Heterogeneity of executive function revealed by a functional random forest approach across ADHD and ASD

May combine two claims.

ISG-Mild demonstrated better performance on tasks involved in response inhibition (stop task accuracy) and working memory (digit span backwards).

“ISG-Mild also demonstrated better performance on tasks involved in response inhibition (stop task accuracy) and working memory (digit span backwards).”

May combine two claims.

Some imaging results appeared to follow a severity trend (ISG-Severe decreased connectivity compared to ISG-Mild, which is decreased compared to TD).

“Some of the imaging results appeared to follow a severity trend (i.e. ISG-Severe showing decreased connectivity between identified regions compared to ISG-Mild, which is decreased compared to TD.)”

May combine two claims.

There were no significant differences between inattentive subgroups on diagnostic composition of ASD and ADHD participants, gender, age, or estimated IQ.

“There were no significant differences between the subgroups on diagnostic composition of ASD and ADHD participants per subgroup, gender, age, or estimated IQ (see Table 7.)”

May combine two claims.

Of the comorbidities, 33 with ADHD (50%), 3 with ASD-ADHD (33%), 5 with ASD+subADHD (26%), and 17 ASD+ADHD (50%) moved from a Mild to Severe (or vice versa) subgroup across the models.

“Of the comorbidities, 33 with ADHD (50%), 3 with ASD-ADHD (33%), 5 with ASD+subADHD (26%), and 17 ASD+ADHD (50%) moved from a Mild to Severe (or vice versa) subgroup across the models.”

May combine two claims.

There were no significant differences between the Hyperactive subgroups on diagnostic composition of ASD and ADHD participants per subgroup, gender, age, or estimated IQ.

“There were no significant differences between the subgroups on diagnostic composition of ASD and ADHD participants per subgroup, gender, age, or estimated IQ (see Table 4.)”

May combine two claims.

All 43 EF variables helped identify the unique profiles among participants, with different combinations informing subgroups for each model.

“All 43 EF variables helped identify the unique profiles among participants, with different combinations informing subgroups for each model.”

May combine two claims.

A similar "non-pattern" emerged across networks, with the first three network connections showing severity trends, and the remaining 11 connections having no distinguishable patterns as related to inattentive symptoms and EF impairment.

“A similar “non-pattern” emerged across networks, with the first three network connections on 6b showing severity trends, and the remaining 11 connections having no distinguishable patterns as related to inattentive symptoms and EF impairment.”

May combine two claims.

The TD group showed significantly greater connectivity between CiP and ReT networks compared to HSG-Mild, and HSG-Mild was significantly greater than HSG-Severe.

“although the TD group showed significantly greater connectivity between the cingulo-opercular parietal (CiP) and retrosplenial (ReT) (Figs. 1, 5a) networks as compared to HSG-Mild, and HSG-Mild was significantly greater than HSG-Severe”

May combine two claims.

The authors' findings showed significant differences among subgroups both within and between multiple functional brain networks, but no discernably consistent trend.

“Our findings showed just that: there were significant differences among subgroups both within and between multiple functional brain networks, but no discernably consistent trend.”

May combine two claims.

The two Severe and two Mild subgroups were comprised of different combinations of participants; the subject composition of HSG-Severe did not simply duplicate the subject composition of ISG-Severe.

“when we compare HSG-Severe to ISG-Severe and HSG-Mild to ISG-Mild, we find that the two Severe and two Mild subgroups were comprised of different combinations of participants: although all 130 participants were included in each model, the subject composition of HSG-Severe did not simply duplicate the subject composition of ISG-Severe.”

May combine two claims.

The hyperactive subgroups differed significantly on measures related to multiple cognitive domains, with HSG-Mild showing improved performance across multiple measures of EF as compared to HSG-Severe.

“The hyperactive subgroups differed significantly on measures related to multiple cognitive domains– with HSG-Mild showing improved performance across multiple measures of EF as compared to HSG-Severe.”

May combine two claims.

The inattentive subgroups showed significant differences on multiple measures of EF, with ISG-Mild out-performing/showing better ratings than ISG-Severe across tasks.

“The inattentive subgroups showed significant differences on multiple measures of EF, with ISG-Mild out-performing/showing better ratings than ISG-Severe across tasks.”

May combine two claims.

If behavioral differences were influenced by the presence of ASD, subgroup splitting based on ASD criteria would be expected, but no such splitting was observed.

“Still, if the behavioral differences were influenced by the presence of ASD, we would expect to see subgroup splitting based on this criteria, which we did not.”

Probably not a substantial claim: may not pass S3 (load-bearing).

Inattentive symptoms are significantly associated with EF deficits in metacognition for those with ASD+ADHD.

