Implementation of a Clinical Decision Support Tool for Postpartum Depression (CDS)

This study will evaluate the use of an automated process in the electronic health record (EHR) that will help providers to detect patients at risk of developing postpartum depression (PPD).

Study Overview

• Status: Not yet recruiting
• Conditions: Postpartum Depression
• Intervention / Treatment: Other: Clinical Decision Support Tool

Detailed Description

The goal of this randomized clinical trial is to assess the implementation of a clinical decision support (CDS) tool. The tool is designed to assist providers in managing patients at risk of developing of postpartum depression.

Investigators hypothesize that this tool will be acceptable and feasible for use and improve the use of mental health services for postpartum depression.

Patients in the control arm will receive usual care, while those in the intervention arm will receive CDS.

Clinicians will manage patients per usual care, including initiating PPD preventive such as conducting referrals to nutrition and behavioral health, suggest educational readings through patient portals, or no actions. Clinicians in the intervention arm will refer patients based on the CDS.

• Study Type: Interventional
• Enrollment (Estimated): 160
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Rochelle Joly, MD; Phone Number: 646-962-4222; Email: roj9069@med.cornell.edu

Study Locations

• United States
  • New York
    • Brooklyn, New York, United States, 11215
      • Center for Community Health: 515 6th street (3rd floor)
      • Contact: Tracy Grossman, MD; Email: trg2005@med.cornell.edu
      • Contact: Jessica Miller; Phone Number: 718-499-2273
      • Sub-Investigator: Tracy Grossman, MD
    • New York, New York, United States, 10038
      • Ob GYN Lower Manhattan 156 William street, New York City
      • Contact: Szilvia Nagy, MD; Email: szn3001@med.cornell.edu
      • Sub-Investigator: Szilvia Nagy, MD
    • New York, New York, United States, 10065
      • Weill Cornell Medicine- Women's Health practice 505 East 70th street, New York City
      • Contact: Rochelle Joly, MD; Email: roj9069@med.cornell.edu
      • Sub-Investigator: Rochelle Joly, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• 18 years or older
• being seen at one of participating clinics
• pregnancy at 20 week gestation or more

Exclusion Criteria:

• Does not speak inclusion
• does not have internet access

Clinician eligibility:

• If they manage patients in the three clinics as a board-certified OBGYN clinician.
• No exclusion criteria apply for clinician based on their knowledge and experience in treating PPD

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Supportive Care
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

3

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention: CDS support , clinician; Clinicians in the intervention arm will refer patients based on the CDS.The CDS will alert clinicians only if patients have high risk of developing PPD, and provide clinicians with risk score, risk factors, and anticipatory actions with an order set to assist with ordering. Clinicians will make the ultimate clinical judgement after receiving CDS aid, including taking no actions towards PPD prevention. Clinicians will manage patients per usual care, including initiating PPD preventive such as conducting referrals to nutrition and behavioral health, suggest educational readings through patient portals, or no actions.	Other: Clinical Decision Support Tool; The CDS in and AI algorithm that will alert clinicians only if patients have high risk of developing PPD, and provide clinicians with risk score, risk factors, and anticipatory actions with an order set to assist with ordering. Clinicians will make the ultimate clinical judgement after receiving CDS aid, including taking no actions towards PPD prevention. Clinicians will manage patients per usual care, including initiating PPD prevention such as conducting referrals to nutrition and behavioral health, suggest educational readings through patient portals, or no actions. Clinicians in the intervention arm will refer patients based on the CDS.
No Intervention: No intervention: Patients; The CDS will alert clinicians only if patients have high risk of developing PPD. Clinicians will manage patients per usual care, including initiating PPD preventive such as conducting referrals to nutrition and behavioral health, suggest educational readings through patient portals, or no actions.
Experimental: Intervention: Patients	Other: Clinical Decision Support Tool; The CDS in and AI algorithm that will alert clinicians only if patients have high risk of developing PPD, and provide clinicians with risk score, risk factors, and anticipatory actions with an order set to assist with ordering. Clinicians will make the ultimate clinical judgement after receiving CDS aid, including taking no actions towards PPD prevention. Clinicians will manage patients per usual care, including initiating PPD prevention such as conducting referrals to nutrition and behavioral health, suggest educational readings through patient portals, or no actions. Clinicians in the intervention arm will refer patients based on the CDS.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Acceptability as measured by Unified Theory of Technology Acceptance Theory (UTAUT).	UTAUT has five constructs: performance expectation, effort expectation, social influence, facilitating conditions, and behavioral intention. The performance expectation construct in UTAUT is the CDS's ability to identify patients at risk of PPD that clinicians agree with. For each construct, responses will be sought in the 7-point Likert scale, setting 1 as 'strongly disagree', 2 as 'disagree', to 7 as 'strongly agree'. We will average the acceptability survey responses at the end of the study for each of the 5 UTAUT constructs to create a binary variable. An average score of 5 or above will be considered acceptance and non-acceptance otherwise	One month after initiation of tool use and three months after use.
Appropriateness as measured by Appropriateness Measure (IAM).	IAM is a 4-item measure to assess the appropriateness of the intervention, respectively, with excellent usability. IAM is to be answered by participants in 5-point response scale: 1 = Completely disagree, 2 = Disagree, 3 = Neither agree nor disagree, 4 = Agree, 5 = Completely agree.	One month after initiation of tool use and three months after use.
Feasibility as measured by Feasibility of Intervention Measure (FIM).	FIM is a 4-item measure to assess the feasibility of the intervention, respectively, with excellent usability. FIM is to be answered by participants in 5-point response scale: 1 = Completely disagree, 2 = Disagree, 3 = Neither agree nor disagree, 4 = Agree, 5 = Completely agree.	One month after initiation of tool use and three months after use.
Mental Health service utilization as measured by number of mental health visits	Mental health service utilization includes presentations to ED or inpatient admission for mental health related reasons.	one month and three month

