CoChat
Sign Up
Cited by 99Mobile Health and mHealth ApplicationsArtificial Intelligence in Healthcare and EducationReproductive Health and Contraception

Reducing preconception risks among African American women with conversational agent technology

Open access
Jack, B., Bickmore, T., Hempstead, M., Yinusa-Nyahkoon, L., Sadikova, E., Mitchell, S., Gardiner, P., Adigun, F. +3 more·2015·The Journal of the American Board of Family Medicine
DOI 10.3122/jabfm.2015.04.140327PMC PMC4739811
Open this paper in CoChat — free accountOpen PDF

Abstract

BACKGROUND: Systems and tools are needed to identify and mitigate preconception health (PCH) risks, particularly for African American (AA) women, given persistent health disparities. We developed and tested "Gabby," an online preconception conversational agent system. METHODS: One hundred nongravid AA women 18-34 years of age were screened for over 100 PCH risks and randomized to the Gabby or control group. The Gabby group interacted with the system for up to six months; the control group received a letter indicating their health risks with a recommendation to talk with their clinician. The numbers, proportions, and types of risks were compared between groups. RESULTS: There were 23.7 (SD 5.9) risks identified per participant. Eighty-five percent (77 of 91) provided 6 month follow up data. The Gabby group had greater reductions in the number (8.3 vs. 5.5 risks, P < .05) and the proportion (27.8% vs 20.5%, P < 0.01) of risks compared to controls. The Gabby group averaged 63.7 minutes of interaction time. Seventy-eight percent reported that it "was easy to talk to Gabby" and 64% used information from Gabby to improve their health. CONCLUSION: Gabby was significantly associated with preconception risk reduction. More research is needed to determine if Gabby can benefit higher risk populations and if risk reduction is clinically significant.

AI snapshot

Written from the paper’s full text.

TL;DR

In a 6-month randomized controlled trial of 100 non-gravid African American women, mostly college-attending, the Gabby conversational agent was associated with greater reduction in preconception health risks than a control letter. The authors conclude Gabby holds promise but larger, more socio-demographically diverse trials are needed.

Key findings

  • Among 77 women with baseline and 6-month outcome data, the Gabby group resolved 27.8% (297/1,067) of reported risks versus 20.5% (224/1,091) in controls (p<0.01); average risks resolved were 8.3 vs 5.5 (p<0.01). The abstract reports the number of PCH risks as 34% higher (8.3 vs 5.5, p<.05) and proportion resolved as 25% higher (27.8% vs 20.5%, p<0.01).
  • At baseline, all participants had at least one PCH risk; mean (SD) was 23.7 (5.9), range 11–45. The most common content areas triggered were “Nutrition and Activity” (27.5%), “Infectious Disease” (16.4%), “Environmental Issues” (10.2%), and “Immunizations and Vaccines” (8.8%).
  • Gabby usage: 42 women interacted at least once; 144 interactions totaling 2,676 minutes; average session 18.6 (SD 12.1) minutes; average interaction time 63.7 (SD 70.4, range 2.8–286) minutes per woman; average 2.9 logins. 78% reported it “was easy to talk to Gabby,” 64% used information from Gabby to improve their health, 59% trusted her, 56% said Gabby did a good job answering questions, and 22% planned to use the information in the future.
  • Risks most often resolved in the Gabby group included “Bad diet or food choices” (18), “Not using multivitamin with folic acid or folic acid supplement” (16), “At risk for sexually transmitted infection” (15), “Not taking iron supplement” (13), “Use of caffeine” (12), and “At risk for tuberculosis” (12); these six accounted for 29% of risks resolved. Some clinically important risks infrequently or never resolved: “Any current tobacco use” (0/6), “Currently taking any over-the-counter medicines” (1/13), and “No birth control” (3/20).

