception of the quality of the patient admission process from obstetric triage to the labor and delivery unit through standardization. DESIGN: Preassessment and postassessment online surveys. SETTING: A 13-bed labor and delivery unit in a quaternary care, Magnet Recognition Program, academic medical center in Pennsylvania. PARTICIPANTS: Preintervention (n = 100), postintervention (n = 52), and 6-month follow-up survey respondents (n = 75) represented secretaries, registered nurses, surgical technicians, certified nurse-midwives, nurse practitioners, maternal-fetal medicine fellows, anesthesiologists, and obstetric and family medicine attending and resident physicians from triage and labor and delivery units. METHODS: We educated staff and implemented interventions, an admission huddle and safety time-out whiteboard, to standardize the admission process. Participants were evaluated with the use of preintervention, postintervention, and 6-month follow-up surveys about their perceptions regarding the admission process. Data tracked through the electronic medical record were used to determine compliance with the admission huddle and whiteboards. RESULTS: A 77% reduction (decrease of 49%) occurred in the perception of incomplete patient admission processes from baseline to 6-month follow-up after the intervention. Postintervention and 6-month follow-up survey results indicated that 100% of respondents responded strongly agree/agree/neutral that the new admission process improved communication surrounding care for patients. Data in the electronic medical record indicated that compliance with use of admission huddles and whiteboards increased from 50% to 80% by 6 months. CONCLUSION: The new patient admission process, including a huddle and safety time-out board, improved staff perception of the quality of admission from obstetric triage to the labor and delivery unit.