Evaluation of an artificial intelligence-based medical device for diagnosis of autism spectrum disorder.

Autism spectrum disorder (ASD) can be reliably diagnosed at 18 months, yet significant diagnostic delays persist in the United States. This double-blinded, multi-site, prospective, active comparator cohort study tested the accuracy of an artificial intelligence-based Software as a Medical Device designed to aid primary care healthcare providers (HCPs) in diagnosing ASD. The Device combines behavioral features from three distinct inputs (a caregiver questionnaire, analysis of two short home videos, and an HCP questionnaire) in a gradient boosted decision tree machine learning algorithm to produce either an ASD positive, ASD negative, or indeterminate output. This study compared Device outputs to diagnostic agreement by two or more independent specialists in a cohort of 18-72-month-olds with developmental delay concerns (425 study completers, 36% female, 29% ASD prevalence). Device output PPV for all study completers was 80.8% (95% confidence intervals (CI), 70.3%-88.8%) and NPV was 98.3% (90.6%-100%). For the 31.8% of participants who received a determinate output (ASD positive or negative) Device sensitivity was 98.4% (91.6%-100%) and specificity was 78.9% (67.6%-87.7%). The Device's indeterminate output acts as a risk control measure when inputs are insufficiently granular to make a determinate recommendation with confidence. If this risk control measure were removed, the sensitivity for all study completers would fall to 51.6% (63/122) (95% CI 42.4%, 60.8%), and specificity would fall to 18.5% (56/303) (95% CI 14.3%, 23.3%). Among participants for whom the Device abstained from providing a result, specialists identified that 91% had one or more complex neurodevelopmental disorders. No significant differences in Device performance were found across participants' sex, race/ethnicity, income, or education level. For nearly a third of this primary care sample, the Device enabled timely diagnostic evaluation with a high degree of accuracy. The Device shows promise to significantly increase the number of children able to be diagnosed with ASD in a primary care setting, potentially facilitating earlier intervention and more efficient use of specialist resources.

Multistage Adolescent Depression Screening: A Comparison of 11-Year-Olds to 12-Year-Olds.

INTRODUCTION: Adolescent depression screening is recommended starting at age 12 years, but younger children experience depression as well. Our objective was to determine whether screening for depression at age 11 years yields similar results to screening at age 12 years. METHODS: We conducted a retrospective chart review of 1000 11- and 12-year-olds in multiple pediatric offices of a large-group practice associated with a health maintenance organization in Southern California. All offices used a multistage depression screening process during well-child visits using the Patient Health Questionnaire for Adolescents, the global depression inquiry within a parent questionnaire, a chart-based review of mental health history, and brief patient/parent interview informed by the first 3 elements. RESULTS: The 11- and 12-year-old cohorts had similar completion rates for the Patient Health Questionnaire for Adolescents (99.2% vs 97.8%, P = 0.06), with similar mean total Patient Health Questionnaire for Adolescents scores (2.12 vs 2.22, P = 0.48). There was no significant difference for positive screenings determined by the pediatrician (12.0% vs 16.0%, P = 0.07), but parents of 12-year-olds were more likely have concerns for their child's mood (6.8% vs 10.5%, P = 0.04). There were similar percentages of referrals (6.2% vs 8.8%, P = 0.12), beneficial conversations related to depression and anxiety, (4.5% vs 4.8%, P = 0.85), and new mental health diagnoses (2.0% vs 2.3%, P = 0.79). DISCUSSION: The process, results, and outcomes of screenings are similar for 11- and 12-year-olds, with a tendency toward more positive findings in 12-year-olds. CONCLUSION: Multistage depression screening in 11-year-olds can be applied successfully in clinical practice, with most cases identifying youths without a prior mental health diagnosis.

School Readiness.