Methods

  • A 6-month RCT (March 2013–February 2014) used a purposeful, convenience sample of 100 self-identified African American/black women, 18–34 years, English-speaking, not pregnant, with telephone and computer internet access. Recruitment sources were the HHS Office of Minority Health’s national Preconception Peer Educator program (n=86), a Healthy Start site in Florida (n=8), a Health Expo in Boston (n=4), and word of mouth (n=2).
  • All participants were screened for 107 distinct PCH risk factors across 12 content areas and randomized via sequentially numbered, opaque, sealed envelopes to Gabby or control. Gabby participants received bi-weekly reminder emails and interactions consisting of a greeting, review of identified risks, discussion of selected risks, and review/update of “My Health To-Do List.” Controls received a mailed letter listing their PCH risks with the suggestion to discuss them with a health care provider.
  • Baseline measures included demographics, General Self Efficacy Scale, Multidimensional Scale of Perceived Social Support, Everyday Discrimination Scale, and the 66-word Rapid Estimate of Adult Literacy in Health. Six-month outcomes were collected by online survey plus telephone call to determine whether each baseline risk was still active or resolved. Analyses used two-sided t-tests, chi-square/Fisher’s exact tests, Z-tests for proportions, and crude Poisson regressions.

Limitations

  • Stated: follow-up was relatively short and behavior change takes time; data were self-reported, with possible misunderstanding, wrong response selection, or intentional misinformation; social desirability bias, recall bias, and self-selection bias were possible; the control group also received a personalized risk letter, which may have led to underestimation of Gabby’s impact; Gabby was desktop/laptop-only, and uptake may have been limited by preference for telephone or tablet; average 2.9 logins over 6 months fell short of the ideal goal of one session per week.
  • Stated: the sample was mostly college-educated, computer literate, and reported high self-efficacy, high social support, and low perceived racial discrimination; authors call for a larger, more socio-demographically diverse group and note that whether reducing the number of risks is clinically significant remains unknown.
  • Evident from the text: the small sample (100 enrolled; 80 completed the 6-month follow-up phone call; 77 had both baseline and outcome data; 42 interacted with Gabby at least once) limits precision and generalizability, and the study measured risk resolution rather than clinical outcomes.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3122/jabfm.2015.04.140327

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 17 cited sources checked · 0 supported · 0 flagged

  • Findingown data

    At six months, Gabby-group women resolved an average of 8.3 risks (from an average of 23.2 identified), compared with 5.5 (of 24.2) in the control group (p<0.01).

    “At six months, women in the Gabby group resolved 8.3 risks on average (from 23.2 identified on average), compared to 5.5 (of 24.2) in the control group, (p<0.01).”
    Quote in the paperSubstantial claim
  • Findingown data

    The nutrition and physical activity content area had the most risks triggered, discussed, and resolved.

    “The nutrition and physical activity content area contained the most risks triggered, discussed, and resolved.”
    Quote in the paperNot a substantial claim
  • Findingown data

    Among the 77 women with both baseline and six-month outcome data, 27.8% (297/1,067) of reported risks were resolved in the Gabby group versus 20.5% (224/1,091) in the control group (p<0.01).

    “Among the 77 women for whom both baseline data and six month outcome data were available, 27.8% (297/1,067) of the reported risks were resolved in the Gabby group, compared to 20.5% (224/1,091) in the control group (Table 2, p<0.01).”
    Quote in the paperSubstantial claim
  • Interpretationcitation

    Our trust findings align with other studies showing that patients prefer sharing sensitive information with computerized agents perceived as less judgmental and having more time than traditional providers.

    “Our findings regarding participants’ trust in Gabby are consistent with other studies that indicate patients prefer sharing sensitive information with computerized agents who they perceive to be less judgmental and have more time than traditional providers.26”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [26] Bickmore T Pfeifer L Jack BW Taking the Time to Care: Empowering Low Health Literacy Hospital Patients with Virtual Nurse Agents Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI) 2009 Boston, MA 2009

      Not checked in the free run.

  • Premisecitation

    Studies using conversational agents have demonstrated significant clinical impacts on outcomes.

    “Conversational agents have also been used in studies that have shown significant clinical impact on outcomes.11, 17, 18”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [11] King A Bickmore T Campero M Employing “virtual advisors” in preventive care for underserved communities: results from the COMPASS study J Health Commun 2013 18 12 1449 64 23941610 PMC7187757

      Not checked in the free run.

