Promises, Pitfalls, and Clinical Applications of Artificial Intelligence in Pediatrics.

Artificial intelligence (AI) broadly describes a branch of computer science focused on developing machines capable of performing tasks typically associated with human intelligence. Those who connect AI with the world of science fiction may meet its growing rise with hesitancy or outright skepticism. However, AI is becoming increasingly pervasive in our society, from algorithms helping to sift through airline fares to substituting words in emails and SMS text messages based on user choices. Data collection is ongoing and is being leveraged by software platforms to analyze patterns and make predictions across multiple industries. Health care is gradually becoming part of this technological transformation, as advancements in computational power and storage converge with the rapid expansion of digitized medical information. Given the growing and inevitable integration of AI into health care systems, it is our viewpoint that pediatricians urgently require training and orientation to the uses, promises, and pitfalls of AI in medicine. AI is unlikely to solve the full array of complex challenges confronting pediatricians today; however, if used responsibly, it holds great potential to improve many aspects of care for providers, children, and families. Our aim in this viewpoint is to provide clinicians with a targeted introduction to the field of AI in pediatrics, including key promises, pitfalls, and clinical applications, so they can play a more active role in shaping the future impact of AI in medicine.

Increased delay from initial concern to diagnosis of autism spectrum disorder and associated health care resource utilization and cost among children aged younger than 6 years in the United States.

BACKGROUND: Prolonged delays between first caregiver concern and autism spectrum disorder (ASD) diagnosis have been reported, but associations between length of time to diagnosis (TTD) and health care resource utilization (HCRU) and costs have not been studied in a large sample of children with ASD. OBJECTIVE: To address these informational gaps in the ASD diagnostic pathway. METHODS: This retrospective, observational, single cohort analysis of Optum's administrative claims data from January 1, 2011, to December 31, 2020, included commercially insured children who had 2 or more claims for an ASD diagnosis (earliest diagnosis designated as the index date), were between the ages of older than 1.5 years and 6 years or younger at index date, and were continuously enrolled for up to 48 months before and for 12 months after the index date. Two cohorts (between the ages of older than 1.5 years and 3 years or younger and between the ages of older than 3 years and 6 years or younger at ASD diagnosis) were divided into shorter (less than median) and longer (greater than or equal to median) TTD around each cohort median TTD calculated from the first documented ASD-related concern to the earliest ASD diagnosis, because TTD may vary by age at diagnosis. This exploratory analysis compared all-cause and ASD-related HCRU and costs during a 12-month period preceding ASD diagnosis among children with shorter vs longer TTD. RESULTS: 8,954 children met selection criteria: 4,205 aged 3 years or younger and 4,749 aged older than 3 years at diagnosis, with median TTD of 9.5 and 22.1 months, respectively. In the year preceding ASD diagnosis, children with longer TTD in both age cohorts experienced a greater number of all-cause and ASD-related health care visits compared with those with shorter TTD (mean and median number of office or home visits were approximately 1.5- and 2-fold greater in longer vs shorter TTD groups; P < 0.0001). The mean all-cause medical cost per child in the year preceding ASD diagnosis was approximately 2-fold higher for those with longer vs shorter TTD ($5,268 vs $2,525 in the younger and $5,570 vs $2,265 in the older cohort; P < 0.0001 for both). Mean ASD-related costs were also higher across age cohorts for those with longer vs shorter TTD ($2,355 vs $859 in the younger and $2,351 vs $1,144 in the older cohort; P < 0.0001 for both). CONCLUSIONS: In the year prior to diagnosis, children with longer TTD experienced more frequent health care visits and greater cost burden in their diagnostic journey compared with children with shorter TTD. Novel diagnostic approaches that could accelerate TTD may reduce costs and HCRU for commercially insured children. DISCLOSURES: This study was funded by Cognoa, Inc. Optum received funding from Cognoa to conduct this study. Dr Salomon is an employee and holds stock options of Cognoa, Inc. Dr Campbell was an employee of Cognoa, Inc., at the time this study was conducted. Dr Duhig was an employee of Cognoa, Inc., at the time the study was conducted and holds stock options. Dr Vu, Ms Kruse, Mr Gaur, and Ms Gupta are employees and/or stockholders of Optum. Dr Tibrewal was an employee of Optum at the time the research for this study was conducted. Dr Taraman is an employee and holds stock options of Cognoa, Inc., receives consulting fees from Cognito Therapeutics, volunteers as a board member of the American Academy of Pediatrics California and Orange County Chapter, is a paid advisor for MI10 LLC, and owns stock options of NTX, Inc., and HandzIn.