School readiness includes the readiness of the individual child, the school's readiness for children, and the ability of the family and community to support optimal early child development. It is the responsibility of schools to meet the needs of all children at all levels of readiness. Children's readiness for kindergarten should become an outcome measure for a coordinated system of community-based programs and supports for the healthy development of young children. Our rapidly expanding insights into early brain and child development have revealed that modifiable factors in a child's early experience can greatly affect that child's health and learning trajectories. Many children in the United States enter kindergarten with limitations in their social, emotional, cognitive, and physical development that might have been significantly diminished or eliminated through early identification and attention to child and family needs. A strong correlation between social-emotional development and school and life success, combined with alarming rates of preschool expulsion, point toward the urgency of leveraging opportunities to support social-emotional development and address behavioral concerns early. Pediatric primary care providers have access to the youngest children and their families. Pediatricians can promote and use community supports, such as home visiting programs, quality early care and education programs, family support programs and resources, early intervention services, children's museums, and libraries, which are important for addressing school readiness and are too often underused by populations who can benefit most from them. When these are not available, pediatricians can support the development of such resources. The American Academy of Pediatrics affords pediatricians many opportunities to improve the physical, social-emotional, and educational health of young children, in conjunction with other advocacy groups. This technical report provides an updated version of the previous iteration from the American Academy of Pediatrics published in 2008.

Young adult outcomes in the follow-up of the multimodal treatment study of attention-deficit/hyperactivity disorder: symptom persistence, source discrepancy, and height suppression.

BACKGROUND: The Multimodal Treatment Study (MTA) began as a 14-month randomized clinical trial of behavioral and pharmacological treatments of 579 children (7-10 years of age) diagnosed with attention-deficit/hyperactivity disorder (ADHD)-combined type. It transitioned into an observational long-term follow-up of 515 cases consented for continuation and 289 classmates (258 without ADHD) added as a local normative comparison group (LNCG), with assessments 2-16 years after baseline. METHODS: Primary (symptom severity) and secondary (adult height) outcomes in adulthood were specified. Treatment was monitored to age 18, and naturalistic subgroups were formed based on three patterns of long-term use of stimulant medication (Consistent, Inconsistent, and Negligible). For the follow-up, hypothesis-generating analyses were performed on outcomes in early adulthood (at 25 years of age). Planned comparisons were used to estimate ADHD-LNCG differences reflecting persistence of symptoms and naturalistic subgroup differences reflecting benefit (symptom reduction) and cost (height suppression) associated with extended use of medication. RESULTS: For ratings of symptom severity, the ADHD-LNCG comparison was statistically significant for the parent/self-report average (0.51 ± 0.04, p < .0001, d = 1.11), documenting symptom persistence, and for the parent/self-report difference (0.21 ± 0.04, p < .0001, d = .60), documenting source discrepancy, but the comparisons of naturalistic subgroups reflecting medication effects were not significant. For adult height, the ADHD group was 1.29 ± 0.55 cm shorter than the LNCG (p < .01, d = .21), and the comparisons of the naturalistic subgroups were significant: the treated group with the Consistent or Inconsistent pattern was 2.55 ± 0.73 cm shorter than the subgroup with the Negligible pattern (p < .0005, d = .42), and within the treated group, the subgroup with the Consistent pattern was 2.36 ± 1.13 cm shorter than the subgroup with the Inconsistent pattern (p < .04, d = .38). CONCLUSIONS: In the MTA follow-up into adulthood, the ADHD group showed symptom persistence compared to local norms from the LNCG. Within naturalistic subgroups of ADHD cases, extended use of medication was associated with suppression of adult height but not with reduction of symptom severity.

Prevalence and Characteristics of School Services for High School Students with Attention-Deficit/Hyperactivity Disorder.

This study examines the prevalence and characteristics of services reported by school staff for 543 high school students participating in the 8 year follow-up of the multi-site Multimodal Treatment study of ADHD (MTA). Overall, 51.6% of students with a history of attention-deficit/hyperactivity disorder (ADHD) were receiving services through an Individualized Educational Plan (IEP) or a 504 plan, a rate higher than expected for this age group. Less than 5% of these had 504 plans; 35.5% attended special education classes. Very few services (except tutoring) were provided outside of an IEP or 504 plan. Almost all students with services received some type of academic intervention, whereas only half received any behavioral support or learning strategy. Less than one-fourth of interventions appear to be evidence-based. Students receiving services showed greater academic and behavioral needs than those not receiving services. Services varied based upon type of school, with the greatest number of interventions provided to students attending schools that only serve those with disabilities. Original MTA treatment randomization was unrelated to services, but cumulative stimulant medication and greater severity predicted more service receipt. Results highlight a need for accommodations with greater evidence of efficacy and for increased services for students who develop academic difficulties in high school.

