Pediatric decision support using adapted Arden Syntax

A comprehensive overview of barriers and strategies for AI implementation in healthcare: Mixed-method design

Implementation of artificial intelligence systems for healthcare is challenging. Understanding the barriers and implementation strategies can impact their adoption and allows for better anticipation and planning. This study's objective was to create a detailed inventory of barriers to and strategies for AI implementation in healthcare to support advancements in methods and implementation processes in healthcare. A sequential explanatory mixed method design was used. Firstly, scoping reviews and systematic literature reviews were identified using PubMed. Selected studies included empirical cases of AI implementation and use in clinical practice. As the reviews were deemed insufficient to fulfil the aim of the study, data collection shifted to the primary studies included in those reviews. The primary studies were screened by title and abstract, and thereafter read in full text. Then, data on barriers to and strategies for AI implementation were extracted from the included articles, thematically coded by inductive analysis, and summarized. Subsequently, a direct qualitative content analysis of 69 interviews with healthcare leaders and healthcare professionals confirmed and added results from the literature review. Thirty-eight empirical cases from the six identified scoping and literature reviews met the inclusion and exclusion criteria. Barriers to and strategies for AI implementation were grouped under three phases of implementation (planning, implementing, and sustaining the use) and were categorized into eleven concepts; Leadership, Buy-in, Change management, Engagement, Workflow, Finance and human resources, Legal, Training, Data, Evaluation and monitoring, Maintenance. Ethics emerged as a twelfth concept through qualitative analysis of the interviews. This study illustrates the inherent challenges and useful strategies in implementing AI in healthcare practice. Future research should explore various aspects of leadership, collaboration and contracts among key stakeholders, legal strategies surrounding clinicians' liability, solutions to ethical dilemmas, infrastructure for efficient integration of AI in workflows, and define decision points in the implementation process.

Barriers and Enablers for Implementation of an Artificial Intelligence-Based Decision Support Tool to Reduce the Risk of Readmission of Patients With Heart Failure: Stakeholder Interviews

BACKGROUND

Artificial intelligence (AI) applications in health care are expected to provide value for health care organizations, professionals, and patients. However, the implementation of such systems should be carefully planned and organized in order to ensure quality, safety, and acceptance. The gathered view of different stakeholders is a great source of information to understand the barriers and enablers for implementation in a specific context.

OBJECTIVE

This study aimed to understand the context and stakeholder perspectives related to the future implementation of a clinical decision support system for predicting readmissions of patients with heart failure. The study was part of a larger project involving model development, interface design, and implementation planning of the system.

METHODS

Interviews were held with 12 stakeholders from the regional and municipal health care organizations to gather their views on the potential effects implementation of such a decision support system could have as well as barriers and enablers for implementation. Data were analyzed based on the categories defined in the nonadoption, abandonment, scale-up, spread, sustainability (NASSS) framework.

RESULTS

Stakeholders had in general a positive attitude and curiosity toward AI-based decision support systems, and mentioned several barriers and enablers based on the experiences of previous implementations of information technology systems. Central aspects to consider for the proposed clinical decision support system were design aspects, access to information throughout the care process, and integration into the clinical workflow. The implementation of such a system could lead to a number of effects related to both clinical outcomes as well as resource allocation, which are all important to address in the planning of implementation. Stakeholders saw, however, value in several aspects of implementing such system, emphasizing the increased quality of life for those patients who can avoid being hospitalized.

CONCLUSIONS

Several ideas were put forward on how the proposed AI system would potentially affect and provide value for patients, professionals, and the organization, and implementation aspects were important parts of that. A successful system can help clinicians to prioritize the need for different types of treatments but also be used for planning purposes within the hospital. However, the system needs not only technological and clinical precision but also a carefully planned implementation process. Such a process should take into consideration the aspects related to all the categories in the NASSS framework. This study further highlighted the importance to study stakeholder needs early in the process of development, design, and implementation of decision support systems, as the data revealed new information on the potential use of the system and the placement of the application in the care process.

Adolescent suicide assessment and management in primary care

Background

To understand how suicide management occurs within the primary care setting in terms of follow-up assessments and referral practices.

Methods

At an initial primary care visit, adolescents (aged 12–20 years old) completed electronic screening. Data were focused on youth who endorsed a suicidal risk item while completing screening at two Midwestern primary care clinics. Data were collected through retrospective chart reviews to analyze actions taken by the primary care physician at the youth’s initial visit and follow-up visit within the next 12 months.