“Inattentive symptoms were also significantly associated with EF deficits in metacognition for those with ASD+ADHD indicating that metacognitive EF may be linked to inattention for those with ASD+ADHD (Berenguer et al., 2018).”

• cites Berenguer et al., 2018 sourceNot checked yet

  Not checked in the free run.

Classified as probably not a substantial claim. May combine two claims.

Although EF are associated with ADHD, effect sizes are moderate and findings are not universal per affected individual.

“A meta-analysis indicated that although EF were associated with ADHD, effect sizes were moderate and findings were not universal per effected individual (Willcutt et al., 2005).”

• cites Willcutt et al., 2005 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

Different mechanisms may contribute to the same symptom degree/severity, necessitating modeling approaches suited to address it.

“Different mechanisms may contribute to the same symptom degree/severity, necessitating modeling approaches suited to address it.”

Probably not a substantial claim: may not pass S3 (load-bearing).

EF tasks can discriminate those with ADHD and typically developing adolescents.

“EF tasks can also discriminate those with ADHD (i.e., a defined increase of hyperactive/inattentive symptoms) and typically developing (TD) adolescents (Holmes et al., 2010).”

• cites Holmes et al., 2010 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

Heritability of ASD and ADHD appears to overlap, with parents with ADHD having elevated rates of ASD offspring and siblings cross-aggregating within ADHD and ASD.

“Moreover, heritability of ASD and ADHD appears to overlap; for example, parents with ADHD have elevated rates of ASD offspring compared to parents without ADHD (Musser et al., 2014) and siblings cross aggregate within ADHD and ASD (Miller et al., 2019).”

• cites Musser et al., 2014 sourceNot checked yet

  Not checked in the free run.

• cites Miller et al., 2019Not checked yet

  Not checked in the free run.

Classified as probably not a substantial claim.

A set of potentially shared mechanisms across ADHD and ASD instantiate atypical executive functioning (EF).

“A set of potentially shared mechanisms across ADHD and ASD instantiate atypical executive functioning (EF) (Karalunas et al., 2018).”

• cites Karalunas et al., 2018 sourceNot checked yet

  Not checked in the free run.

May combine two claims.

EF are not a sole nor sufficient explanation for elevated hyperactive/inattentive symptoms.

“It is increasingly recognized that EF are not a sole nor sufficient explanation for elevated hyperactive/inattentive symptoms (Nigg, 2006)”

• cites Nigg, 2006 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

ASD is a neurodevelopmental population in which symptoms of hyperactivity and inattention are recognized as a substantial problem in DSM-5.

“ASD is a second neurodevelopmental population in which symptoms of hyperactivity and inattention are now recognized as a substantial problem in the DSM-5 (American Psychiatric Association, 2013).”

• cites American Psychiatric Association, 2013Not checked yet

  Not checked in the free run.

Classified as probably not a substantial claim. May combine two claims.

Adolescents with ADHD, ASD, and learning deficits cluster into unique cognitive profiles that do not map onto diagnostic categories.

“Importantly, while the first group consisted of mostly participants diagnosed with ADHD, all three groups contained children from each of the three diagnostic categories.”

• cites Bathelt et al., 2018 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

EF has been commonly associated with hyperactive and inattentive symptoms.

“EF has been commonly associated with hyperactive and inattentive symptoms (Silverstein et al., 2018; Willcutt, Doyle, Nigg, Faraone, & Pennington, 2005)”

• cites Silverstein et al., 2018Not checked yet

  Not checked in the free run.

• cites Willcutt et al., 2005 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

Adolescents with ASD and comorbid ADHD represent approximately 28 to 50% of all ASD cases.

“Best estimates across studies utilizing clinical, in-lab, and national samples report that adolescents with ASD and comorbid ADHD (ASD+ADHD) broadly represent anywhere from ~28 to 50% of all ASD cases (Matson & Burns, 2019).”

• cites Matson & Burns, 2019Not checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

A community detection approach combined with support vector machines identified three transdiagnostic subtypes of EF across ASD, ADHD, and TD participants.

“In doing so, they found three transdiagnostic subtypes with specific relevance to the engagement of different brain regions involved in EF.”

• cites Vaidya et al., 2020 sourceNot checked yet

  Not checked in the free run.

Classified as probably not a substantial claim.

It is unclear which EF deficits persist among those with ASD and/or ADHD in light of, or in the absence of, hyperactive/inattentive symptoms.

“Overall, it is unclear which EF deficits persist among those with ASD and/or ADHD in light of, or in the absence of, hyperactive/inattentive symptoms.”

Classified as probably not a substantial claim.

Several components of EF have been linked to hyperactive and/or inattentive symptom domains for those with ASD and/or ADHD.

“As well, several components of EF have been linked to hyperactive and/or inattentive symptom domains for those with ASD and/or ADHD (Sinzig et al., 2008).”

