Evaluation of a novel electronic genetic screening and clinical decision support tool in prenatal clinical settings

Genetically guided precision medicine clinical decision support tools: a systematic review

OBJECTIVES

Patient care using genetics presents complex challenges. Clinical decision support (CDS) tools are a potential solution because they provide patient-specific risk assessments and/or recommendations at the point of care. This systematic review evaluated the literature on CDS systems which have been implemented to support genetically guided precision medicine (GPM).

MATERIALS AND METHODS

A comprehensive search was conducted in MEDLINE and Embase, encompassing January 1, 2011-March 14, 2023. The review included primary English peer-reviewed research articles studying humans, focused on the use of computers to guide clinical decision-making and delivering genetically guided, patient-specific assessments, and/or recommendations to healthcare providers and/or patients.

RESULTS

The search yielded 3832 unique articles. After screening, 41 articles were identified that met the inclusion criteria. Alerts and reminders were the most common form of CDS used. About 27 systems were integrated with the electronic health record; 2 of those used standards-based approaches for genomic data transfer. Three studies used a framework to analyze the implementation strategy.

DISCUSSION

Findings include limited use of standards-based approaches for genomic data transfer, system evaluations that do not employ formal frameworks, and inconsistencies in the methodologies used to assess genetic CDS systems and their impact on patient outcomes.

CONCLUSION

We recommend that future research on CDS system implementation for genetically GPM should focus on implementing more CDS systems, utilization of standards-based approaches, user-centered design, exploration of alternative forms of CDS interventions, and use of formal frameworks to systematically evaluate genetic CDS systems and their effects on patient care.

Could a decision support tool be the key to supporting choice for women regarding place of birth?

OBJECTIVE

To assess the effectiveness of using an innovative decision aid, MyBirthplace, to facilitate shared decision-making regarding place of birth.

DESIGN

A quasi-experimental study comparing pre-test and post-test responses from participants who had access to the intervention.

SETTING

A large urban hospital in the south of England.

PARTICIPANTS

All pregnant women who accessed maternity care between April and December 2016.

INTERVENTION

A decision aid (MyBirthplace) designed to provide information and support regarding place of birth. The digital tool (available in both an app and web-based version) was used to facilitate discuss between the women and her midwife at the booking visit.

MEASUREMENTS

Women's stage of decision making as measured by the Stage of Decision Making Scale. A questionnaire was administered before and after using MyBirthplace at booking, and again at 28 weeks gestation.

FINDINGS

Nearly half the women (42.1%) had already decided where they wanted to give birth before the booking appointment, but a third (34.3%) had not yet begun to think about their choices. The introduction of the decision aid during the booking visit was associated with a significant increase in the stage of decision making suggesting that women had greater certainty in their decision P< 0.0001 [SD 1.077]. Women who accessed MyBirthplace had lower decisional conflict after the booking appointment than those women that did not access the decision aid (35.5% compared with 22.0%) but this difference was not statistically significant.

KEY CONCLUSIONS

Decision aids, as a standard part of practice, have the potential to ensure women are informed of their options and encourage shared decision making about place of birth. Women were more confident with their decision following the booking appointment and by 28 weeks; however, further research is needed to identify the role that the decision aid played in building this confidence.

IMPLICATIONS FOR PRACTICE

The introduction of a decision aid, Mybirthplace, within the hospital impacted early discussions between the woman and the midwife and appeared to benefit women's decision making regarding place of birth. Further studies of midwives' use of innovative technologies and their implementation are required.

Towards an explainable clinical decision support system for large-for-gestational-age births

A myriad of maternal and neonatal complications can result from delivery of a large-for-gestational-age (LGA) infant. LGA birth rates have increased in many countries since the late 20th century, partially due to a rise in maternal body mass index, which is associated with LGA risk. The objective of the current study was to develop LGA prediction models for women with overweight and obesity for the purpose of clinical decision support in a clinical setting. Maternal characteristics, serum biomarkers and fetal anatomy scan measurements for 465 pregnant women with overweight and obesity before and at approximately 21 weeks gestation were obtained from the PEARS (Pregnancy Exercise and Nutrition with smart phone application support) study data. Random forest, support vector machine, adaptive boosting and extreme gradient boosting algorithms were applied with synthetic minority over-sampling technique to develop probabilistic prediction models. Two models were developed for use in different settings: a clinical setting for white women (AUC-ROC of 0.75); and a clinical setting for women of all ethnicity and regions (AUC-ROC of 0.57). Maternal age, mid upper arm circumference, white cell count at the first antenatal visit, fetal biometry and gestational age at fetal anatomy scan were found to be important predictors of LGA. Pobal HP deprivation index and fetal biometry centiles, which are population-specific, are also important. Moreover, we explained our models with Local Interpretable Model-agnostic Explanations (LIME) to improve explainability, which was proven effective by case studies. Our explainable models can effectively predict the probability of an LGA birth for women with overweight and obesity, and are anticipated to be useful to support clinical decision-making and for the development of early pregnancy intervention strategies to reduce pregnancy complications related to LGA.