    • cites [17] Ellis T Latham N DeAngelis T Thomas C Saint-Hilaire M Bickmore T Feasibility of a virtual exercise coach to promote walking in community-dwelling persons with Parkinson Disease American Journal of Physical Medicine and Rehabilitation 2013 92 6 472 485 23552335 PMC4266140

      Not checked in the free run.

    • cites [18] Bickmore T Silliman R Nelson K Cheng D Winter M Henaulat L Paasche-Orlow M A randomized controlled trial of an automated exercise coach for older adults Journal of the American Geriatrics Society 2013 61 1676 1683 24001030

      Not checked in the free run.

  • May combine two claims. 29
  • Classified as probably not a substantial claim. 19

  • May combine two claims.

    Findingown data

    Every participant had at least one PCH risk; the mean number was 23.7 (SD 5.9), with a range of 11 to 45.

    “all had at least one PCH risk with a mean (sd) of 23.7 (5.9), range of 11 to 45 PCH risks.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    In the Gabby group, 78% found it easy to talk with Gabby, 59% trusted her, 56% said she answered questions well, almost two thirds had used Gabby information to improve their health, and 22% planned to do so.

    “Most women in the Gabby group felt that it was easy to talk with Gabby (78%) and reported that they trusted her (59%). More than half (56%) stated that Gabby did a good job of answering their questions, almost two thirds reported that they had used information from Gabby to improve their health, and another 22% planned to do so in the future.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    Gabby-group participants were more likely than controls (64% vs 51%, p=.21) to report at least one primary care appointment within 6 months, but the difference was not significant.

    “They were also more likely than those in the control group (64% vs 51%, p=.21) to report at least one primary care appointment within 6 months, an important but non-significant finding potentially due to the relatively short follow-up period.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingown data

    About two thirds of the baseline sample worked at least part-time and had at least some college education, and 41% were students.

    “about two thirds were employed at least part-time and completed at least some college, and 41% were students.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingown data

    Most of the baseline sample reported high self-efficacy, high social support, and low perceived racial discrimination.

    “the majority reported high self-efficacy, high social support, and low perceived racial discrimination.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    The average number of risks triggered was 23.7 (SD 5.9): 23.2 in the Gabby group and 24.2 in the control group.

    “The average number of risks triggered was 23.7 (S.D. 5.9), per participant, 23.2 (5.95) for the Gabby group and 24.2 (5.84) for the control group.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingown data

    The 91 participants who completed the risk assessment triggered 2,158 risks in total: 1,067 in the Gabby group and 1,091 in the control group.

    “A total of 2,158 risks were triggered by the 91 participants who completed the risk assessment, 1067 by the Gabby group, and 1091 by the control group.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingown data

    The 99 women who provided baseline data had a mean age of 25.5 years.

    “The average age was 25.5 years;”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Users averaged 2.9 logins over 6 months, which was below our ideal of one session per week.

    “The average 2.9 logins per user over 6 months fell short of our ideal goal of one session per week and underscores the need to plan for the future of Gabby and how women will interact with her outside of the research setting.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    The most frequently triggered content area was Nutrition and Activity (27.5%), followed by Infectious Disease (16.4%), Environmental Issues (10.2%), and Immunizations and Vaccines (8.8%).

    “The most common content area triggered among all participants was “Nutrition and Activity,” (27.5%), followed by “Infectious Disease” (16.4%), “Environmental Issues” (10.2%), and “Immunizations and Vaccines” (8.8%).”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingown data

    Of the total Gabby interaction time, 30% was spent on Nutrition and Activity and 10.3% on Reproductive Health.

    “Thirty percent of the total time interacting with Gabby was spent discussing “Nutrition and Activity,” and 10.3% was spent discussing “Reproductive Health.””
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingown data

    The average Gabby session lasted 18.6 (SD 12.1) minutes, and average interaction time per woman over the study was 63.7 (SD 70.4, range 2.8-286) minutes.