Results

At initial visits 200 adolescents endorsed a suicidal risk item and 39 (19.5%) were considered to be concerning by their primary care physician. The average age was 14.7 years old (SD ± 2.0). Seventy-two percent (n = 144) were female, and 65% (n = 129) identified as Black. At initial visits, significant differences between suicidal concern groups were found in reporting active suicidal ideation, past suicide attempts, those who were referred to behavioral health counseling, and those who had a diagnosis of depression. Interestingly, only 13% (n = 25) of all patients who endorsed the suicide item were asked whether or not there were weapons in their home and primary care providers asked only 7% (n = 13) of all patients whether they had a safety plan.

Conclusions

There was inconsistent follow-up for adolescents with a history of suicide concerns. At this time, national guidelines do not exist regarding primary care follow-up of youth with suicide concerns. Guidelines are a necessary precursor for practice improvement.

Trial Registration

Clinical Trials Registry: NCT02244138. Registration date, September 1, 2014.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12887-022-03454-4.

Artificial Intelligence Applications in Health Care Practice: A Scoping Review (Preprint)

Background

Artificial intelligence (AI) is often heralded as a potential disruptor that will transform the practice of medicine. The amount of data collected and available in health care, coupled with advances in computational power, has contributed to advances in AI and an exponential growth of publications. However, the development of AI applications does not guarantee their adoption into routine practice. There is a risk that despite the resources invested, benefits for patients, staff, and society will not be realized if AI implementation is not better understood.

Objective

The aim of this study was to explore how the implementation of AI in health care practice has been described and researched in the literature by answering 3 questions: What are the characteristics of research on implementation of AI in practice? What types and applications of AI systems are described? What characteristics of the implementation process for AI systems are discernible?

Methods

A scoping review was conducted of MEDLINE (PubMed), Scopus, Web of Science, CINAHL, and PsycINFO databases to identify empirical studies of AI implementation in health care since 2011, in addition to snowball sampling of selected reference lists. Using Rayyan software, we screened titles and abstracts and selected full-text articles. Data from the included articles were charted and summarized.

Results

Of the 9218 records retrieved, 45 (0.49%) articles were included. The articles cover diverse clinical settings and disciplines; most (32/45, 71%) were published recently, were from high-income countries (33/45, 73%), and were intended for care providers (25/45, 56%). AI systems are predominantly intended for clinical care, particularly clinical care pertaining to patient-provider encounters. More than half (24/45, 53%) possess no action autonomy but rather support human decision-making. The focus of most research was on establishing the effectiveness of interventions (16/45, 35%) or related to technical and computational aspects of AI systems (11/45, 24%). Focus on the specifics of implementation processes does not yet seem to be a priority in research, and the use of frameworks to guide implementation is rare.

Conclusions

Our current empirical knowledge derives from implementations of AI systems with low action autonomy and approaches common to implementations of other types of information systems. To develop a specific and empirically based implementation framework, further research is needed on the more disruptive types of AI systems being implemented in routine care and on aspects unique to AI implementation in health care, such as building trust, addressing transparency issues, developing explainable and interpretable solutions, and addressing ethical concerns around privacy and data protection.

The patient record and the rise of the pediatric EHR

Medical documentation arose as individual case reports written for teaching purposes. Documentation for patient care later occurred in physicians' personal daybooks and only evolved into the individual patient record in the early 20th century. Dr. Lawrence Weed improved the utility of the patient record by introducing a problem-oriented/subject-object-assessment-plan structure and he and other innovators transformed the patient record into electronic form. Pediatricians built on these innovations to create a child health electronic health record (EHR) for primary care. An American Academy of Pediatrics task force formally specified the child-specific needs of the EHR, but much work remains to integrate the EHR into the pediatric primary care of the future.

Feasibility of computerized clinical decision support for pediatric to adult care transitions for patients with special healthcare needs

The objective of this study was to determine the feasibility of a computerized clinical decision support (cCDS) tool to facilitate referral to adult healthcare services for children with special healthcare needs. A transition-specific cCDS was implemented as part of standard care in a general pediatrics clinic at a tertiary care academic medical center. The cCDS alerts providers to patients 17-26 years old with 1 or more of 15 diagnoses that may be candidates for referral to an internal medicine adult transition clinic (ATC). Provider responses to the cCDS and referral outcomes (e.g. scheduled and completed visits) were retrospectively analyzed using descriptive statistics. One hundred and fifty-two patients were seen during the 20-month observation period. Providers referred 87 patients to the ATC using cCDS and 77% of patients ≥18 years old scheduled a visit in the ATC. Transition-specific cCDS tools are feasible options to facilitate adult care transitions for children with special healthcare needs.

Screening for Problematic Sleep in a Diverse Sample of Infants

OBJECTIVE

To examine screening strategies for identifying problematic sleep in a diverse sample of infants.