Identification and Impact Analysis of Family History of Psychiatric Disorder in Mood Disorder Patients With Pretrained Language Model

Mood disorders are ubiquitous mental disorders with familial aggregation. Extracting family history of psychiatric disorders from large electronic hospitalization records is helpful for further study of onset characteristics among patients with a mood disorder. This study uses an observational clinical data set of in-patients of Nanjing Brain Hospital, affiliated with Nanjing Medical University, from the past 10 years. This paper proposes a pretrained language model: Bidirectional Encoder Representations from Transformers (BERT)-Convolutional Neural Network (CNN). We first project the electronic hospitalization records into a low-dimensional dense matrix via the pretrained Chinese BERT model, then feed the dense matrix into the stacked CNN layer to capture high-level features of texts; finally, we use the fully connected layer to extract family history based on high-level features. The accuracy of our BERT-CNN model was 97.12 ± 0.37% in the real-world data set from Nanjing Brain Hospital. We further studied the correlation between mood disorders and family history of psychiatric disorder.

Physicians' strategies for using family history data: having the data is not the same as using the data

Objective

To identify needs in a clinical decision support tool development by exploring how primary care providers currently collect and use family health history (FHH).

Design

Survey questionnaires and semi-structured interviews were administered to a mix of primary and specialty care clinicians within the University of Utah Health system (40 surveys, 12 interviews).

Results

Three key themes emerged regarding providers' collection and use of FHH: (1) Strategies for collecting FHH vary by level of effort; (2) Documentation practices extend beyond the electronic health record's dedicated FHH module; and (3) Providers desire feedback from genetic services consultation and are uncertain how to refer patients to genetic services.

Conclusion

Study findings highlight the varying degrees of engagement that providers have with collecting FHH. Improving the integration of FHH into workflow, and providing decision support, as well as links and tools to help providers better utilize genetic counseling may improve patient care.

Primary care physician experiences utilizing a family health history tool with electronic health record-integrated clinical decision support: an implementation process assessment

Family health history (FHH) screening plays a key role in disease risk identification and tailored disease prevention strategies. Primary care physicians (PCPs) are in a frontline position to provide personalized medicine recommendations identified through FHH screening; however, adoption of FHH screening tools has been slow and inconsistent in practice. Information is also lacking on PCP facilitators and barriers of utilizing family history tools with clinical decision support (CDS) embedded in the electronic health record (EHR). This study reports on PCPs' initial experiences with the Genetic and Wellness Assessment (GWA), a patient-administered FHH screening tool utilizing the EHR and CDS. Semi-structured interviews were conducted with 24 PCPs who use the GWA in a network of community-based practices. Four main themes regarding GWA implementation emerged: benefits to clinical care, challenges in practice, CDS-specific issues, and physician-recommended improvements. Sub-themes included value in improving patient access to genetic services, inadequate time to discuss GWA recommendations, lack of patient follow-through with recommendations, and alert fatigue. While PCPs valued the GWA's clinical utility, a number of challenges were identified in the administration and use of the GWA in practice. Based on participants' recommendations, iterative changes have been made to the GWA and workflow to increase efficiency, upgrade the CDS process, and provide additional education to PCPs and patients. Future studies are needed to assess a diverse sample of physicians' and patients' perspectives on the utility of FHH screening utilizing EHR-based genomics recommendations.

What maximizes the effectiveness and implementation of technology-based interventions to support healthcare professional practice? A systematic literature review

Background

Technological support may be crucial in optimizing healthcare professional practice and improving patient outcomes. A focus on electronic health records has left other technological supports relatively neglected. Additionally, there has been no comparison between different types of technology-based interventions, and the importance of delivery setting on the implementation of technology-based interventions to change professional practice. Consequently, there is a need to synthesise and examine intervention characteristics using a methodology suited to identifying important features of effective interventions, and the barriers and facilitators to implementation. Three aims were addressed: to identify interventions with a technological component that are successful at changing professional practice, to determine if and how such interventions are theory-based, and to examine barriers and facilitators to successful implementation.

