Saltar al contenido
Dispositivos y mediciónArtículo de investigación3 min read

Wearable data flagged children's ADHD and sleep problems, but with many false alarms

Colectivo editorial MoveVitals · Study published · Reading updated

Original paper:Machine Learning-Based Prediction of Attention-Deficit/Hyperactivity Disorder and Sleep Problems With Wearable Data in Children. · JAMA network open · 2023 · Artículo original ↗

Idea principal

Machine learning models using 21 days of wearable data from children in the Adolescent Brain Cognitive Development (ABCD) study separated children with ADHD from controls with an AUC of 0.798, and those with sleep problems with an AUC of 0.737. Positive predictive values were low (0.159 for ADHD, 0.036 for sleep problems), so most children flagged would not have the condition.

Study design

Artículo de investigación

Reading basis

Published abstract

Reading focus

Design & applicability

Esta explicación editorial está disponible en inglés, chino simplificado y chino tradicional. Esta interfaz muestra la lectura en inglés.

Pregunta de investigación

Early detection of ADHD and sleep problems matters for children's mental health, but interview-based diagnosis has drawbacks. The authors tested whether circadian-rhythm features from wearable data could predict ADHD and sleep problems diagnosed with a structured interview.

Población y método

Diagnostic study using the ABCD study (release 3.0, 21 US sites). Screening data from 6571 patients and 21 days of wearable data from 5725 patients at the 2-year follow-up were used, with circadian-rhythm-based features generated per participant. Diagnoses came from the Kiddie Schedule for Affective Disorders and Schizophrenia (K-SADS) for DSM-5. Models were evaluated by area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV), and Shapley Additive Explanations values ranked feature importance.

Resultados

The authors’ reported results. Read each estimate with its population and uncertainty.

  1. 1
    For ADHD (79 children vs 1011 controls), AUC was 0.798, sensitivity 0.756, specificity 0.716, PPV 0.159 and NPV 0.976.
  2. 2
    For sleep problems (68 children vs 3346 controls), AUC was 0.737, sensitivity 0.743, specificity 0.632, PPV 0.036 and NPV 0.992.
  3. 3
    The very low PPVs mean that most children who test positive would not have the condition, while the high NPVs mean a negative result is usually right. This is expected when the conditions are uncommon in the sample.

Límites e incertidumbre

  1. 1
    Only 79 children with ADHD and 68 with sleep problems were in the final analysis, so performance estimates may be unstable.
  2. 2
    The abstract does not say whether the models were tested on children from outside the dataset, so real-world accuracy is unknown.
  3. 3
    Children were about 12 years old and from the US ABCD sample, so results may not apply to younger children or other populations.
  4. 4
    The models predict an interview-based diagnosis and are a screening idea, not a diagnosis, as the authors note that follow-up studies could improve performance.
  5. 5
    This reading is based on the abstract only.

Relevancia práctica

This is early research on whether wrist-worn data could someday help flag children for further assessment. It is not a tool to decide whether your child has ADHD or a sleep disorder. Concerns about a child's attention or sleep should go to a paediatrician or other clinician.

Tus datos

Sleep timing and regularity from a wearable, which relate to circadian rhythm, are the kinds of data used here. If you track a child's sleep, use the same device and compare weeks of data rather than single nights, and bring any persistent concern to a clinician rather than relying on an app.

Cómo interpretar la evidencia

The index does not establish a precise design. Read the methods before making causal claims; check population, comparator, outcomes and uncertainty in the source.

Resumen estructurado de los autores English

El resumen original en inglés se reproduce con atribución bajo la licencia indicada. Es una fuente, no una interpretación de MoveVitals. El análisis preparado figura arriba; verifica los resultados importantes en la fuente.

Importance

Early detection of attention-deficit/hyperactivity disorder (ADHD) and sleep problems is paramount for children's mental health. Interview-based diagnostic approaches have drawbacks, necessitating the development of an evaluation method that uses digital phenotypes in daily life.

Objective

To evaluate the predictive performance of machine learning (ML) models by setting the data obtained from personal digital devices comprising training features (ie, wearable data) and diagnostic results of ADHD and sleep problems by the Kiddie Schedule for Affective Disorders and Schizophrenia Present and Lifetime Version for Diagnostic and Statistical Manual of Mental Disorders, 5th edition (K-SADS) as a prediction class from the Adolescent Brain Cognitive Development (ABCD) study.