• cites Sinzig et al., 2008 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

The severity of EF impairments is linked to an increased number of ADHD symptoms for adolescents with either ADHD or ASD.

“the severity of EF impairments has also been linked to an increased number of ADHD symptoms for adolescents with either ADHD or ASD (Semrud-Clikeman et al., 2010).”

• cites Semrud-Clikeman et al., 2010 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

Hyperactivity-impulsivity and inattention-disorganization comprise two partially separable symptom domains with distinct validation in factor structure, clinical correlates, and neurobiology.

“Although they co-occur sufficiently often to be clustered in the syndrome of Attention-deficit Hyperactivity disorder (ADHD), hyperactivity-impulsivity and inattention-disorganization comprise two partially separable symptom domains with distinct validation in regard to factor structure, clinical correlates, and neurobiology (Willcutt et al., 2012).”

• cites Willcutt et al., 2012 sourceNot checked yet

  Not checked in the free run.

Classified as probably not a substantial claim. May combine two claims.

Variability in the relationship between EF and ASD has been demonstrated, but whether this is due to comorbid ASD+ADHD remains unclear.

“This variability in the relationship between EF and ASD has also been demonstrated, but whether this is due to comorbid ASD+ADHD remains unclear (Karalunas et al., 2018).”

• cites Karalunas et al., 2018 sourceNot checked yet

  Not checked in the free run.

May combine two claims.

There may be more than one sole cause of any given phenotype, and such causes may be shared and distinct both between and within the disorders.

“These results indicate that while ASD and ADHD share some etiological basis, there may be more than one sole “cause” of any given phenotype (Musser et al., 2014; Reiersen & Todd, 2008) and such causes may also be shared and distinct, both between and within the disorders (Karalunas et al., 2018; Rommelse et al., 2017; Vaidya et al., 2020).”

• cites Karalunas et al., 2018 sourceNot checked yet

  Not checked in the free run.

• cites Rommelse et al., 2017 sourceNot checked yet

  Not checked in the free run.

• cites Vaidya et al., 2020 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

The study examined the age difference and potential relationship to EF variables to address possible batch effect due to participant age differences.

“Because of this, we further examined the age difference and potential relationship to the EF variables (see: Supplemental Materials, 2. Supplemental Analyses).”

Classified as probably not a substantial claim. May combine two claims.

In previous work, the FRF approach distinguished ASD and TD participants with 72.7% accuracy across groups using multiple measures of affect processing, and identified subgroups.

“In previous work, our group employed this FRF approach to distinguish ASD and TD participants with 72.7% accuracy across groups using multiple measures of affect processing, as well as identify subgroups (Feczko et al., 2018).”

• cites Feczko et al., 2018 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

Participants were demographically matched to ASD and ADHD participants with useable scan data.

“These participants were demographically matched to ASD and ADHD participants with useable scan data (see: 2.4 fMRI data, below, and Table 2 for demographic comparisons.”

Probably not a substantial claim: may not pass S3 (load-bearing).

fMRI data were processed using a modified version of the Human Connectome Project image processing pipeline.

“All of the data were processed using a modified version of the Human Connectome Project (HCP) image processing pipeline (Glasser et al., 2013; Mills et al., 2018).”

• cites Glasser et al., 2013Not checked yet

  Not checked in the free run.

• cites Mills et al., 2018Not checked yet

  Not checked in the free run.

May combine two claims.

In this study, the subgroups did not split by primary diagnosis, indicating that features of EF may be shared transdiagnostically.

“In our study the subgroups did not split by primary diagnosis, indicating that features of EF may be shared transdiagnostically.”

Classified as probably not a substantial claim.

FDR correction was used to control for multiple comparisons.

“FDR correction is used to control for multiple comparisons.”

Classified as probably not a substantial claim.

In the Hyperactive model, 38 participants from HSG-Mild and 29 from HSG-Severe met the requirements for analyzable imaging data and were included along with matched TD group (n=28).

“In the Hyperactive model, 38 participants from HSG-Mild (ASD = 16, ADHD = 22) and 29 from HSG-Severe (ASD = 10, ADHD = 19) met the requirements for analyzable imaging data (see 2.4 fMRI data and Supplemental Materials 1.5.2 fMRI data processing and 1.5.3 Quality control) and were subsequently included in the analysis along with the matched TD group (n = 28).”

May combine two claims.

The authors' subtypes complement the profiles found in Vaidya et al. (2020), who found EF and symptom subtypes whereas the authors found EF subtypes tied to hyperactive/inattentive symptoms.

“For example, our subtypes compliment the profiles found in a recent study (Vaidya et al., 2020); they found EF and symptom subtypes whereas we found EF subtypes tied to hyperactive/inattentive symptoms.”