Methods

A literature review informed by realist review methods was conducted involving a systematic search of studies reporting either: (1) behavior change interventions that included technology to support professional practice change; or (2) barriers and facilitators to implementation of technological interventions. Extracted data was quantitative and qualitative, and included setting, target professionals, and use of Behaviour Change Techniques (BCTs). The primary outcome was a change in professional practice. A thematic analysis was conducted on studies reporting barriers and facilitators of implementation.

Results

Sixty-nine studies met the inclusion criteria; 48 (27 randomized controlled trials) reported behavior change interventions and 21 reported practicalities of implementation. The most successful technological intervention was decision support providing healthcare professionals with knowledge and/or person-specific information to assist with patient management. Successful technologies were more likely to operationalise BCTs, particularly “instruction on how to perform the behavior”. Facilitators of implementation included aligning studies with organisational initiatives, ensuring senior peer endorsement, and integration into clinical workload. Barriers included organisational challenges, and design, content and technical issues of technology-based interventions.

Conclusions

Technological interventions must focus on providing decision support for clinical practice using recognized behavior change techniques. Interventions must consider organizational context, clinical workload, and have clearly defined benefits for improving practice and patient outcomes.

Electronic supplementary material

The online version of this article (10.1186/s12911-018-0661-3) contains supplementary material, which is available to authorized users.

What education, background, and credentials are required to provide genetic counseling?

Technological advances in genetics have resulted in an increase in the number and complexity of screening and diagnostic tests in the prenatal clinical arena. It is critical that patients are provided with appropriate counseling to enable them to make educated decisions. During this workshop session participants discussed the education, background and credentials required to provide counseling regarding prenatal genetic testing options. The participants agreed that prenatal care providers may have limited time and training to adequately address prenatal genetic testing. Telemedicine and online education may help to address this challenge. Workshop participants agreed that educational and certifying organizations should work together to develop standards for the certification and maintenance of certification processes.

An approach to improve the care of mid-life women through the implementation of a Women's Health Assessment Tool/Clinical Decision Support toolkit

The objectives of this study are to describe the implementation process of the Women's Health Assessment Tool/Clinical Decision Support toolkit and summarize patients' and clinicians' perceptions of the toolkit. The Women's Health Assessment Tool/Clinical Decision Support toolkit was piloted at three clinical sites over a 4-month period in Washington State to evaluate health outcomes among mid-life women. The implementation involved a multistep process and engagement of multiple stakeholders over 18 months. Two-thirds of patients (n = 76/110) and clinicians (n = 8/12) participating in pilot completed feedback surveys; five clinicians participated in qualitative interviews. Most patients felt more prepared for their annual visit (69.7%) and that quality of care improved (68.4%) while clinicians reported streamlined patient visits and improved communication with patients. The Women's Health Assessment Tool/Clinical Decision Support toolkit offers a unique approach to introduce and address some of the key health issues that affect mid-life women.

Pre- and post-test genetic counseling for chromosomal and Mendelian disorders

Genetic carrier screening, prenatal screening for aneuploidy, and prenatal diagnostic testing have expanded dramatically over the past 2 decades. Driven in part by powerful market forces, new complex testing modalities have become available after limited clinical research. The responsibility for offering these tests lies primarily on the obstetrical care provider and has become more burdensome as the number of testing options expands. Genetic testing in pregnancy is optional, and decisions about undergoing tests, as well as follow-up testing, should be informed and based on individual patients' values and needs. Careful pre- and post-test counseling is central to supporting informed decision-making. This article explores three areas of technical expansion in genetic testing: expanded carrier screening, non-invasive prenatal screening for fetal aneuploidies using cell-free DNA, and diagnostic testing using fetal chromosomal microarray testing, and provides insights aimed at enabling the obstetrical practitioner to better support patients considering these tests.

Comparing genetic counselor's and patient's perceptions of needs in prenatal chromosomal microarray testing

OBJECTIVE

Chromosome microarray analysis is poised to take a significant place in the prenatal setting given its increased yield over standard karyotyping, but concerns regarding ethical and counseling challenges remain, especially associated with the risk of uncertain and incidental findings. Guidelines recommend patients receiving prenatal screening to undergo genetic counseling prior to testing, but little is known about women's specific pre-testing and post-testing informational needs, as well as their preference for return of various types of results.

