In recent years, computer science has made major advances in understanding drawing behavior. Artificial intelligence, and more precisely deep learning, has displayed unprecedented performance in the automatic recognition and classification of large databases of sketches and drawings collected through touchpad devices. Although deep learning can perform these tasks with high accuracy, the way they are performed by the algorithms remains largely unexplored. Improving the interpretability of deep neural networks is a very active research area, with promising recent advances in understanding human cognition. Deep learning thus offers a powerful framework to study drawing behavior and the underlying cognitive processes, particularly in children and non-human animals, on whom knowledge is incomplete. In this literature review, we first explore the history of deep learning as applied to the study of drawing along with the main discoveries in this area, while proposing open challenges. Second, multiple ideas are discussed to understand the inherent structure of deep learning models. A non-exhaustive list of drawing datasets relevant to deep learning approaches is further provided. Finally, the potential benefits of coupling deep learning with comparative cultural analyses are discussed.

A small but significant number of children and adolescents with cancer experience severe physical and psychological distress. Previous studies have shown that drawing therapy positively affects relieving psychological problems. However, the effect of drawing therapy on pediatric oncology patients has not been established by systematic review.

The aim of this study was to determine the effect of drawing therapy on the pediatric oncology population.

PubMed, EMBASE, MEDLINE, Cochrane, PsycINFO, CINAHL, and Chinese databases including CNKI, Wanfang, VIP, and CBM were searched. Studies published in the English and Chinese languages up to December 2019 were screened, and randomized controlled trials and nonrandomized experimental studies of drawing therapy interventions for pediatric oncology patients were reviewed. Screening was undertaken independently by 2 reviewers. The review protocol was registered with PROSPERO (registration number: CRD42020178365).

Eight studies were included. Three studies were randomized controlled trials, and 5 studies were nonrandomized experimental studies. Seven studies showed that drawing therapy had positive effects on reducing depression and anxiety and improving quality of life. However, 1 study showed a contradictory result, that is, participants had an increased anxiety level after intervention.

Drawing therapy is effective in improving negative emotions, relieving somatic symptoms, and increasing social communication for pediatric oncology patients.

Drawing therapy may be considered an adjuvant psychological intervention strategy for pediatric oncology patients. Meanwhile, more rigorous studies are needed to address the deficiencies of small number size and methodological weakness.

To investigate psychopathological correlates of child obesity via the Draw-A-Person test (DAP).

The participants were 50 children with a mean age of 9.74 years. Body mass index (BMI) was used as a measure of body fat. Children were divided into normal (n = 17), overweight (n = 14) and obese (n = 19). Two qualitative methods of scoring the DAP based on an integrative approach were used to assess self-concept (ESW) and overall level of children's adjustment (EAC). A procedure for judging interpretative skills of clinicians was implemented before they evaluated children's drawings.

As predicted by our hypothesis, BMI was negatively correlated with ESW, r (50) = -0.29, P < 0.05, but not with EAC, r (50) = - 0.08, P = ns. To evaluate the effect of gender, Pearson correlations were re-computed regrouping the sample accordingly: BMI and EAC reached a significant negative correlation in female subjects, r (24) = -0.36, P < 0.05, and a positive correlation in male subjects, r (26) = 0.37, P = < 0.05; negative correlation between BMI and ESW became stronger in females, r (24) = -0.51, P < 0.01 but not in males, whose correlation disappeared resulting not-significant, r (26) = -0.06, P = ns. No effect of age was found. Results indicate that obesity has a negative correlation exclusively on overall adjustment and self-concept in female children.

It was concluded that there is a negative bias toward females that reveals how the stigma of obesity is widespread in Western society.

Our aim was to test the hypothesis that emotional withdrawal is an early indicator of affective disorder in infants heavily exposed prenatally to alcohol, which is independent of alcohol-related effects on mother-infant interaction and temperament and discriminated between children later diagnosed with fetal alcohol syndrome (FAS) and partial FAS (PFAS) and predicted cognitive and affective outcomes at 5 and 9 years.

The sample consisted of Cape Coloured (mixed ancestry) infants, whose mothers were interviewed during pregnancy regarding their alcohol consumption using a timeline follow-back approach. Infant emotional withdrawal (n = 85) was assessed on the Alarm Distress Baby Scale at 6.5 months. Mother-infant interaction was evaluated from video recordings during free play and infant feeding at 6.5 months (n = 127). Infant temperament was assessed by maternal report on the EAS Temperament Survey at 13 months (n = 119). Sociodemographic and psychological correlates of maternal alcohol use and infant iron deficiency were examined as potential confounders. The children were diagnosed for FAS/PFAS by expert dysmorphologists at 5 years, cognitive and affective function at 5 and 9 years.

Prenatal alcohol exposure was associated with increased infant emotional withdrawal and decreased activity, but unrelated to mother-infant interaction or any other temperament measures. Children later diagnosed with FAS and PFAS at 5 years exhibited more emotional withdrawal and less responsivity and activity as infants. Infant withdrawal, responsivity, quality of interaction, and maternal sensitivity also predicted poorer IQ and affective response at 5 and 9 years. When all 4 infant affective measures were examined simultaneously in a regression analysis, only infant emotional withdrawal persisted as a significant predictor of 9-year IQ.