METHODS

Parents of infants (5-19 months; N = 3,271) presenting for a primary care visit responded to five screening items and the Infant Sleep Questionnaire (ISQ), a validated measure of problematic infant sleep. If parents responded affirmatively to any screening item, primary care providers received a prompt to evaluate. For each of the screening questions, we examined differences in item endorsement and criterion related validity with the ISQ. Using conceptual composites of night waking and sleep difficulty, prevalence, criterion-related validity, and concurrent demographic correlates were analyzed.

RESULTS

Infants were primarily of Black race (50.1%) or Hispanic ethnicity (31.7%), with the majority (63.3%) living in economically distressed communities. Rates of problematic sleep ranged from 7.4%, for a single item assessing parental perception of an infant having a sleep problem, to 74.0%, for a single item assessing night wakings requiring adult intervention. Items assessing sleep difficulty had high (95.0-97.8%) agreement with the ISQ in identifying infants without problematic sleep, but low agreement (24.9-34.0%) in identifying those with problematic sleep. The opposite was true for items assessing night waking, which identified 91.0-94.6% of those with sleep problems but only 31.8-46.9% of those without.

CONCLUSIONS

Screening strategies for identifying problematic infant sleep yielded highly variable prevalence rates and associated factors, depending on whether the strategy emphasized parent-perceived sleep difficulty or night wakings. The strategy that is most appropriate will depend on the system's goals.

How can healthcare professionals provide guidance and support to parents of adolescents? Results from a primary care-based study

BACKGROUND

This study explored the rewards and difficulties of raising an adolescent and investigated parents' level of interest in receiving guidance from healthcare providers on parenting and adolescent health topics. Additionally, this study investigated whether parents were interested in parenting programs in primary care and explored methods in which parents want to receive guidance.

METHODS

Parents of adolescents (ages 12-18) who attended an outpatient pediatric clinic with their adolescent were contacted by telephone and completed a short telephone survey. Parents were asked open-ended questions regarding the rewards and difficulties of parenting and rated how important it was to receive guidance from a healthcare provider on certain parenting and health topics. Additionally, parents reported their level of interest in a parenting program in primary care and rated how they would like to receive guidance.

RESULTS

Our final sample included 104 parents, 87% of whom were interested in a parenting program within primary care. A variety of parenting rewards and difficulties were associated with raising an adolescent. From the list of parenting topics, communication was rated very important to receive guidance on (65%), followed by conflict management (50%). Of health topics, parents were primarily interested in receiving guidance on sex (77%), mental health (75%), and alcohol and drugs (74%). Parents in the study wanted to receive guidance from a pediatrician or through written literature.

CONCLUSIONS

The current study finds that parents identify several rewarding and difficult aspects associated with raising an adolescent and are open to receiving guidance on a range of parenting topics in a variety of formats through primary care settings. Incorporating such education into healthcare visits could improve parents' knowledge. Healthcare providers are encouraged to consider how best to provide parenting support during this important developmental time period.

Improving Patient-Centered Communication about Sudden Unexpected Death in Epilepsy through Computerized Clinical Decision Support

BACKGROUND

Sudden unexpected death in epilepsy (SUDEP) is a rare but fatal risk that patients, parents, and professional societies clearly recommend discussing with patients and families. However, this conversation does not routinely happen.

OBJECTIVES

This pilot study aimed to demonstrate whether computerized decision support could increase patient communication about SUDEP.

METHODS

A prospective before-and-after study of the effect of computerized decision support on delivery of SUDEP counseling. The intervention was a screening, alerting, education, and follow-up SUDEP module for an existing computerized decision support system (the Child Health Improvement through Computer Automation [CHICA]) in five urban pediatric primary care clinics. Families of children with epilepsy were contacted by telephone before and after implementation to assess if the clinician discussed SUDEP at their respective encounters.

RESULTS

The CHICA-SUDEP module screened 7,154 children age 0 to 21 years for seizures over 7 months; 108 (1.5%) reported epilepsy. We interviewed 101 families after primary care encounters (75 before and 26 after implementation) over 9 months. After starting CHICA-SUDEP, the number of caregivers who reported discussing SUDEP with their child's clinician more than doubled from 21% (16/75) to 46% (12/26; p = 0.03), and when the parent recalled who brought up the topic, 80% of the time it was the clinician. The differences between timing and sampling methodologies of before and after intervention cohorts could have led to potential sampling and recall bias.

CONCLUSION

Clinician-family discussions about SUDEP significantly increased in pediatric primary care clinics after introducing a systematic, computerized screening and decision support module. These tools demonstrate potential for increasing patient-centered education about SUDEP, as well as incorporating other guideline-recommended algorithms into primary and subspecialty cares.

CLINICAL TRIAL REGISTRATION

clinicaltrials.gov, NCT03502759.

