Attention Deficit/Hyperactivity Disorder (ADHD) is the most common neurobehavioral disorder in children and adolescents. However, its etiology is still unknown, and this hinders the existence of reliable, fast and inexpensive standard diagnostic methods. Objective: This paper proposes an end-to-end methodology for automatic diagnosis of the combined type of ADHD. Methods: Diagnosis is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks to classify spectrograms of activity windows. Results: We achieve up to 97.62% average sensitivity, 99.52% specificity and AUC values over 99%. Overall, our figures overcome those obtained by actigraphy-based methods reported in the literature as well as others based on more expensive (and not so convenient) acquisition methods. Conclusion: These results reinforce the idea that combining deep learning techniques together with actimetry can lead to a robust and efficient system for objective ADHD diagnosis. Significance: Reliance on simple activity measurements leads to an inexpensive and non-invasive objective diagnostic method, which can be easily implemented with daily devices.
4 August 2023 in Artificial Intelligence in Medicine
Attention Deficit/Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder in childhood that often persists into adulthood. Objectively diagnosing ADHD can be challenging due to the reliance on subjective questionnaires in clinical assessment. Fortunately, recent advancements in artificial intelligence (AI) have shown promise in providing objective diagnoses through the analysis of medical images or activity recordings. These AI-based techniques have demonstrated accurate ADHD diagnosis; however, the growing complexity of deep learning models has introduced a lack of interpretability. These models often function as black boxes, unable to offer meaningful insights into the data patterns that characterize ADHD. This paper proposes a methodology to interpret the output of an AI-based diagnosis system for combined ADHD in age and gender-stratified populations. Our system is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks (CNNs) to classify spectrograms of activity windows. These windows are interpreted using occlusion maps to highlight the time-frequency patterns explaining ADHD activity. Significant differences in the frequency patterns between ADHD and controls both in diurnal and nocturnal activity were found for all the populations. Temporal dispersion also presented differences in the male population. The proposed interpretation techniques for CNNs highlighted gender- and age-related differences between ADHD patients and controls. Leveraging these differences could potentially lead to improved diagnostic accuracy, especially if a larger and more balanced dataset is utilized. Our findings pave the way for the development of an AI-based diagnosis system for ADHD that offers interpretability, thereby providing valuable insights into the underlying etiology of the disease.
Rhythm research has had a long tradition in psychiatry, especially in affective disorders. The study of trends in incidence plays a central role in epidemiology and public health. The aims of this research were to describe the socio-demographic and clinical characteristics of persons admitted for psychiatric hospitalization and their trends and periodicity in cases (global and by groups) in Spain over the 11 year study span. We conducted a cross-sectional study of the hospital discharge database of Castilla y León from 2005 to 2015, selecting hospitalizations for psychiatric reasons. Trends in the rates of hospitalization were studied by joinpoint regression analysis. Time series analysis for periodicities was done by spectral analysis, fast Fourier transform, and cosinor analysis. Some 49501 hospitalizations due to psychiatric disorders, out of 2717192 hospital admissions, took place during the study span. Hospitalizations for psychosis were frequent (15949, 32.2%), while such for eating disorders were infrequent, but showed the highest average stay (28 days) and DRG relative weight (2.41). The general trend was a statistically significant 2% annual increase in psychiatric hospitalizations over the 11 year span; substance abuse was the only exception to this trend. The whole population and the subgroups of psychosis and bipolar disorders showed significant circannual (one-year) variation in admissions. The rhythm percentage of the global group was 11.4%, while the rhythm percentages of the psychosis, bipolar, and eating disorders were 17.1%, 17.5%, and 9.6%, respectively (p < .05).
Eating disorders are on top of chronic conditions in children and adolescents, and the most severe cases may require hospitalization. Inpatient psychiatric treatment is one of the most expensive ones and therefore the efforts when treating eating disorders should focus on avoiding and shortening admissions, as well as preventing readmissions. Advances in of eating disorders treatment lie in an accurate knowledge of those patients requiring admission. This study examined the Conjunto Mínimo Básico de Datos—the largest public hospitalization database in Spain—to estimate the prevalence of eating and other psychiatric disorders during childhood and adolescence. It is a cross-sectional study of the hospital discharges in Castilla y León (Spain) from 2005 to 2015, in which patients under 18 years old with a psychiatric diagnosis at discharge were selected. Trends in the rates of hospitalization/1000 hospitalizations per year were studied by joinpoint regression analysis. Conclusions: eating disorders were the only group that presented an upward and continuous trend throughout the study period. This statistically significant increase showed an annual change of 7.8%.
Dementias are brain diseases that affect long-term cognitive and behavioral functions and cause a decrease in the ability to think and remember that is severe enough to disturb daily functioning. In Spain, the number of people suffering from dementia is rising due to population ageing. Reducing admissions, many of them avoidable, would be advantageous for patients and care-providers. Understanding the correlation of admission of people with dementia and its trends in hospitalization would help us to understand the factors leading to admission. We conducted a cross-sectional study of the hospital discharge database of Castilla y León from 2005 to 2015, selecting hospitalizations for dementia. Trends in hospitalizations by year and age quartiles were studied by joinpoint regression analysis. 2807 out of 2,717,192 total hospitalizations (0.10%) were due to dementias; the main groups were degenerative dementia (1907) followed by vascular dementia (607). Dementias are not a major cause of hospitalization, but the average stay and cost are high, and many of them seem avoidable. Decreasing trends were detected in hospitalization rates for all dementias except for the group of mild cognitive impairment, which grew. An increasing–decreasing joinpoint detected in 2007 for vascular dementia and the general downward hospitalization trends for most dementias suggest that socio-health measures established since 2007 in Spain might play a key role in reducing hospitalizations.