'Get Healthy!' physical activity and healthy eating intervention for adults with intellectual disability: results from the feasibility pilot.

BACKGROUND: People with intellectual disabilities (ID) experience high rates of lifestyle related morbidities, in part due to lack of access to tailored health promotion programmes. This study aimed to assess the feasibility and preliminary efficacy of a tailored healthy lifestyle intervention, Get Healthy! METHODS: Get Healthy! is a 12-week physical activity and healthy eating programme designed to address lifestyle-related risks for adults with mild-moderate ID. The feasibility pilot was designed to assess subjective participant experience and programme feasibility across: recruitment and screening, retention, session attendance and engagement, adverse events, and practicality and reliability of outcome procedures. Exploratory programme efficacy was assessed across the following measures: anthropometry (body mass index, weight, waist circumference), cardiovascular fitness, physical strength, dietary intake, healthy literacy, and quality of life. RESULTS: Six participants with moderate ID and two carer participants completed the feasibility trial, representing a 100% retention rate. Qualitative data indicated the programme was well received. Participants with ID attended 75% of sessions offered and displayed a high level of engagement in sessions attended (91% mean engagement score). While most data collection procedures were feasible to implement, several measures were either not feasible for our participants, or required a higher level of support to implement than was provided in the existing trial protocol. Participants with ID displayed decreases in mean waist circumference between baseline and endpoint (95% CI: - 3.20, - 0.17 cm) and some improvements in measures of cardiovascular fitness and physical strength. No changes in weight, body mass index, or objectively measured knowledge of nutrition and exercise or quality of life were detected from baseline to programme endpoint. Dietary intake results were mixed. DISCUSSION: The Get Healthy! programme was feasible to implement and well received by participants with moderate ID and their carers. Exploratory efficacy data indicates the programme has potential to positively impact important cardiometabolic risk factors such as waist circumference, cardiovascular fitness, and physical strength. Several of the proposed data collection instruments will require modification or replacement prior to use in a sufficiently powered efficacy trial. TRIAL REGISTRATION: ACTRN: ACTRN12618000349246. Registered March 8th 2018-retrospectively registered, https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=374497 UTN: U1111-1209-3132.

An Introduction to Artificial Intelligence in Developmental and Behavioral Pediatrics.

ABSTRACT: Technological breakthroughs, together with the rapid growth of medical information and improved data connectivity, are creating dramatic shifts in the health care landscape, including the field of developmental and behavioral pediatrics. While medical information took an estimated 50 years to double in 1950, by 2020, it was projected to double every 73 days. Artificial intelligence (AI)-powered health technologies, once considered theoretical or research-exclusive concepts, are increasingly being granted regulatory approval and integrated into clinical care. In the United States, the Food and Drug Administration has cleared or approved over 160 health-related AI-based devices to date. These trends are only likely to accelerate as economic investment in AI health care outstrips investment in other sectors. The exponential increase in peer-reviewed AI-focused health care publications year over year highlights the speed of growth in this sector. As health care moves toward an era of intelligent technology powered by rich medical information, pediatricians will increasingly be asked to engage with tools and systems underpinned by AI. However, medical students and practicing clinicians receive insufficient training and lack preparedness for transitioning into a more AI-informed future. This article provides a brief primer on AI in health care. Underlying AI principles and key performance metrics are described, and the clinical potential of AI-driven technology together with potential pitfalls is explored within the developmental and behavioral pediatric health context.

Feasibility and Impact of Integrating an Artificial Intelligence-Based Diagnosis Aid for Autism Into the Extension for Community Health Outcomes Autism Primary Care Model: Protocol for a Prospective Observational Study.