Collaborators and Investigators

• Sponsor: Weill Medical College of Cornell University
• Investigators: Principal Investigator: Yiye Zhang, PhD, Weill Medical College of Cornell University

Publications and helpful links

General Publications

• Rabin R, de Charro F. EQ-5D: a measure of health status from the EuroQol Group. Ann Med. 2001 Jul;33(5):337-43. doi: 10.3109/07853890109002087.
• Weiner BJ, Lewis CC, Stanick C, Powell BJ, Dorsey CN, Clary AS, Boynton MH, Halko H. Psychometric assessment of three newly developed implementation outcome measures. Implement Sci. 2017 Aug 29;12(1):108. doi: 10.1186/s13012-017-0635-3.
• Dunkel Schetter C, Tanner L. Anxiety, depression and stress in pregnancy: implications for mothers, children, research, and practice. Curr Opin Psychiatry. 2012 Mar;25(2):141-8. doi: 10.1097/YCO.0b013e3283503680.
• Curtin SC, Abma JC, Ventura SJ, Henshaw SK. Pregnancy rates for U.S. women continue to drop. NCHS Data Brief. 2013 Dec;(136):1-8.
• Cox EQ, Sowa NA, Meltzer-Brody SE, Gaynes BN. The Perinatal Depression Treatment Cascade: Baby Steps Toward Improving Outcomes. J Clin Psychiatry. 2016 Sep;77(9):1189-1200. doi: 10.4088/JCP.15r10174.
• Krause N, Borawski-Clark E. Social class differences in social support among older adults. Gerontologist. 1995 Aug;35(4):498-508. doi: 10.1093/geront/35.4.498.
• Zhang Y, Wang S, Hermann A, Joly R, Pathak J. Development and validation of a machine learning algorithm for predicting the risk of postpartum depression among pregnant women. J Affect Disord. 2021 Jan 15;279:1-8. doi: 10.1016/j.jad.2020.09.113. Epub 2020 Sep 30.
• Wang S, Pathak J, Zhang Y. Using Electronic Health Records and Machine Learning to Predict Postpartum Depression. Stud Health Technol Inform. 2019 Aug 21;264:888-892. doi: 10.3233/SHTI190351.
• Venkatesh KK, Nadel H, Blewett D, Freeman MP, Kaimal AJ, Riley LE. Implementation of universal screening for depression during pregnancy: feasibility and impact on obstetric care. Am J Obstet Gynecol. 2016 Oct;215(4):517.e1-8. doi: 10.1016/j.ajog.2016.05.024. Epub 2016 May 20.
• Werner E, Miller M, Osborne LM, Kuzava S, Monk C. Preventing postpartum depression: review and recommendations. Arch Womens Ment Health. 2015 Feb;18(1):41-60. doi: 10.1007/s00737-014-0475-y. Epub 2014 Nov 25.

Study record dates

Study Major Dates

• Study Start (Estimated): May 1, 2026
• Primary Completion (Estimated): December 1, 2026
• Study Completion (Estimated): December 1, 2026

Study Registration Dates

• First Submitted: February 7, 2025
• First Submitted That Met QC Criteria: February 7, 2025
• First Posted (Actual): February 10, 2025

Study Record Updates

• Last Update Posted (Actual): April 2, 2026
• Last Update Submitted That Met QC Criteria: March 30, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: Clinical decision support tool
• Additional Relevant MeSH Terms: Urogenital Diseases; Mental Disorders; Female Urogenital Diseases and Pregnancy Complications; Pregnancy Complications; Mood Disorders; Puerperal Disorders; Depressive Disorder; Depression, Postpartum
• Other Study ID Numbers: 24-03027259

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: The study protocol with the statistical analysis plan will be available following publication.
• IPD Sharing Time Frame: The data will be available once published.
• IPD Sharing Access Criteria: Anyone who subscribes to the journal, or has access online will be able to review the data.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No