A multi-institutional medical educational collaborative: advocacy training in California pediatric residency programs.

Educational collaboratives offer a promising approach to disseminate educational resources and provide faculty development to advance residents' training, especially in areas of novel curricular content; however, their impact has not been clearly described. Advocacy training is a recently mandated requirement of the Accreditation Council for Graduate Medical Education that many programs struggle to meet.The authors describe the formation (in 2007) and impact (from 2008 to 2010) of 13 California pediatric residency programs working in an educational collaboration ("the Collaborative") to improve advocacy training. The Collaborative defined an overarching mission, assessed the needs of the programs, and mapped their strengths. The infrastructure required to build the collaboration among programs included a social networking site, frequent conference calls, and face-to-face semiannual meetings. An evaluation of the Collaborative's activities showed that programs demonstrated increased uptake of curricular components and an increase in advocacy activities. The themes extracted from semistructured interviews of lead faculty at each program revealed that the Collaborative (1) reduced faculty isolation, increased motivation, and strengthened faculty academic development, (2) enhanced identification of curricular areas of weakness and provided curricular development from new resources, (3) helped to address barriers of limited resident time and program resources, and (4) sustained the Collaborative's impact even after formal funding of the program had ceased through curricular enhancement, the need for further resources, and a shared desire to expand the collaborative network.

Prevalence of ADHD symptoms in patients with congenital heart disease.

OBJECTIVE: The presence of attention-deficit-hyperactivity disorder (ADHD) symptoms in children with congenital heart disease (CHD) was investigated. METHODS: Swanson, Nolan and Pelham teacher and parent rating scales, version 4 (SNAP-IV), commonly used for assessing symptoms of ADHD, were completed by parents and counselors of children who attended a CHD summer camp. Mean scores (n = 51) were compared with two comparison groups without CHD: patients with ADHD (n = 75) and patients without ADHD (n = 41). Parent scores were also compared to previously published parent normative data. RESULTS: Patients with CHD were reported to have elevated SNAP-IV scores by parents and counselors (11.8%). Parent ratings of inattention were significantly greater in CHD subjects when compared to the comparison group without ADHD (P < 0.001), and similar to the ADHD-positive comparison group. Regarding parent ratings of hyperactivity and impulsivity, the CHD group was significantly lower than the ADHD-positive controls (P = 0.024) but greater than the ADHD-negative controls (P < 0.001). CONCLUSION: ADHD symptoms are more prevalent in children with CHD. Parent ratings of inattention and hyperactivity symptoms in CHD patients are similar to ratings in children diagnosed with ADHD. There is a trend towards a greater prevalence of inattention symptoms in patients with cyanosis or single ventricle physiology.

Adverse events in medication treatment-naïve children with attention-deficit/hyperactivity disorder: results from a small, controlled trial of lisdexamfetamine dimesylate.

OBJECTIVE: To evaluate the type, frequency, duration, and severity of treatment emergent adverse events (TEAEs) of the prodrug lisdexamfetamine dimesylate (LDX) in children with and without previous exposure to stimulant medication in the treatment of attention-deficit/hyperactivity disorder (ADHD). METHODS: This single-blind, modified laboratory school study used open-label, dose optimization of children aged 6-12 years. LDX, initiated at 30 mg, was dose titrated in 20 mg increments to a possible 70 mg over 4-5 weeks. Safety was assessed using adverse effects and LDX levels. RESULTS: Twenty-eight subjects enrolled in the study, with 27 safety protocol completers (n=14 previous stimulant exposure; n=13 stimulant naïve). The stimulant-naïve group reported more trouble sleeping, stomach pain, and hyperfocus, but only previous-exposure subjects experienced dizziness. Previous-exposure subjects showed trends of more decreased appetite, less talkativeness, and less lip sucking. There were no differences in the mean duration of TEAEs. The epidemiological method of percent person-weeks applied to ADHD treatment offers a novel approach to interpreting the pattern of TEAEs. CONCLUSION: LDX reduced the core symptoms of ADHD with more severe adverse events in stimulant-naïve than previous-exposure subjects. Future controlled studies with larger samples should address the impact of previous stimulant exposure on other ADHD treatments.

Improving Communication in ADHD Care: Results from In-office Linguistic Research.