BACKGROUND: The Extension for Community Health Outcomes (ECHO) Autism Program trains clinicians to screen, diagnose, and care for children with autism spectrum disorder (ASD) in primary care settings. This study will assess the feasibility and impact of integrating an artificial intelligence (AI)-based ASD diagnosis aid (the device) into the existing ECHO Autism Screening Tool for Autism in Toddlers and Young Children (STAT) diagnosis model. The prescription-only Software as a Medical Device, designed for use in children aged 18 to 72 months at risk for developmental delay, produces ASD diagnostic recommendations after analyzing behavioral features from 3 distinct inputs: a caregiver questionnaire, 2 short home videos analyzed by trained video analysts, and a health care provider questionnaire. The device is not a stand-alone diagnostic and should be used in conjunction with clinical judgment. OBJECTIVE: This study aims to assess the feasibility and impact of integrating an AI-based ASD diagnosis aid into the ECHO Autism STAT diagnosis model. The time from initial ECHO Autism clinician concern to ASD diagnosis is the primary end point. Secondary end points include the time from initial caregiver concern to ASD diagnosis, time from diagnosis to treatment initiation, and clinician and caregiver experience of device use as part of the ASD diagnostic journey. METHODS: Research participants for this prospective observational study will be patients suspected of having ASD (aged 18-72 months) and their caregivers and up to 15 trained ECHO Autism clinicians recruited by the ECHO Autism Communities research team from across rural and suburban areas of the United States. Clinicians will provide routine clinical care and conduct best practice ECHO Autism diagnostic evaluations in addition to prescribing the device. Outcome data will be collected via a combination of electronic questionnaires, reviews of standard clinical care records, and analysis of device outputs. The expected study duration is no more than 12 months. The study was approved by the institutional review board of the University of Missouri-Columbia (institutional review board-assigned project number 2075722). RESULTS: Participant recruitment began in April 2022. As of June 2022, a total of 41 participants have been enrolled. CONCLUSIONS: This prospective observational study will be the first to evaluate the use of a novel AI-based ASD diagnosis aid as part of a real-world primary care diagnostic pathway. If device integration into primary care proves feasible and efficacious, prolonged delays between the first ASD concern and eventual diagnosis may be reduced. Streamlining primary care ASD diagnosis could potentially reduce the strain on specialty services and allow a greater proportion of children to commence early intervention during a critical neurodevelopmental window. TRIAL REGISTRATION: ClinicalTrials.gov NCT05223374; https://clinicaltrials.gov/ct2/show/NCT05223374. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/37576.

Primary care for people with an intellectual disability - what is prescribed? An analysis of medication recommendations from the BEACH dataset.

BACKGROUND: People with intellectual disability (ID) experience a range of health disparities. Little is known about differential primary care prescribing patterns for people with and without ID. AIM: To compare medications recommended by GPs at encounters where ID is recorded versus other encounters. DESIGN & SETTING: Analysis of national Australian GP medication data from the Bettering the Evaluation and Care of Health (BEACH) programme, January 2003-December 2012 inclusive. METHOD: Medication recommendations made at encounters where an ID-defining problem was recorded as a reason for encounter (RFE) and/or as a problem managed, were allocated to the 'ID group' (n = 563). These encounters were compared with all other encounters (the 'non-ID group', n = 1 004 095) during the study period. Following age-sex standardisation of ID group encounters, significant differences were determined by non-overlapping 95% confidence intervals (CIs). RESULTS: Antipsychotics and anticonvulsants were recommended more frequently at ID group encounters than at non-ID group encounters. Antidepressant and anxiolytic recommendation rates did not differ between groups. Narcotic analgesic and antihypertensive recommendations were significantly lower at ID group encounters. CONCLUSION: Higher rates of epilepsy and mental illness, and off-label use of some antipsychotics and anticonvulsants for behaviour management in people with ID, may have contributed to medication recommendations observed in this analysis. Lower narcotic analgesic recommendations at ID group encounters may relate to complex presentations and the nature of problems managed, while lower antihypertensive recommendations may indicate some potential omission of routine blood pressure measurement.

'Get Healthy!' A physical activity and nutrition program for older adults with intellectual disability: pilot study protocol.

BACKGROUND: Older adults with intellectual disability have high rates of lifestyle-related illness yet remain poorly engaged in physical activity and nutrition interventions. There is a need to clarify what types of healthy lifestyle interventions are feasible and effective to implement in this population and how outcome measures can best be tracked. This paper describes the pilot feasibility study protocol for implementing a 12-week physical activity and healthy eating program, 'Get Healthy!' with older adults with intellectual disability. METHODS: The primary study aims are to assess the feasibility of implementing and monitoring the 'Get Healthy!' program with adults with mild to moderate intellectual disability, aged 40 years and over, and their carers. Secondary study aims are to assess the impact of the intervention across the following parametres: body mass index, waist circumference, cardiovascular fitness, physical activity (amount and intensity) and sedentary behaviours, resting blood pressure, functional strength/capacity, dietary intake (energy intake, food group consumption and diet quality), dietary and physical activity knowledge, and quality of life. Between 8 and 10 participants in total will be recruited into the 12-week program that will be run in metropolitan NSW, Australia. A combination of objective and subjective measures will be used to assess program feasibility and impact at set timepoints (baseline, mid and end-program). DISCUSSION: Results from the feasibility pilot will be used to refine the study methodology and 'Get Healthy!' program content for future use in a sufficiently powered trial. Findings may be of interest to a broad range of disability and allied health workers engaged in supporting and monitoring healthy lifestyle change in adults with intellectual disability. TRIAL REGISTRATION: ACTRN: ACTRN12618000349246. Registered March 8, 2018- Retrospectively registered, UTN: U1111-1209-3132.