Proteomics and Metabolomics Approaches towards a Functional Insight onto AUTISM Spectrum Disorders: Phenotype Stratification and Biomarker Discovery

Autism spectrum disorders (ASDs) are neurodevelopmental disorders characterized by behavioral alterations and currently affect about 1% of children. Significant genetic factors and mechanisms underline the causation of ASD. Indeed, many affected individuals are diagnosed with chromosomal abnormalities, submicroscopic deletions or duplications, single-gene disorders or variants. However, a range of metabolic abnormalities has been highlighted in many patients, by identifying biofluid metabolome and proteome profiles potentially usable as ASD biomarkers. Indeed, next-generation sequencing and other omics platforms, including proteomics and metabolomics, have uncovered early age disease biomarkers which may lead to novel diagnostic tools and treatment targets that may vary from patient to patient depending on the specific genomic and other omics findings. The progressive identification of new proteins and metabolites acting as biomarker candidates, combined with patient genetic and clinical data and environmental factors, including microbiota, would bring us towards advanced clinical decision support systems (CDSSs) assisted by machine learning models for advanced ASD-personalized medicine. Herein, we will discuss novel computational solutions to evaluate new proteome and metabolome ASD biomarker candidates, in terms of their recurrence in the reviewed literature and laboratory medicine feasibility. Moreover, the way to exploit CDSS, performed by artificial intelligence, is presented as an effective tool to integrate omics data to electronic health/medical records (EHR/EMR), hopefully acting as added value in the near future for the clinical management of ASD.

Clinician Perceptions of a Computerized Decision Support System for Pediatric Type 2 Diabetes Screening

OBJECTIVE

With the increasing prevalence of type 2 diabetes (T2D) in youth, primary care providers must identify patients at high risk and implement evidence-based screening promptly. Clinical decision support systems (CDSSs) provide clinicians with personalized reminders according to best evidence. One example is the Child Health Improvement through Computer Automation (CHICA) system, which, as we have previously shown, significantly improves screening for T2D. Given that the long-term success of any CDSS depends on its acceptability and its users' perceptions, we examined what clinicians think of the CHICA diabetes module.

METHODS

CHICA users completed an annual quality improvement and satisfaction questionnaire. Between May and August of 2015 and 2016, the survey included two statements related to the T2D-module: (1) "CHICA improves my ability to identify patients who might benefit from screening for T2D" and (2) "CHICA makes it easier to get the lab tests necessary to identify patients who have diabetes or prediabetes." Answers were scored using a 5-point Likert scale and were later converted to a 2-point scale: agree and disagree. The Pearson chi-square test was used to assess the relationship between responses and the respondents. Answers per cohort were compared using the Mann-Whitney U-test.

RESULTS

The majority of respondents (N = 60) agreed that CHICA improved their ability to identify patients who might benefit from screening but disagreed as to whether it helped them get the necessary laboratories. Scores were comparable across both years.

CONCLUSION

CHICA was endorsed as being effective for T2D screening. Research is needed to improve satisfaction for getting laboratories with CHICA.

The Natural Course of Adolescent Depression Treatment in the Primary Care Setting

INTRODUCTION

Little is known about how adolescents receive depression follow-up in primary care. The purpose of this study was to describe the rates of symptom assessment and depression treatment over time in a group of adolescents screening positive for moderate or severe depression in the primary care setting.

METHODS

Retrospective chart reviews were conducted to gather information related to symptom reassessments, antidepressant prescriptions, psychotherapy referrals, and treatment discontinuation. Descriptive statistics were calculated, and a qualitative content analysis was conducted to determine the reasons for treatment discontinuation.

RESULTS

Eighty records were reviewed (mean age = 15.3, 73% female, 59% Black). Treatment was initiated for 83% (n = 66) of patients, and 45% (n = 30) of patients discontinued treatment during the review period for a variety of reasons.

DISCUSSION

To improve adolescents' adherence to depression treatment, providers should address factors that contribute to treatment discontinuation and use tools to manage depression follow-up care.

Effect of a Computer-Based Decision Support Intervention on Autism Spectrum Disorder Screening in Pediatric Primary Care Clinics: A Cluster Randomized Clinical Trial

IMPORTANCE

Universal early screening for autism spectrum disorder (ASD) is recommended but not routinely performed.

OBJECTIVE

To determine whether computer-automated screening and clinical decision support can improve ASD screening rates in pediatric primary care practices.

DESIGN, SETTING, AND PARTICIPANTS

This cluster randomized clinical trial, conducted between November 16, 2010, and November 21, 2012, compared ASD screening rates among a random sample of 274 children aged 18 to 24 months in urban pediatric clinics of an inner-city county hospital system with or without an ASD screening module built into an existing decision support software system. Statistical analyses were conducted from February 6, 2017, to June 1, 2018.

INTERVENTIONS

Four clinics were matched in pairs based on patient volume and race/ethnicity, then randomized within pairs. Decision support with the Child Health Improvement Through Computer Automation system (CHICA) was integrated with workflow and with the electronic health record in intervention clinics.