UNLABELLED: IntroductionAn in-office linguistic study was conducted to help improve understanding of how to better evaluate and treat attention-deficit/hyperactivity disorder (ADHD). METHODS: Naturally occurring interactions were recorded among 7 psychiatrists and 23 patients and 8 pediatricians along with 22 patients and their parents. Participants were interviewed separately post-visit. Transcripts of interactions and interviews were analyzed using sociolinguistic techniques. RESULTS: Visits were variable in length and lacked concrete treatment plans. In the pediatric setting, children were typically excluded from dialogues, accounting for only 8% of words spoken. School was the primary metric used to evaluate symptoms. Pediatricians allayed parents' concerns about stimulant therapy by promising to prescribe the lowest possible dose, rather than discussing titrating to an optimal dose. Adults were evaluated idiosyncratically without the use of scales or tools. Stimulants were positioned as short-term "trials" without strong physician recommendations.DiscussionConversations about stimulant therapy lacked goal- and expectation-setting. Also missing from conversations was a definitive treatment plan based on the core symptoms of ADHD. Incorporating open-ended questions and tools or rating scales may result in a more effective and efficient in-office dialogue. CONCLUSION: Further research is warranted to assess the efficacy of communication strategies to enhance in-office discussions of ADHD and stimulant therapy.

Does prior exposure to stimulants in children with ADHD impact cardiovascular parameters from lisdexamfetamine dimesylate?

OBJECTIVE: To evaluate the safety profile, based on cardiovascular measurements, of lisdexamfetamine dimesylate (LDX) in children with and without prior exposure to stimulant medication in the treatment of attention-deficit/hyperactivity disorder (ADHD). METHODS: This single-blind, modified laboratory school study used open-label dose optimization of children aged 6 to 12 years. Lisdexamfetamine dimesylate, initiated at 30 mg, was dose titrated in 20-mg weekly increments to a possible 70 mg over 4 to 5 weeks. Safety outcomes presented in this study were assessed using vital signs (blood pressure and pulse) and electrocardiograms, conducted at baseline and following LDX treatment. Analyses were performed across all subjects, as well as post hoc based on prior treatment status. In addition, hematologic and blood biochemistry analyses were conducted at baseline but not following treatment. RESULTS: Twenty-eight subjects enrolled in the study, with 27 safety protocol completers (n = 14 prior stimulant exposure; n = 13 stimulant naïve). In total, 2 subjects in the stimulant-naïve group experienced changes from baseline vital sign measurements outside the normal range: 1 with tachycardia and 1 with blood pressure ≥ 95th percentile of the normal age range. One other subject in the stimulant-naïve group experienced prolonged QTc in response to LDX, which resolved at follow-up. Pretreatment laboratory work revealed no differences on any parameters when reviewed by exposure subgroup. CONCLUSION: While LDX reduced the core symptoms of ADHD to a similar degree in treatment-naïve and previously treated groups of children with ADHD, more cardiovascular effects were measured in stimulant-naïve children than in children who had previously been exposed to stimulant treatment. Future controlled studies with larger samples should address the impact of prior stimulant exposure on other ADHD treatments.

Long-term safety of stimulant medications used to treat children with ADHD.

Attention-deficit/hyperactivity disorder (ADHD) is a common mental health condition that affects children, adolescents, and adults. Because it is a chronic condition and typically requires effective treatment for several years or more, information on the benefits and risks of long-term pharmacotherapy for ADHD is vital to clinicians. This article reviews the emerging literature on the safety of long-term stimulant medications in ADHD-the most commonly prescribed medications for this condition. Common side effects, including cardiovascular effects, growth effects, and tics, are discussed, as well as treatment of children younger than age 6 and evidence of carcinogenic and reproductive effects.

Evidence, interpretation, and qualification from multiple reports of long-term outcomes in the Multimodal Treatment Study of children with ADHD (MTA): Part II: supporting details.