Intellectual disability content within pre-registration nursing curriculum: How is it taught?

BACKGROUND: Despite experiencing higher rates of physical and mental health conditions compared with the general population, people with intellectual disability face inequitable access to healthcare services. Improving education of healthcare professionals is one way to reduce these inequalities. OBJECTIVE: To determine how intellectual disability content is taught within Australian nursing schools. DESIGN: A two-phase audit of Australian nursing curricula content was conducted using an interview and online survey. SETTING: Nursing schools Australia-wide providing pre-registration courses. PARTICIPANTS: For Phase 1, course coordinators from 31 nursing schools completed an interview on course structure. Teaching staff from 15 schools in which intellectual disability content was identified completed an online survey for Phase 2. METHODS: Methods used to teach intellectual disability content and who taught the content were audited using an online survey. RESULTS: Across the 15 schools offering intellectual disability content, lectures were the most common teaching method (82% of units), followed by tutorials (59%), workshops (26%), then other methods (e.g. e-learning; 12%). Approximately three-quarters of intellectual disability teaching used some problem-and/or enquiry-based learning. Only one nursing school involved a person with intellectual disability in delivering teaching content. Six (19%) participating schools identified staff who specialise in intellectual disability, and seven (23%) identified staff with a declared interest in the area. CONCLUSION: While some nursing schools are using diverse methods to teach intellectual disability content, many are not; as a result, nursing students may miss out on acquiring the attributes which enable them to address the significant health inequalities faced by this group. A specific deficit was identified relating to inclusive teaching and clinical contact with people with intellectual disability.

Impact of age of onset of psychosis and engagement in higher education on duration of untreated psychosis.

BACKGROUND: The average age of onset of psychosis coincides with the age of college enrollment. Little is known about the impact of educational engagement on DUP in a college-aged population. AIMS: To determine DUP, and the impact of educational engagement, for college-aged participants of the RAISE study (n = 404). METHOD: We conducted secondary data analyses on the publicly available RAISE dataset. Subsamples were analyzed to determine the impact of age and educational engagement on DUP. RESULTS: DUP was significantly shorter (p < 0.02) for participants who were college-aged (18-22 years, n = 44) and engaged in post-secondary education (median = 12 weeks, mean = 29 weeks) compared with participants who were college-aged and not engaged in higher education (n = 92, median = 29 weeks, mean = 44 weeks). CONCLUSIONS: Educational engagement appears to be associated with a shorter DUP. This may be partially explained by the presence of on-site wellness centers in college settings. However, even among young people who engaged in post-secondary education DUP was still at, or beyond, the upper limit of WHO recommendations in this group. Future research exploring how colleges could improve their capacity to detect and refer at risk students for treatment at an earlier stage is recommended.

Prescribing psychotropic drugs to adults with an intellectual disability.

Mental illness is common in people with intellectual disability. They may also have physical health problems which can affect their mental state. Difficulties in communication can contribute to mental health problems being overlooked. These may present with changes in behaviour. Psychological management is usually preferable to prescribing psychotropic drugs. Behavioural approaches are the most appropriate way to manage challenging behaviour. If a drug is considered, prescribers should complete a thorough diagnostic assessment, exclude physical and environmental contributions to symptoms, and consider medical comorbidities before prescribing. Where possible avoid psychotropics with the highest cardiometabolic burden. Prescribe the minimum effective dose and treatment length, and regularly monitor drug efficacy and adverse effects. There is insufficient evidence to support the use of psychotropics for challenging behaviour. They should be avoided unless the behaviour is severe and non-responsive to other treatments.

Positive cardiometabolic health for adults with intellectual disability: an early intervention framework.

Cardiometabolic morbidity is a significant contributor to the poorer health outcomes experienced by people with intellectual disability (ID). Tailoring cardiometabolic monitoring tools developed for the general population to better fit the altered risk profiles and extra needs of people with ID may help to improve health outcomes. This paper describes a new cardiometabolic monitoring framework designed to address the extra needs of people with ID. The framework was adapted from a generalist guideline after a process of extensive consultation with the original authors and over 30 ID and cardiometabolic experts. In addition to standard cardiometabolic monitoring practice, the framework encourages clinicians to: anticipate and address barriers to care such as communication difficulties and fear of blood tests; account for socioeconomic and genetic factors altering baseline cardiometabolic risk; and carefully rationalize psychotropic prescription. Together with this framework, a toolkit of free cardiometabolic resources tailored for people with ID and formal and informal carers is included. The monitoring framework promotes a multidisciplinary and holistic approach to cardiometabolic care for people with ID.