MAIN OUTCOMES AND MEASURES

The main outcome was screening rates among children aged 18 to 24 months. Because the intervention was discontinued among children aged 18 months at the request of the participating clinics, only results for those aged 24 months were collected and analyzed. Rates of positive screening results, clinicians' response rates to screening results in the computer system, and new cases of ASD identified were also measured. Main results were controlled for race/ethnicity and intracluster correlation.

RESULTS

Two clinics were randomized to receive the intervention, and 2 served as controls. Records from 274 children (101 girls, 162 boys, and 11 missing information on sex; age range, 23-30 months) were reviewed (138 in the intervention clinics and 136 in the control clinics). Of 263 children, 242 (92.0%) were enrolled in Medicaid, 138 (52.5%) were African American, and 96 (36.5%) were Hispanic. Screening rates in the intervention clinics increased from 0% (95% CI, 0%-5.5%) at baseline to 68.4% (13 of 19) (95% CI, 43.4%-87.4%) in 6 months and to 100% (18 of 18) (95% CI, 81.5%-100%) in 24 months. Control clinics had no significant increase in screening rates (baseline, 7 of 64 children [10.9%]; 6-24 months after the intervention, 11 of 72 children [15.3%]; P = .46). Screening results were positive for 265 of 980 children (27.0%) screened by CHICA during the study period. Among the 265 patients with positive screening results, physicians indicated any response in CHICA in 151 (57.0%). Two children in the intervention group received a new diagnosis of ASD within the time frame of the study.

CONCLUSIONS AND RELEVANCE

The findings suggest that computer automation, when integrated with clinical workflow and the electronic health record, increases screening of children for ASD, but follow-up by physicians is still flawed. Automation of the subsequent workup is still needed.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT01612897.

Caregiver Comfort in Adolescents Independently Completing Screening Tablet-Based Questionnaires at Primary Care Visits

PURPOSE

The objective of this study was to assess caregiver comfort regarding adolescent completion of computerized health screening questionnaires created for adolescents.

METHODS

We conducted a mixed-method, cross-sectional survey of caregivers of adolescent patients (n = 104) aged 12-18 years who had a medical visit between June 2017 and August 2017. Topics assessed included who completed the questionnaire, caregiver comfort and concern regarding questionnaire data, and caregiver reasons for involvement in completing the questionnaire. A one-way analysis of variance was used to compare the age of the adolescent and caregiver involvement in the questionnaire.

RESULTS

The majority of adolescents (64%) reported independent completion of the questionnaire. Thirteen percent of caregivers completed the questionnaire with no involvement of the adolescent and 23% reported that caregivers and adolescents completed the questionnaire in tandem. The majority of caregivers (84%) were comfortable with adolescents completing the questionnaire. A variety of reasons were identified for caregivers completing the questionnaire (time constraints, 22%; adolescent requested caregiver help, 19%; caregiver desired to answer questions, 14%; caregiver did not realize that the questionnaire was intended for the adolescent, 11%; caregiver believed that the adolescent was too young to respond alone, 11%). Caregiver comfort with adolescent completing the questionnaire increase with age.

CONCLUSION

We found the reason most caregivers gave for completing the questionnaires were related to clinic processes (e.g. time constraints). Caregivers were more likely to complete the questionnaire with younger adolescents. Thus, pediatricians should consider how to best prepare families for initial questionnaires in primary care.

Prevalence of pain reports in pediatric primary care and association with demographics, body mass index, and exam findings: a cross-sectional study

BACKGROUND

Pediatric pain is associated to patient weight and demographics in specialized settings, but pain prevalence and its associated patient attributes in general pediatric outpatient care are unknown. Our objective was to determine the rate of positive pain screenings in pediatric primary care and evaluate the relationship between reported pain and obesity, demographics, and exam findings during routine pediatric encounters.

METHODS

Cross-sectional observational study of 26,180 patients ages 2 to 19 seen in five urban pediatric primary care clinics between 2009 and 2016. Data were collected from systematic screening using a computerized clinical decision support system. Multivariable logistic regressions were used to analyze the association between pain reporting and obesity (body mass index), age, sex, race, season, insurance status, clinic site, prior pain reporting, pain reporting method, and exam findings.

RESULTS

Pain was reported by the patient or caregiver in 14.9% of visits. In adjusted models, pain reporting was associated with obesity (Odds Ratio (OR) 1.23, 95% Confidence Intervals (CI) 1.11-1.35) and severe obesity (OR 1.32, CI 1.17-1.49); adolescents (OR 1.47, CI 1.33-1.61); and females (OR 1.21, CI 1.12-1.29). Pain reported at the preceding visit increased odds of pain reporting 2.67 times (CI 2.42-2.95). Abnormal abdominal, extremity, ear, nose, throat, and lymph node exams were associated with pain reporting. Pain reporting increased in minority races within clinics that predominantly saw a concordant race.

