Open-Label Pilot Study of a Clinician-Facing Decision-Support Algorithm for Blood Pressure Forecasting During Cesarean Delivery Under Spinal Anesthesia
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 入组人数
- 20
- 试验地点
- 1
- 主要终点
- Root Mean Square Error of 1-Minute-Ahead Mean Arterial Pressure Forecast
研究概览
简要总结
This single-center, open-label pilot study evaluates a clinician-facing decision-support algorithm that displays real-time forecasts of maternal mean arterial pressure (MAP), a measure of blood pressure, during elective cesarean delivery under spinal anesthesia. The display provides 1-, 2-, and 3-minute MAP forecasts from the time of spinal anesthesia administration until delivery or up to 20 minutes, whichever occurs first. Clinicians continue to manage blood pressure according to usual institutional practice, including phenylephrine infusion and bolus dosing, and retain full autonomy over treatment decisions; the study display does not provide dosing recommendations. The primary objective is to assess the prospective accuracy of short-horizon MAP forecasts. Secondary outcomes assess intraoperative hypotension burden and phenylephrine exposure during the observation window, including exploratory comparison with matched nonconcurrent controls.
详细描述
This single-center, open-label, single-group pilot study evaluated the prospective performance and operating-room feasibility of a clinician-facing autoregressive with exogenous input (ARX) decision-support algorithm for short-horizon maternal blood pressure forecasting during elective cesarean delivery under spinal anesthesia. Adult pregnant patients at term undergoing elective cesarean delivery with planned spinal anesthesia and prophylactic phenylephrine management were enrolled at a tertiary care academic hospital.
The ARX system generated real-time forecasts of maternal mean arterial pressure (MAP) at 1-, 2-, and 3-minute horizons from the time of spinal anesthesia administration until delivery or 20 minutes, whichever occurred first. The model used prior MAP values together with time-stamped phenylephrine infusion and bolus dosing and intrathecal bupivacaine dose/time as inputs. Forecasts were displayed on a dedicated screen adjacent to the anesthesia workstation. The display was intended to support clinician awareness of short-horizon hemodynamic trends and did not provide dosing recommendations. Blood pressure management remained under usual clinical care, including phenylephrine infusion and bolus administration according to institutional practice, and treating anesthesiologists retained full autonomy over all management decisions.
The primary objective was to assess prospective forecast accuracy at each prediction horizon using the difference between predicted and observed MAP during the study observation window. Additional analyses assessed other forecast-accuracy metrics, short-horizon identification of hypotension defined as MAP below 80% of baseline, and implementation feasibility based on uninterrupted display operation and clinician-reported overrides. Baseline MAP was defined as the mean of the last three pre-spinal noninvasive blood pressure measurements. Baseline MAP was defined as the mean of the last three pre-spinal noninvasive blood pressure measurements. Noninvasive blood pressure was recorded at 1-minute intervals, and model inputs were entered in real time by in-room research staff. Secondary outcomes assessed intraoperative hypotension burden and phenylephrine exposure during the observation window, including exploratory comparison with matched nonconcurrent controls; these analyses were not part of prospective assignment to the study intervention.
研究设计
- 研究类型
- Interventional
- 分配方式
- Na
- 干预模型
- Single Group
- 主要目的
- Other
- 盲法
- None
入排标准
- 年龄范围
- 18 Years 至 45 Years（Adult）
- 性别
- Female
- 接受健康志愿者
- 否
入选标准
- •Adult pregnant individuals (≥18 years old) presenting for elective or scheduled cesarean delivery.
- •ASA physical status 2 or 3 (obstetric patients without severe comorbidities).
- •Singleton pregnancy at term (≥37 weeks gestation).
- •Planned spinal anesthesia for cesarean delivery with phenylephrine infusion (and/or boluses) as the primary vasopressor.
- •Able to provide informed consent.
- •No known fetal anomalies or intrauterine demise.
排除标准
- •Pre-existing or gestational hypertensive disorders (e.g., chronic hypertension, preeclampsia, eclampsia) or use of cardiovascular medications that can affect blood pressure or heart rate (e.g.
- •propranolol for migraine)
- •Known major cardiovascular disease or arrhythmias requiring treatment (e.g., heart failure, significant valvular disease).
- •Planned use of non-phenylephrine vasopressors (e.g., ephedrine, norepinephrine) for routine BP management.
- •Allergy or contraindication to bupivacaine or phenylephrine.
- •Urgent or emergent cesarean delivery (where time constraints may not allow for adequate data collection or informed consent).
- •Inability to cooperate with protocol procedures.
研究组 & 干预措施
ARX Decision-Support Display
Participants undergoing elective cesarean delivery under spinal anesthesia received standard clinical management plus a clinician-facing ARX decision-support display that showed 1-, 2-, and 3-minute forecasts of maternal mean arterial pressure from spinal anesthesia administration until delivery or up to 20 minutes, whichever occurred first. The display did not provide dosing recommendations. Phenylephrine infusion and bolus dosing remained under clinician direction according to institutional practice.
干预措施: ARX Decision-Support Display (Other)
结局指标
主要结局
Root Mean Square Error of 1-Minute-Ahead Mean Arterial Pressure Forecast
时间窗: From spinal anesthesia administration until delivery or up to 20 minutes, whichever occurred first.
Patient-level mean root mean square error (RMSE) between algorithm-predicted and observed maternal mean arterial pressure (MAP) for the 1-minute forecast horizon using minute-level intraoperative data.
Root Mean Square Error of 2-Minute-Ahead Mean Arterial Pressure Forecast
时间窗: From spinal anesthesia administration until delivery or up to 20 minutes, whichever occurred first.
Patient-level mean root mean square error (RMSE) between algorithm-predicted and observed maternal mean arterial pressure (MAP) for the 2-minute forecast horizon using minute-level intraoperative data.
Root Mean Square Error of 3-Minute-Ahead Mean Arterial Pressure Forecast
时间窗: From spinal anesthesia administration until delivery or up to 20 minutes, whichever occurred first.
Patient-level mean root mean square error (RMSE) between algorithm-predicted and observed maternal mean arterial pressure (MAP) for the 3-minute forecast horizon using minute-level intraoperative data.
次要结局
- Incidence of Maternal Hypotension During the Observation Window(From spinal anesthesia administration until delivery or up to 20 minutes, whichever occurred first.)
- Duration of Maternal Hypotension During the Observation Window(From spinal anesthesia administration until delivery or up to 20 minutes, whichever occurred first.)
- Total Phenylephrine Dose During the Observation Window(From spinal anesthesia administration until delivery or up to 20 minutes, whichever occurred first.)
研究者
Vesela Kovacheva, MD
Associate Professor
Brigham and Women's Hospital