Intellectual disability health content within nursing curriculum: An audit of what our future nurses are taught.

BACKGROUND: Individuals with intellectual disability experience chronic and complex health issues, but face considerable barriers to healthcare. One such barrier is inadequate education of healthcare professionals. OBJECTIVE: To establish the quantity and nature of intellectual disability content offered within Australian nursing degree curricula. DESIGN: A two-phase national audit of nursing curriculum content was conducted using an interview and online survey. SETTING: Australian nursing schools offering pre-registration courses. PARTICIPANTS: Pre-registration course coordinators from 31 universities completed the Phase 1 interview on course structure. Unit coordinators and teaching staff from 15 universities in which intellectual disability content was identified completed the Phase 2 online survey. METHODS: Quantity of compulsory and elective intellectual disability content offered (units and teaching time) and the nature of the content (broad categories, specific topics, and inclusive teaching) were audited using an online survey. RESULTS: Over half (52%) of the schools offered no intellectual disability content. For units of study that contained some auditable intellectual disability content, the area was taught on average for 3.6h per unit of study. Units were evenly distributed across the three years of study. Just three participating schools offered 50% of all units audited. Clinical assessment skills, and ethics and legal issues were most frequently taught, while human rights issues and preventative health were poorly represented. Only one nursing school involved a person with intellectual disability in content development or delivery. CONCLUSION: Despite significant unmet health needs of people with intellectual disability, there is considerable variability in the teaching of key intellectual disability content, with many gaps evident. Equipping nursing students with skills in this area is vital to building workforce capacity.

Antipsychotic discontinuation syndromes: a narrative review of the evidence and its integration into Australian mental health nursing textbooks.

In light of the high number of people discontinuing antipsychotics each year, it is essential that nurses develop a robust understanding of all aspects of the discontinuation experience. While there is a large body of published work documenting post-discontinuation relapse rates, less is known about other aspects of the discontinuation experience. This paper presents the results of a narrative review of international studies of antipsychotic discontinuation syndromes and their relevance to nursing practice. Four key mental health nursing textbooks used in student nurse education in Australia are examined to assess how this evidence has been incorporated into clinical recommendations. This review finds that the evidence for discontinuation syndromes could be more widely disseminated and applied than it is at present. Strikingly, this evidence has not been incorporated into key mental health nursing textbooks in Australia at all. Slow integration into nursing published work may be influenced by a number of clinical and research uncertainties. We consider the impact of this silence on key nursing roles of psycho-education and adverse event monitoring during antipsychotic discontinuation periods. Further robust research should be conducted into discontinuation syndromes as a matter of urgency. Given the high number of consumers potentially impacted upon by discontinuation syndromes, nurse authors and educators should consider revising key nursing textbooks to include the currently available information about discontinuation syndromes.

"All roads lead to medication?" Qualitative responses from an Australian first-person survey of antipsychotic discontinuation.

OBJECTIVE: The purpose of the survey was to better understand the experiences of people who attempt antipsychotic discontinuation. METHOD: A multiple-choice and short-answer survey was distributed in 2011-2012 to potential participants involved in participating organizations. Respondents were asked about past discontinuation events, including decision negotiation and withdrawal experience. This article thematically analyses their free-text responses. RESULTS: There were 98 valid surveys returned. Respondents highlighted the roles of the therapeutic alliance and health and illness explanatory models in understanding the context of discontinuation. Reported impacts of discontinuation were mixed and complex. Withdrawal syndromes were described by over half of the participants. Of the 98 respondents, 21 reported remaining antipsychotic-free at the time of survey completion. CONCLUSIONS AND IMPLICATIONS FOR PRACTICE: Participant accounts highlight the importance of context and relationships in their thinking about antipsychotic discontinuation. Although results cannot necessarily be generalized, participant descriptions of withdrawal syndromes suggest there may be a need to improve education, monitoring, and support strategies for some people during discontinuation. Shifting toward a more collaborative, transparent, and service-user-driven approach to discontinuation may help to mitigate some of the negative discontinuation impacts identified. The polarized discontinuation outcomes described highlight the individuality of every participant's recovery journey and the need to avoid generalizing about the role of antipsychotics in care.