CONCLUSIONS

Pain is common in general pediatric encounters, and occurs more frequently in obese children and those who previously reported pain. Pain reporting may be influenced by seasonal variation and clinic factors. Future pediatric pain screening may be guided by associated risk factors to improve identification and targeted healthcare interventions.

Characteristics Associated with Confidential Consultation for Adolescents in Primary Care

OBJECTIVE

To examine how provider report of confidential consultation in the electronic health record is associated with adolescent characteristics, health risk factors, and provider training.

STUDY DESIGN

This prospective cohort study was conducted as part of a larger study implementing computerized clinical decision support in 2 urban primary care clinics. Adolescents used tablets to complete screening questions for specified risk factors in the waiting room. Adolescent-reported risk factors included sexual activity, substance use, and depressive symptoms. Providers were prompted on encounter forms to address identified risk factors and indicate whether confidential consultation was provided. Provider types included adolescent medicine board certified pediatrics and general pediatrics. Differences in proportions of adolescents reporting risk factors by provider type were assessed using χ² tests. Associations between adolescent characteristics, risk factors, and provider-reported confidential consultation were examined using logistic regression analyses.

RESULTS

The sample included 1233 English and Spanish-speaking adolescents 12-20 years of age (52% female; 60% black; 50% early adolescent). Patients seen by adolescent medicine board certified providers reported sexual activity, depressive symptoms, and substance use significantly more often than those seen by general pediatric providers. Among patients seen by board certified adolescent medicine providers, confidential consultation was provided to 90%. For those seen by general pediatric providers, confidential consultation was provided to 53%. Results of multiple logistic regression demonstrated that female sex, later adolescence, and clinic location were significantly associated with confidential consultation.

CONCLUSIONS

Provider training is needed to reinforce the importance of confidential consultation for all adolescents.

Unexplained Practice Variation in Primary Care Providers' Concern for Pediatric Obstructive Sleep Apnea

OBJECTIVE

To examine primary care provider (PCP) screening practice for obstructive sleep apnea (OSA) and predictive factors for screening habits. A secondary objective was to describe the polysomnography completion proportion and outcome. We hypothesized that both provider and child health factors would predict PCP suspicion of OSA.

METHODS

A computer decision support system that automated screening for snoring was implemented in 5 urban primary care clinics in Indianapolis, Indiana. We studied 1086 snoring children aged 1 to 11 years seen by 26 PCPs. We used logistic regression to examine the association between PCP suspicion of OSA and child demographics, child health characteristics, provider characteristics, and clinic site.

RESULTS

PCPs suspected OSA in 20% of snoring children. Factors predicting PCP concern for OSA included clinic site (P < .01; odds ratio [OR] = 0.13), Spanish language (P < .01; OR = 0.53), provider training (P = .01; OR = 10.19), number of training years (P = .01; OR = 4.26) and child age (P < .01), with the youngest children least likely to elicit PCP concern for OSA (OR = 0.20). No patient health factors (eg, obesity) were significantly predictive. Proportions of OSA suspicion were variable between clinic sites (range, 6-28%) and between specific providers (range, 0-63%). Of children referred for polysomnography (n = 100), 61% completed the study. Of these, 67% had OSA.

CONCLUSIONS

Results suggest unexplained small area practice variation in PCP concern for OSA among snoring children. It is likely that many children at risk for OSA remain unidentified. An important next step is to evaluate interventions to support PCPs in evidence-based OSA identification.

A six-year repeated evaluation of computerized clinical decision support system user acceptability

OBJECTIVE

Long-term acceptability among computerized clinical decision support system (CDSS) users in pediatrics is unknown. We examine user acceptance patterns over six years of our continuous computerized CDSS integration and updates.

MATERIALS AND METHODS

Users of Child Health Improvement through Computer Automation (CHICA), a CDSS integrated into clinical workflows and used in several urban pediatric community clinics, completed annual surveys including 11 questions covering user acceptability. We compared responses across years within a single healthcare system and between two healthcare systems. We used logistic regression to assess the odds of a favorable response to each question by survey year, clinic role, part-time status, and frequency of CHICA use.

RESULTS

Data came from 380 completed surveys between 2011 and 2016. Responses were significantly more favorable for all but one measure by 2016 (OR range 2.90-12.17, all p < 0.01). Increasing system maturity was associated with improved perceived function of CHICA (OR range 4.24-7.58, p < 0.03). User familiarity was positively associated with perceived CDSS function (OR range 3.44-8.17, p < 0.05) and usability (OR range 9.71-15.89, p < 0.01) opinions.