This study is the first to document a direct effect of fetal alcohol exposure on emotional withdrawal in infancy. These data link prenatal alcohol to a specific aspect of infant affective function not attributable to mother-infant interaction, infant temperament, or other socioemotional aspects of the infant's environment and identify infant emotional withdrawal as an early indicator of affective disturbance, particularly in children later diagnosed with FAS and PFAS.

This exploratory study examined the discriminant validity of 10 human-figure features commonly used by many proponents of the draw-a-person (DAP) projective technique as evidence of childhood sexual abuse. Two exploratory features were also examined.

Rather than drawing human figures, 64 children (M = 8 years, 9 months), including 19 sexually abused children, 26 nonsexually abused but emotionally/behaviourally troubled children, and 19 nonabused, nonclinical children, were instructed to build male and female figures using groups of prefabricated pieces of human-figure body parts. Unbeknownst to the children, each group of parts contained a potential sexual abuse feature (or features).

None of the human-figure features under examination, either individually, or in combination, distinguished the sexually abused group from the other two groups of children.

In accordance with years worth of DAP projective technique research, no support for the validity of the human-figure features under examination as evidence of childhood sexual abuse, was found.

The authors examined aspects of reliability and validity of the Goodenough-Harris Draw-A-Person Test (DAP; D. B. Harris, 1963). The participants were 115 seven- to nine-year-old students attending regular or special education schools. Three judges, with a modest degree of training similar to that found among practicing clinicians, rated the students' human figure drawings on developmental and personality variables. The authors found that counting details and determining developmental level in the DAP test could be carried out reliably by judges with limited experience. However, the reliability of judgments of children's social and emotional development and personality was insufficient. Older students and students attending regular schools received significantly higher scores than did younger students or students attending special education schools. The authors found that the success of the DAP test as an indicator of cognitive level, socioemotional development, and personality is limited when global judgments are used. The authors concluded that more specific, reliable, valid, and useful scoring systems are needed for the DAP test.

Relatively few studies have predicted adolescent or adult delinquency from childhood Rorschach data. Incremental validity of Rorschach measures over other known consistent and more easily obtained predictors has typically not been investigated. We addressed Rorschach data's incremental validity over mother's reports of externalizing behavior and mother-child relations for predicting officially registered adolescent and adult delinquency in a longitudinal study of 122 Swedish men. The Rorschach measures we used were aggregates of blind, prospectively performed, global expert ratings based on a holistic evaluation of protocols. An aggregate of Rorschach-based ratings of ego strength significantly improved the prediction of delinquency in adolescence and adulthood over and above earlier identified best predictors (mother's ratings of mother-child relations and externalizing problem behavior).

This validity study examined the extent to which the Draw-A-Person: Screening Procedure for Emotional Disturbance (DAP:SPED; J. A. Naglieri, T. J. McNeish, & A. N. Bardos, 1991) was a significant predictor of behavioral functioning within a clinical sample of 68 latency-age children (6-12 years old) receiving counseling services at outpatient and residential treatment facilities. Study results showed that the total DAP:SPED (man, woman, and self scores summed) was a significant predictor in explaining variation in internalizing behavioral disturbance. Specifically, the DAP:SPED remained a moderate strength predictor of internalizing behavioral disturbance after controlling for the Child and Adolescent Adjustment Profile parent-report behavioral measure. Findings lend preliminary support to the DAP:SPED's validity in providing assessment information about child behavioral functioning. Continued validation investigation along these lines is recommended.

We investigated the hypothesis that certain signs in the Draw-A-Person projective technique reflect male homosexuality. Human figure drawings from gay and 88 heterosexual men, with no clinical psychological symptoms, were submitted to trained raters who were blind to the purpose of this research. The raters independently judged whether 21 signs, previously referenced in the literature as suggestive of male homosexuality, were present in the figure drawings. Only two signs, hair and hips, differentiated between groups. Results were interpreted in the light of changing social attitudes towards homosexuals and methodological problems of prior studies.

In recent years, there has been debate about the validity of figure drawings, although surveys of clinicians in both general and forensic practice still find them to be one of the most widely used tests of personality functioning. Using both Heilbrun's (1992) guidelines for the use of psychological tests in a forensic evaluation and the U.S. Supreme Court's Daubert v. Merrell Dow Pharmaceuticals, Inc. (1993) criteria for the admission of scientific evidence, I examine the admissibility of human figure drawings in court. The results suggest that the most commonly used methods for interpreting human figure drawings fall short of meeting the standards for admissibility. The use of overall rating scales, although weak in validity, appear to minimally meet these standards.

To evaluate the reliability of using certain indicators derived from human figure drawings to distinguish between suicidal and nonsuicidal adolescents.

Ninety consecutive admissions to an adolescent inpatient unit were assessed. Thirty-nine patients were admitted because of suicidal behavior and 51 for other reasons. All subjects were given the Human Figure Drawing (HFD) test. HFD was evaluated according to the method of Pfeffer and Richman, and the degree of suicidal behavior was rated by the Child Suicide Potential Scale.

The internal reliability was satisfactory. HFD indicators correlated significantly with quantitative measures of suicidal behavior; of these indicators specifically, overall impression of the evaluator enabled the prediction of suicidal behavior and the distinction between suicidal and nonsuicidal inpatients (p < .001). A group of graphic indicators derived from a discriminant analysis formed a function, which was able to identify 84.6% of the suicidal and 76.6% of the nonsuicidal adolescents correctly. Many of the items had a regressive quality.

The HFD is an example of a simple projective test that may have empirical reliability. It may be useful for the assessment of severe suicidal behavior in adolescents.