    “The average session lasted 18.6 (S.D 12.1) minutes and the average interaction time with Gabby during the study was 63.7 (S.D 70.4, range 2.8–286) minutes per woman.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Some clinically important risks rarely or never resolved: current tobacco use (0 of 6 Gabby participants), taking over-the-counter medicines (1 of 13), and no birth control (3 of 20).

    “On the other hand, there were clinically-important risks that infrequently or never resolved, such as: “Any current tobacco use” (0 Gabby group participants resolved it out of 6 identified at baseline); “Currently taking any over-the-counter medicines” (1 resolved out of 13); and “No birth control” (3 resolved out of 20).”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingown data

    More than 90% of the baseline sample had used computers to access online health information.

    “Over 90% had used computers to access online health information.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Findingown data

    Over the 6-month intervention, 42 women interacted with Gabby at least once, producing 144 interactions and 2,676 total minutes.

    “During the 6-month intervention period, 42 women interacted with Gabby at least once. There were a total of 144 interactions totaling 2,676 minutes.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Over half of the baseline sample had home computer access, and all used a computer regularly or considered themselves expert.

    “More than half had computer access at home and all used a computer regularly or considered themselves expert.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Findingown data

    More than 90% of the baseline sample read at a high school level or higher.

    “Over 90% read at the high school level or better,”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Conversational agent systems can help overcome clinicians' time constraints and support delivery of recommended preventive care.

    “and that these systems can overcome clinician time constraints15 and assist in delivering recommended preventive care.16”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [15] Yarnell KS Pollak KI Østbye T Krause KM Michener JL Primary care: is there enough time for prevention? American Journal of Public Health 2003 93 635 641 12660210 PMC1447803

      Not checked in the free run.

    • cites [16] Shires DA Stange KC Divine G Ratliff S Vashi R Tai-Seale M Lafata JE Prioritization of evidence-based preventive health services during periodic health examinations American Journal of Preventive Medicine 2012 42 164 173 22261213 PMC3262983

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Premisecitation

    Health information technology offers opportunities to create innovative tools that help clinicians deliver PCC and that engage and empower women to improve their PCH.

    “Health information technology presents opportunities to develop innovative tools that assist clinicians in delivering PCC7, and to engage and empower women to improve their PCH.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [7] Henderson JT Weisman CS Grason H Are two doctors better than one? Women’s physician use and appropriate care Women’s Health Issues 2002 12 138 149 12015186

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductown data

    Randomization to the Gabby and control groups used sequentially numbered, opaque, sealed envelopes containing the group assignment.

    “Participants were randomized into the Gabby and control groups using sequentially numbered, opaque, sealed envelopes containing the random group assignment.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Study design and conductown data

    Complete baseline and six-month outcome data were available for 36 Gabby-group women and 41 control-group women, and response rates did not differ significantly between groups (p=0.34).

    “Complete baseline and six-month outcome data were obtained from 36 women in the Gabby group and 41 in the control group (Figure 3). There was no significant difference in response rates between groups (p=0.34).”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    The findings show that in a group of mostly college-educated, computer-literate African American women, Gabby can identify preconception risks and prompt actions that reduce the number of such risks.

    “The study findings demonstrate that among a group of mostly college-educated, computer literate African American women, the Gabby system can identify preconception risks and initiate actions to reduce the number of preconception risks.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationreasoning

    Currently Gabby is designed for desktop or laptop computers, and its uptake may have been limited because the target population prefers phones or tablets over traditional computers.

    “In its current state, the Gabby system is designed for use on a desktop or laptop computer; uptake of the system may have been limited due to the preference of our target population to use a telephone or tablet instead of traditional computer.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The 2013 National Action Plan for Promoting PCH in the U.S. set goals to improve knowledge, attitudes, and behaviors about PCC, eliminate disparities in adverse maternal, fetal, and infant outcomes, and ensure all U.S. women of childbearing age receive PCC services.