METHODS

The present study surveys 199 prenatal genetic counselors who have counseled patients undergoing chromosome microarray analysis testing and 152 women who have undergone testing on the importance of understanding pre-test information, return of various types of results, and resources made available following an abnormal finding.

RESULTS

Counselors and patients agree on many aspects, although findings indicate patients consider all available information very important, while genetic counselors give more varying ratings.

CONCLUSION

Counseling sessions would benefit from information personalized to a patient's particular needs and a shared decision-making model, to reduce informational overload and avoid unnecessary anxiety. Additionally, policies regarding the return of various types of results are needed. © 2015 John Wiley & Sons, Ltd.

Primary-care providers' perceived barriers to integration of genetics services: a systematic review of the literature

PURPOSE

We aimed to systematically review the literature to identify primary-care providers' perceived barriers against provision of genetics services.

METHODS

We systematically searched PubMed and ERIC using key and Boolean term combinations for articles published from 2001 to 2012 that met inclusion/exclusion criteria. Specific barriers were identified and aggregated into categories based on topic similarity. These categories were then grouped into themes.

RESULTS

Of the 4,174 citations identified by the search, 38 publications met inclusion criteria. There were 311 unique barriers that were classified into 38 categories across 4 themes: knowledge and skills; ethical, legal, and social implications; health-care systems; and scientific evidence. Barriers most frequently mentioned by primary-care providers included a lack of knowledge about genetics and genetic risk assessment, concern for patient anxiety, a lack of access to genetics, and a lack of time.

CONCLUSION

Although studies reported that primary-care providers perceive genetics as being important, barriers to the integration of genetics medicine into routine patient care were identified. The promotion of practical guidelines, point-of-care risk assessment tools, tailored educational tools, and other systems-level strategies will assist primary-care providers in providing genetics services for their patients.

Formative evaluation of clinician experience with integrating family history-based clinical decision support into clinical practice

Family health history is a leading predictor of disease risk. Nonetheless, it is underutilized to guide care and, therefore, is ripe for health information technology intervention. To fill the family health history practice gap, Cleveland Clinic has developed a family health history collection and clinical decision support tool, MyFamily. This report describes the impact and process of implementing MyFamily into primary care, cancer survivorship and cancer genetics clinics. Ten providers participated in semi-structured interviews that were analyzed to identify opportunities for process improvement. Participants universally noted positive effects on patient care, including increases in quality, personalization of care and patient engagement. The impact on clinical workflow varied by practice setting, with differences observed in the ease of integration and the use of specific report elements. Tension between the length of the report and desired detail was appreciated. Barriers and facilitators to the process of implementation were noted, dominated by the theme of increased integration with the electronic medical record. These results fed real-time improvement cycles to reinforce clinician use. This model will be applied in future institutional efforts to integrate clinical genomic applications into practice and may be useful for other institutions considering the implementation of tools for personalizing medical management.

Implementation of an electronic genomic and family health history tool in primary prenatal care

"The Pregnancy and Health Profile," (PHP) is a free genetic risk assessment software tool for primary prenatal providers that collects patient-entered family (FHH), personal, and obstetrical health history, performs risk assessment, and presents the provider with clinical decision support during the prenatal encounter. The tool is freely available for download at www.hughesriskapps.net. We evaluated the implementation of PHP in four geographically diverse clinical sites. Retrospective chart reviews were conducted for patients seen prior to the study period and for patients who used the PHP to collect data on documentation of FHH, discussion of cystic fibrosis (CF) and hemoglobinopathy (HB) carrier screening, and CF and HB interventions (tests, referrals). Five hundred pre-implementation phase and 618 implementation phase charts were reviewed. Documentation of a 3-generation FHH or pedigree improved at three sites; patient race/ethnicity at three sites, father of the baby (FOB) race/ethnicity at all sites, and ancestry for the patient and FOB at three sites (P < 0.001-0001). CF counseling improved for implementation phase patients at one site (8% vs. 48%, P < 0.0001) and CF screening/referrals at two (2% vs. 14%, P < 0.0001; 6% vs. 14%; P = 0.05). Counseling and intervention rates did not increase for HB. This preliminary study suggests that the PHP can improve documentation of FHH, race, and ancestry, as well as the compliance with current CF counseling and intervention guidelines in some prenatal clinics. Future evaluation of the PHP should include testing in a larger number of clinical environments, assessment of additional performance measures, and evaluation of the system's overall clinical utility.