OBJECTIVE: To review and provide details about the primary and secondary findings from the Multimodal Treatment study of ADHD (MTA) published during the past decade as three sets of articles. METHOD: In the second of a two part article, we provide additional background and detail required by the complexity of the MTA to address confusion and controversy about the findings outlined in part I (the Executive Summary). RESULTS: We present details about the gold standard used to produce scientific evidence, the randomized clinical trial (RCT), which we applied to evaluate the long-term effects of two well-established unimodal treatments, Medication Management (MedMGT) and behavior therapy (Beh), the multimodal combination (Comb), and treatment "as usual" in the community (CC). For each of the first three assessment points defined by RCT methods and included in intent-to-treat analyses, we discuss our definition of evidence from the MTA, interpretation of the serial presentations of findings at each assessment point with a different definition of long-term varying from weeks to years, and qualification of the interim conclusions about long-term effects of treatments for ADHD based on many exploratory analyses described in additional published articles. CONCLUSIONS: Using a question and answer format, we discuss the possible clinical relevance of the MTA and present some practical suggestions based on current knowledge and uncertainties facing families, clinicians, and investigators regarding the long-term use of stimulant medication and behavioral therapy in the treatment of children with ADHD.

Evidence, interpretation, and qualification from multiple reports of long-term outcomes in the Multimodal Treatment study of Children With ADHD (MTA): part I: executive summary.

OBJECTIVE: To review the primary and secondary findings from the Multimodal Treatment study of ADHD (MTA) published over the past decade as three sets of articles. METHOD: In a two-part article-Part I: Executive Summary (without distracting details) and Part II: Supporting Details (with additional background and detail required by the complexity of the MTA)-we address confusion and controversy about the findings. RESULTS: We discuss the basic features of the gold standard used to produce scientific evidence, the randomized clinical trial, for which was used to contrast four treatment conditions: medication management alone (MedMgt), behavior therapy alone (Beh), the combination of these two (Comb), and a community comparison of treatment "as usual" (CC). For each of the three assessment points we review three areas that we believe are important for appreciation of the findings: definition of evidence from the MTA, interpretation of the serial presentations of findings at each assessment point with a different definition of long-term, and qualification of the interim conclusions about long-term effects of treatments for ADHD. CONCLUSION: We discuss the possible clinical relevance of the MTA and present some practical suggestions based on current knowledge and uncertainties facing families, clinicians, and investigators regarding the long-term use of stimulant medication and behavioral therapy in the treatment of children with ADHD.

Hematologic and blood biochemistry monitoring during methylphenidate treatment in children with attention-deficit/hyperactivity disorder: 2-year, open-label study results.

OBJECTIVES: Patients receiving methylphenidate for the management of attention-deficit/hyperactivity disorder are recommended to receive periodic hematologic monitoring. The objective of this study was to evaluate the long-term effects of methylphenidate treatment on blood biochemistry and hematologic values. METHODS: This study involved a detailed analysis of changes in hematologic and blood biochemistry values over the course of a 2-year study of once-daily OROS methylphenidate in otherwise healthy children aged 6 to 13 years with attention-deficit/hyperactivity disorder. Routine hematologic and blood biochemistry assessments were performed at baseline, at 6 and 12 months during study treatment, and at the end of the study. RESULTS: Of the 407 subjects enrolled in the study, 289 completed year 1, and 229 completed 21 of 24 months. No subject was excluded from entry into the study or discontinued from the study because of abnormalities of any of the blood chemistries evaluated. There were no clinically significant changes from baseline in mean values for hematologic or blood biochemistry parameters. For most values, the mean change in value over the course of the study was <5%. CONCLUSIONS: These longer-term data suggest that chronic therapy with OROS methylphenidate has no clinically significant impact on laboratory values, challenging the necessity of routine hematologic monitoring in otherwise healthy children with attention-deficit/hyperactivity disorder who are treated with methylphenidate.

Pharmacokinetics of methylphenidate in preschoolers with attention-deficit/hyperactivity disorder.