Design, setting, and participants

In this diagnostic study, wearable data and K-SADS data were collected at 21 sites in the US in the ABCD study (release 3.0, November 2, 2020, analyzed October 11, 2021). Screening data from 6571 patients and 21 days of wearable data from 5725 patients collected at the 2-year follow-up were used, and circadian rhythm-based features were generated for each participant. A total of 12 348 wearable data for ADHD and 39 160 for sleep problems were merged for developing ML models.

Main outcomes and measures

The average performance of the ML models was measured using an area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). In addition, the Shapley Additive Explanations value was used to calculate the importance of features.

Results

The final population consisted of 79 children with ADHD problems (mean [SD] age, 144.5 [8.1] months; 55 [69.6%] males) vs 1011 controls and 68 with sleep problems (mean [SD] age, 143.5 [7.5] months; 38 [55.9%] males) vs 3346 controls. The ML models showed reasonable predictive performance for ADHD (AUC, 0.798; sensitivity, 0.756; specificity, 0.716; PPV, 0.159; and NPV, 0.976) and sleep problems (AUC, 0.737; sensitivity, 0.743; specificity, 0.632; PPV, 0.036; and NPV, 0.992).

Conclusions and relevance

In this diagnostic study, an ML method for early detection or screening using digital phenotypes in children's daily lives was developed. The results support facilitating early detection in children; however, additional follow-up studies can improve its performance.

Fuentes y atribución

Machine Learning-Based Prediction of Attention-Deficit/Hyperactivity Disorder and Sleep Problems With Wearable Data in Children.

Kim WP, Kim HJ, Pack SP, Lim JH, Cho CH, Lee HJ.

JAMA network open · 2023-03-01

DOI: 10.1001/jamanetworkopen.2023.3502 ↗PubMed · 36930149 ↗Europe PMC · Licencia registrada: cc by ↗

Abstract © the original authors, reproduced under the recorded open licence. Translations support reading; use the English record to check terminology and numerical results. Our methodological interpretation is separate from the authors’ conclusions.

Interpretación editorial de MoveVitals · contenido educativo · sin revisión clínica individual registrada

Fuentes verificadas 2026-11-01

Guías prácticas

Leer en contexto

·Estudio de cohorte

Activity–stroke and heart attack curves differ by accelerometer processing method

Among 90,237 UK Biobank adults free of cardiovascular disease at baseline, followed until December 2022 for 1,298 strokes and 2,031 myocardial infarctions, the shape of the link between moderate-vigorous physical activity (MVPA) and each outcome depended on how the accelerometer data were processed. For stroke, hazard fell in a straight line only with the machine-learning metric; for myocardial infarction, two metrics gave a curved decline and activity counts a straight one. The abstract gives no hazard ratios, so it shows that methods disagree, not which one is right, and the findings are observational associations.

Preventive Medicine

Explicaciones detalladasLeer estudio →
·Estudio/revisión de validación

Smartwatch data as forensic evidence: heart rate is best validated, the rest uneven

A systematic review and meta-analysis of studies on smartwatches from four major brands, framed around digital forensics, found that heart rate was both the most studied and the most accurate measure. Step count, distance, energy expenditure, activity classification and sleep were less consistently validated, and results varied by brand, protocol and reporting. The abstract gives no pooled numbers, and most studies were run in healthy people in laboratories, so it cannot say how a particular watch performs for a particular person in daily life.

Forensic Science International

Explicaciones detalladasLeer estudio →
·Revisión de revisiones

Activity trackers: about 1,800 more steps a day, but small effects on other outcomes

An umbrella review of 39 systematic reviews and meta-analyses, covering 163,992 participants, found that activity trackers were associated with more physical activity (SMD 0.3–0.6), equating to about 1,800 extra steps and 40 minutes more walking per day, and with a bodyweight reduction of about 1 kg. Effects on blood pressure, cholesterol, glycosylated haemoglobin, quality of life and pain were typically small and often non-significant. The abstract does not say what else came with the trackers in these programs or how much the reviews overlap, so the gains cannot be credited to the device alone.

The Lancet Digital Health

Explicaciones detalladasLeer estudio →
·Estudio/revisión de validación

Seven sleep trackers: good at spotting sleep, weak on wake and sleep stages

In a sleep laboratory, 34 healthy young adults wore a subset of seven consumer sleep trackers for three nights. Against polysomnography every device detected sleep very well (sensitivity 0.93 or higher) but caught wake poorly (specificity 0.18–0.54), and five of the seven matched or beat research actigraphy (specificity 0.39). Sleep-stage estimates were inconsistent, and the participants were healthy adults aged 18 to 35 in a fixed 8-hour bed window, with each device tested in only 11 to 20 of them, so the results say little about people with sleep problems.

Sleep

Explicaciones detalladasLeer estudio →
Dispositivos y medición →