CONCLUSION

We present a long-term, repeated follow-up of user acceptability of a CDSS. Favorable opinions of the CDSS were more likely in frequent users, physicians and advanced practitioners, and full-time workers. CHICA acceptability increased as it matured and users become more familiar with it. System quality improvement, user support, and patience are important in achieving wide-ranging, sustainable acceptance of CDSS.

Suicide Screening in Primary Care: Use of an Electronic Screener to Assess Suicidality and Improve Provider Follow-Up for Adolescents

PURPOSE

The purpose of this study was to assess the feasibility of using an existing computer decision support system to screen adolescent patients for suicidality and provide follow-up guidance to clinicians in a primary care setting. Predictors of patient endorsement of suicidality and provider documentation of follow-up were examined.

METHODS

A prospective cohort study was conducted to examine the implementation of a CDSS that screened adolescent patients for suicidality and provided follow-up recommendations to providers. The intervention was implemented for patients aged 12-20 years in two primary care clinics in Indianapolis, Indiana.

RESULTS

The sample included 2,134 adolescent patients (51% female; 60% black; mean age = 14.6 years [standard deviation = 2.1]). Just over 6% of patients screened positive for suicidality. A positive endorsement of suicidality was more common among patients who were female, depressed, and seen by an adolescent-medicine board-certified provider as opposed to general pediatric provider. Providers documented follow-up action for 83% of patients who screened positive for suicidality. Documentation of follow-up action was correlated with clinic site and Hispanic race. The majority of patients who endorsed suicidality (71%) were deemed not actively suicidal after assessment by their provider.

CONCLUSIONS

Incorporating adolescent suicide screening and provider follow-up guidance into an existing computer decision support system in primary care is feasible and well utilized by providers. Female gender and depressive symptoms are consistently associated with suicidality among adolescents, although not all suicidal adolescents are depressed. Universal use of a multi-item suicide screener that assesses recency might more effectively identify suicidal adolescents.

Multi-model-based interactive authoring environment for creating shareable medical knowledge

OBJECTIVE

Technologically integrated healthcare environments can be realized if physicians are encouraged to use smart systems for the creation and sharing of knowledge used in clinical decision support systems (CDSS). While CDSSs are heading toward smart environments, they lack support for abstraction of technology-oriented knowledge from physicians. Therefore, abstraction in the form of a user-friendly and flexible authoring environment is required in order for physicians to create shareable and interoperable knowledge for CDSS workflows. Our proposed system provides a user-friendly authoring environment to create Arden Syntax MLM (Medical Logic Module) as shareable knowledge rules for intelligent decision-making by CDSS.

METHODS AND MATERIALS

Existing systems are not physician friendly and lack interoperability and shareability of knowledge. In this paper, we proposed Intelligent-Knowledge Authoring Tool (I-KAT), a knowledge authoring environment that overcomes the above mentioned limitations. Shareability is achieved by creating a knowledge base from MLMs using Arden Syntax. Interoperability is enhanced using standard data models and terminologies. However, creation of shareable and interoperable knowledge using Arden Syntax without abstraction increases complexity, which ultimately makes it difficult for physicians to use the authoring environment. Therefore, physician friendliness is provided by abstraction at the application layer to reduce complexity. This abstraction is regulated by mappings created between legacy system concepts, which are modeled as domain clinical model (DCM) and decision support standards such as virtual medical record (vMR) and Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT). We represent these mappings with a semantic reconciliation model (SRM).

RESULTS

The objective of the study is the creation of shareable and interoperable knowledge using a user-friendly and flexible I-KAT. Therefore we evaluated our system using completeness and user satisfaction criteria, which we assessed through the system- and user-centric evaluation processes. For system-centric evaluation, we compared the implementation of clinical information modelling system requirements in our proposed system and in existing systems. The results suggested that 82.05% of the requirements were fully supported, 7.69% were partially supported, and 10.25% were not supported by our system. In the existing systems, 35.89% of requirements were fully supported, 28.20% were partially supported, and 35.89% were not supported. For user-centric evaluation, the assessment criterion was 'ease of use'. Our proposed system showed 15 times better results with respect to MLM creation time than the existing systems. Moreover, on average, the participants made only one error in MLM creation using our proposed system, but 13 errors per MLM using the existing systems.

CONCLUSION

We provide a user-friendly authoring environment for creation of shareable and interoperable knowledge for CDSS to overcome knowledge acquisition complexity. The authoring environment uses state-of-the-art decision support-related clinical standards with increased ease of use.