OBJECTIVE: The aim of this study was to compare the pharmacokinetics of immediate-release methylphenidate (MPH) in preschool and school-aged children with attention-deficit/hyperactivity disorder (ADHD). METHODS: Preschool children 4-5 years (n = 14) and school-aged children 6-8 years (n = 9) with diagnoses of ADHD were titrated to an effective dose of MPH based on parent, teacher, and clinician ratings in a protocol specified by the Preschoolers with ADHD Treatment Study (PATS) and then attended a laboratory school where the single morning dose of immediate release MPH was administered. Blood samples for measurement of MPH concentrations were obtained predose, and at 1, 2, 4, and 6 hours postdose. A nonlinear model was used to derive three pharmacokinetic (PK) values for analysis: Peak plasma concentration (C(max)), half-life (t(1/2)), and clearance (CL). RESULTS: The two groups did not differ in the mean mg dose of MPH (p = 0.33), or in the weight-adjusted mg/kg dose (p = 0.20). Dose-normalized C(max) was significantly higher (p = 0.003), and clearance was significantly slower (p = 0.0002) in preschool than in school-aged children. CONCLUSIONS: In this sample, age significantly affected absorption and metabolism of MPH, so that preschool children had greater exposure than school-aged children to the same weight-adjusted dose. These data suggest additional studies should be performed to characterize age-related differences in PK properties of MPH that may inform practitioners about dosing strategies based on the age and size of children being treated.

Once-daily OROS methylphenidate is safe and well tolerated in adolescents with attention-deficit/hyperactivity disorder.

This 8-week, open-label extension of a double-blind study reports on safety data for 171 adolescents with attention-deficit/hyperactivity disorder (ADHD) who received once-daily OROS methylphenidate (MPH) (18-72 mg/day). Headache, anorexia, and insomnia were the most frequently reported treatment-related adverse events. The incidence of adverse events was not related to dose. OROS MPH was safe and well tolerated at doses up to 72 mg/day.

Does prolonged therapy with a long-acting stimulant suppress growth in children with ADHD?

OBJECTIVE: To investigate whether prolonged therapy with a long-acting stimulant affects growth in children with attention-deficit/hyperactivity disorder (ADHD). METHOD: One hundred seventy-eight children ages 6 to 13 years received OROS methylphenidate (OROS MPH, CONCERTA) for at least 21 months. Height and weight were measured monthly during the first year and every 3 months thereafter. RESULTS: At baseline, subjects were approximately the expected height for their age and somewhat heavier than expected. Subjects gained height steadily throughout the study and were on average 0.23 cm less than expected at month 21. Weight did not increase and BMI decreased slightly in the first 4 months. Thereafter, weight Z score and BMI Z score remained relatively constant and children were on average 1.23 kg less than expected at month 21. Previous stimulant therapy tended to be associated with a smaller decrease in Z score during the study compared with no previous stimulant therapy. Drug holidays did not significantly affect growth. CONCLUSIONS: The effects of prolonged OROS MPH therapy on growth were clinically insignificant and limited to slight decreases in weight during the first months of therapy. Drug holidays did not reduce any impact on growth and are thus of questionable utility for limiting potential effects of treatment on growth.

Multisite controlled study of OROS methylphenidate in the treatment of adolescents with attention-deficit/hyperactivity disorder.

BACKGROUND: Despite the persistence of attention-deficit/hyperactivity disorder (ADHD) into adolescence, little is known about the efficacy and tolerability of stimulant medications in this age group. OBJECTIVE: To report the results of a multisite controlled study among adolescents with ADHD evaluating the efficacy and tolerability of osmotic-release oral system (OROS) methylphenidate. DESIGN: Adolescents (N = 220) having a confirmed Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition diagnosis of ADHD underwent dose titration to identify dosages of OROS methylphenidate that improved symptoms to predefined criteria. Subjects successfully completing the dose titration phase (n = 177) (ie, tolerated and responded to treatment and adhered to the protocol) were randomized to receive 2 weeks' treatment with their individualized dosage of OROS methylphenidate (18, 36, 54, or 72 mg once daily) or placebo. Treatment effectiveness was measured using investigator, parent, and adolescent assessments of ADHD. RESULTS: A significant reduction from baseline in the investigator-rated ADHD Rating Scale, the primary efficacy measure, was found with OROS methylphenidate treatment compared with placebo. Similar findings were noted with parent- and adolescent-report measures. Based on a Clinical Global Impression improvement subscale score of much or very much improved, 52% of subjects in the OROS methylphenidate group improved compared with 31% receiving placebo. Thirty-seven percent of subjects required the maximum dosage of 72 mg/d. The incidence of drug-related adverse events was similar between the 2 study groups. CONCLUSION: In adolescents, once-daily OROS methylphenidate significantly reduced ADHD symptoms and was well tolerated using dosages up to 72 mg/d.