    “In 2013 the National Action Plan for Promoting PCH in the U.S. identified the goals of: improving the knowledge, attitudes and behaviors of men and women related to PCC; eliminating disparities in adverse maternal, fetal and infant outcomes; and assuring that all U.S. women of childbearing age receive PCC services.6”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [6] Floyd RL Kay A Johnson KA Owens JR Verbiest S Moore CA Boyle C A National action plan for promoting preconception health and health care in the United States (2012–2014) J Women’s Health 2013 2210 797 802 PMC4480361 23944970

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Interpretationnone given

    Achieving the Healthy People 2020 goal of eliminating disparities requires that adverse health outcome rates decline faster among African American women.

    “Progress towards the Healthy People 2020 goal to eliminate disparities requires that rates of adverse health outcomes fall more rapidly for AA women, which is why the Gabby system was designed for this group.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductown data

    The Gabby and control groups did not differ significantly in demographics, clinical characteristics, or information technology literacy and availability.

    “There were no significant differences in the demographics, clinical characteristics, or information technology literacy and availability between groups.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    Conversational agents are a logical way to deliver PCH information because they can reach many people while being highly acceptable through culturally appropriate content and information suitable for low health literacy.

    “Conversational agents are a logical option to deliver PCH information as they can reach a large audience while providing high user acceptability through culturally-appropriate content and information appropriate to those with low health literacy.11, 12”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [11] King A Bickmore T Campero M Employing “virtual advisors” in preventive care for underserved communities: results from the COMPASS study J Health Commun 2013 18 12 1449 64 23941610 PMC7187757

      Not checked in the free run.

    • cites [12] Bickmore TW Pfeifer LM Byron D Usability of conversational agents by patients with inadequate health literacy: evidence from two clinical trials J Health Commun 2010 15 suppl 2 197 210 20845204

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The CDC Select Expert Preconception Panel's PCC Clinical Workgroup in 2008 listed content areas that should be identified and addressed to improve maternal and infant outcomes, and it made implementation strategies a top priority.

    “In 2008, the CDC Select Expert Preconception Panel’s PCC Clinical Workgroup outlined those content areas important to identify and address to improve maternal and infant outcomes4 and identified implementation strategies as a top priority.5”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [4] Jack BW Atrash H Coonrod DV Moos MK O’Donnell J Johnson K The clinical content of preconception care: an overview and preparation of this supplement Am J Obstet Gynecol 2008 199 suppl S266 279 19081421

      Not checked in the free run.

    • cites [5] Atrash H Jack BW Johnson K Coonrod DV Moos M-K Stubblefield P Cefalo R Damus K Reddy U Where is the “W”oman in MCH? Am J Obstet Gynecol 2008 199 Suppl S259 265 19081420

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Our earlier qualitative research supports giving women autonomy and using a shared decision-making approach that is more empowering.

    “However, our previous qualitative work supports providing autonomy and supporting a shared decision making approach that is more empowering.20”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [20] Office of Minority Health 2013 9 24 Retrieved August 13, 2014, from http://minorityhealth.hhs.gov/omh/browse.aspx?lvl=3&lvlid=9

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Clinicians tend to be more verbally dominant and less patient-centered when interacting with African American patients.

    “There is also evidence that clinicians are more verbally-dominant and less patient-centered with AA patients,14”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [14] Johnson RL Roter D Powe NR Cooper LA Patient race/ethnicity and patient-physician communication during medical visits Am J Public Health 2004 12 94 12 2084 2090 15569958 PMC1448596

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductreasoning

    The data are self-reported, and participants could have misunderstood questions, selected wrong responses, or given intentional misinformation.

    “In addition, data are self-reported and participants potentially could have misunderstood a question, accidentally selected the wrong response, or provided intentional misinformation.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationcitation

    Gabby could potentially address issues of message fidelity and cultural sensitivity, scale, ease of delivery, and clinician time constraints, and it can be used in various settings to address barriers to translating PCC best practices into clinical care.

    “Gabby can potentially address problems regarding fidelity and cultural sensitivity of message, scale, ease of delivery, and clinician time constraints and can be used across a range of settings, addressing problems identified as barriers to translating PCC best practices to clinical care27.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [27] Jack B Atrash A Bickmore T Johnson K The future of preconception care Women’s HealthIssues 2008 18 suppl S19 S25 19059546

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductreasoning

    Possible biases include social desirability when reporting risk status to staff, recall bias in baseline and follow-up data, and self-selection bias in study participation.