Decision support tools in low back pain

Information from individual classification systems or clinical prediction rules that aim to facilitate stratified care in low back pain is important but often not comprehensive enough to be used to support clinical decision-making. The development and implementation of a clinically useful decision support tool (DST) that considering all key features is a challenging enterprise, requiring a multidisciplinary approach. Key features are inclusion of all relevant treatment options, patient characteristics, and benefits and harms and presentation as an accessible and easy to use toolkit. To be of clinical value, a DST should (1) be based on large numbers of high-quality data, allowing robust estimation of benefits and harms; (2) be presented using visually attractive and easy-to-use software; (3) be externally validated with a clinical beneficial impact established; and (4) include a procedure for regular updating and monitoring. As an illustration, we describe the development; presentation; and plans for further validation, implementation, and updating of the Nijmegen Decision Tool for Chronic Low Back Pain (NDT-CLBP).

Effectiveness of Computer Automation for the Diagnosis and Management of Childhood Type 2 Diabetes: A Randomized Clinical Trial

Importance

Type 2 diabetes (T2D) is increasingly common in young individuals. Primary prevention and screening among children and adolescents who are at substantial risk for T2D are recommended, but implementation of T2D screening practices in the pediatric primary care setting is uncommon.

Objective

To determine the feasibility and effectiveness of a computerized clinical decision support system to identify pediatric patients at high risk for T2D and to coordinate screening for and diagnosis of prediabetes and T2D.

Design, Setting, and Participants

This cluster-randomized clinical trial included patients from 4 primary care pediatric clinics. Two clinics were randomized to the computerized clinical decision support intervention, aimed at physicians, and 2 were randomized to the control condition. Patients of interest included children, adolescents, and young adults 10 years or older. Data were collected from January 1, 2013, through December 1, 2016.

Interventions

Comparison of physician screening and follow-up practices after adding a T2D module to an existing computer decision support system.

Main Outcomes and Measures

Electronic medical record (EMR) data from patients 10 years or older were reviewed to determine the rates at which pediatric patients were identified as having a body mass index (BMI) at or above the 85th percentile and 2 or more risk factors for T2D and underwent screening for T2D.

Results

Medical records were reviewed for 1369 eligible children (712 boys [52.0%] and 657 girls [48.0%]; median [interquartile range] age, 12.9 [11.2-15.3]), of whom 684 were randomized to the control group and 685 to the intervention group. Of these, 663 (48.4%) had a BMI at or above the 85th percentile. Five hundred sixty-five patients (41.3%) met T2D screening criteria, with no difference between control and intervention sites. The T2D module led to a significant increase in the percentage of patients undergoing screening for T2D (89 of 283 [31.4%] vs 26 of 282 [9.2%]; adjusted odds ratio, 4.6; 95% CI, 1.5-14.7) and a greater proportion attending a scheduled follow-up appointment (45 of 153 [29.4%] vs 38 of 201 [18.9%]; adjusted odds ratio, 1.8; 95% CI, 1.5-2.2).

Conclusions and Relevance

Use of a computerized clinical decision support system to automate the identification and screening of pediatric patients at high risk for T2D can help overcome barriers to the screening process. The support system significantly increased screening among patients who met the American Diabetes Association criteria and adherence to follow-up appointments with primary care clinicians.

Trial Registration

clinicaltrials.gov Identifier: NCT01814787.

Computerized Clinical Decision Support: Contributions from 2015

OBJECTIVE

To summarize recent research and select the best papers published in 2015 in the field of computerized clinical decision support for the Decision Support section of the IMIA yearbook.

METHOD

A literature review was performed by searching two bibliographic databases for papers related to clinical decision support systems (CDSSs) and computerized provider order entry (CPOE) systems. The aim was to identify a list of candidate best papers from the retrieved papers that were then peer-reviewed by external reviewers. A consensus meeting between the two section editors and the IMIA editorial team was finally conducted to conclude in the best paper selection.

RESULTS

Among the 974 retrieved papers, the entire review process resulted in the selection of four best papers. One paper reports on a CDSS routinely applied in pediatrics for more than 10 years, relying on adaptations of the Arden Syntax. Another paper assessed the acceptability and feasibility of an important CPOE evaluation tool in hospitals outside the US where it was developed. The third paper is a systematic, qualitative review, concerning usability flaws of medication-related alerting functions, providing an important evidence-based, methodological contribution in the domain of CDSS design and development in general. Lastly, the fourth paper describes a study quantifying the effect of a complex, continuous-care, guideline-based CDSS on the correctness and completeness of clinicians' decisions.

CONCLUSIONS

While there are notable examples of routinely used decision support systems, this 2015 review on CDSSs and CPOE systems still shows that, despite methodological contributions, theoretical frameworks, and prototype developments, these technologies are not yet widely spread (at least with their full functionalities) in routine clinical practice. Further research, testing, evaluation, and training are still needed for these tools to be adopted in clinical practice and, ultimately, illustrate the benefits that they promise.