    “There could also be social desirability bias when reporting risk status to staff, recall bias affecting baseline and follow-up data, and self-selection bias for study participation.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given

    A study limitation is that the follow-up period was relatively short, and behavior change takes time.

    “A limitation of this research is that the follow-up period was relatively short and behavior change takes time.”
    Quote in the paperNot a substantial claim
34 of 34

  • The paper relies on this without support.

    About half of pregnancies are unplanned.

    “In addition, about half of pregnancies are unplanned, making it important to promote preconception health (PCH) and deliver preconception care (PCC) to all women of reproductive age, regardless of pregnancy intention.1”

  • The paper relies on this without support.

    Enhancing a woman's health before pregnancy improves perinatal outcomes for women and infants.

    “Despite mounting scientific evidence that enhancing a woman’s health before pregnancy improves perinatal outcomes for women and their infants, many women enter pregnancy in poor health and at risk for preventable adverse pregnancy outcomes.”

  • The paper relies on this without support.

    Additional tools are needed for providers and the public to screen for and address preconception health risks.

    “Additional tools are needed for providers and the public to screen for and address preconception health (PCH) risks, particularly for African American (AA) women given the national persistent health outcome and healthcare disparities.”
3 of 3

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Risk-resolution denominators include participants outside the stated follow-up group

    Major

    The resolution comparison is described as being among 77 women with baseline and outcome data, but its denominators of 1,067 and 1,091 are identified elsewhere as all risks triggered by the groups among 91 women who completed the baseline risk assessment.

1 of 1

Cites

Flagged first, then by citations

1 of the 32 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Related

Authors
Jack, B., Bickmore, T., Hempstead, M., Yinusa-Nyahkoon, L., Sadikova, E., Mitchell, S., Gardiner, P., Adigun, F., Penti, B., Schulman, D., & Damus, K.
Affiliations
Boston University (US)
ORCID
Venue
The Journal of the American Board of Family Medicine
Publisher
American Board of Family Medicine (ABFM)
Published
2015-07-01
Volume
28
Issue
4
Pages
441-451
ISSN
  • 1557-2625 (ISSN-L)
  • 1558-7118
DOI
10.3122/jabfm.2015.04.140327
PMC
PMC4739811
OpenAlex
W2117614818
Semantic Scholar
7b2e72f1029dbf890abb59060a95fa71f77d9bc2
Cited by
99
References
32
Citations by year
2026: 4 · 2025: 7 · 2024: 6 · 2023: 18 · 2022: 16 · 2021: 7 · 2020: 20 · 2019: 8 · 2018: 3 · 2017: 3 · 2016: 5 · 2015: 2
FWCI
7.90
Type
journal article
Language
en
Open access
Locations
  • The Journal of the American Board of Family Medicine (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
  • The Journal of the American Medical Association (JAMA) Network (American Medical Association) (submittedVersion)
Funders
  • U.S. Department of Health and Human Services
  • North Carolina Department of Health and Human Services
  • Charles R. Drew University of Medicine and Science
  • W.K. Kellogg Foundation (P3024018)
  • Health Resources and Services Administration
  • Agency for Healthcare Research and Quality
  • U.S. Public Health Service (HHSA290200600012I, R40 MC21510)
  • California State University, Northridge
  • National Institute on Minority Health and Health Disparities (R01MD006213)
Topics
  • Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Reproductive Health and Contraception
Keywords
preconception health, African American women, chatbots, health disparities, risk screening, digital health interventions, pregnancy planning
MeSH terms
Adolescent, Adult, Black or African American, Female, Follow-Up Studies, Health Promotion, Humans, Medical Informatics Applications, Outcome and Process Assessment, Health Care, Patient Participation, Professional-Patient Relations, United States, Preconception Care, Risk Assessment, Internet, Risk Reduction Behavior, Health Status Disparities, Young Adult, Motivational Interviewing

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-07.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-07.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review