• cites Vaidya et al., 2020 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

Research reliable K-SADS interviews were completed with parents by trained clinicians.

“Research reliable Kiddie-Schedule of Affective Disorders and Schizophrenia (K-SADS) (Kaufman et al., 1997) interviews were completed with the parents by trained clinicians.”

• cites Kaufman et al., 1997 sourceNot checked yet

  Not checked in the free run.

Classified as probably not a substantial claim.

In the Inattentive model, 47 participants from ISG-Severe and 20 from ISG-Mild were determined to have enough good imaging data and were analyzed along with the comparison TD group.

“In the Inattentive model, 47 participants from ISG-Severe (ASD = 17, ADHD = 30) and 20 from ISG-Mild (ASD = 9, ADHD = 11) were determined to have enough good imaging data and were analyzed along with the comparison TD group.”

Probably not a substantial claim: may not pass S3 (load-bearing).

The current study builds on recent studies that have employed transdiagnostic approaches.

“Indeed the current study builds on a handful of recent studies that have employed transdiagnostic approaches (Dajani et al., 2019; Karalunas et al., 2018; Lecei et al., 2019; Vaidya et al., 2020).”

• cites Dajani et al., 2019Not checked yet

  Not checked in the free run.

• cites Karalunas et al., 2018 sourceNot checked yet

  Not checked in the free run.

• cites Lecei et al., 2019 sourceNot checked yet

  Not checked in the free run.

May combine two claims.

The results support growing evidence that while EF are involved in perceived hyperactive/inattentive symptoms across ASD and ADHD, they are not the sole cause.

“Our results support growing evidence that while EF are involved in perceived hyperactive/inattentive symptoms across ASD and ADHD, they are not the sole cause.”

May combine two claims.

The subgroups cannot simply be measured on a continuum of functional-connectivity and may have unique underpinnings.

“It appears that the subgroups cannot simply be measured on a continuum of functional-connectivity and rather, may have unique underpinnings.”

May combine two claims.

Internal cross-validation and neurobiological correlates using brain imaging were used as validation metrics.

“Here, we conducted internal cross-validation and also looked to neurobiological correlates using brain imaging as an index of validity as suggested in the literature (Filiou & Turck, 2011).”

• cites Filiou & Turck, 2011Not checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

A manual curation process was used to further assess fMRI data quality.

“After processing, we used a manual curation process to further assess the data quality.”

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

The FRF algorithm used 10-fold, 3 repetition cross-validation and compared accuracy distributions from 30 permutation tests against 30 null models with a t-test.

“From there, a random selection of participants and variables excluded from the training data are used to evaluate the overall accuracy of the model using 10-fold, 3 repetition, cross-validation by comparing the accuracy distributions from 30 permutation tests against 30 null models with a t-test (Kohavi, 1995).”

• cites Kohavi, 1995Not checked yet

  Not checked in the free run.

Classified as probably not a substantial claim.

The EF battery was designed to comprehensively assess response inhibition, working memory, task control, and cognitive flexibility.

“The battery was designed to comprehensively assess the aforementioned different domains of EF including response inhibition, working memory, task control, and cognitive flexibility (Friedman & Miyake, 2017; Nigg, 2005; Pennington, 1997; Pennington & Ozonoff, 1996).”

• cites Friedman & Miyake, 2017 sourceNot checked yet

  Not checked in the free run.

• cites Nigg, 2005 sourceNot checked yet

  Not checked in the free run.

• cites Pennington, 1997Not checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

Very few data points were missing: only 0.9% of total data was missing, participants averaged 0.7% missing data each, maximum missing for a single participant was 14%, and only 10% of participants had any missing data.

“Very few data points were missing in our dataset. Of the 43 input variables used in the model for all participants, only .9% of the total data was missing. The participants averaged .7% missing data each, with the maximum amount of missing data for a single participant at 14% and only 10% of participants with any missing data at all.”

Classified as probably not a substantial claim.

These transdiagnostic subtypes had specific relevance to the engagement of different brain regions involved in EF.

“In doing so, they found three transdiagnostic subtypes with specific relevance to the engagement of different brain regions involved in EF.”

• cites Vaidya et al., 2020 sourceNot checked yet

  Not checked in the free run.

Classified as probably not a substantial claim.

In the absence of an independent cohort, independent data within the same participants can be used for validation.

“In the absence of such a cohort, independent data within the same participants can be used.”

Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

While the authors identified two subgroups per model, it is possible that the subgroups can be further differentiated with the inclusion of more participants and data.

“While we identified two subgroups per model, it is possible that the subgroups can be further differentiated with the inclusion of more participants and data.”

• AssumptionRests on an assumption: The FRF requires a larger sample size in order to uncover potentially smaller subgroups.

May combine two claims.

The low and high performing groups identified in the current work are tied to the relevant symptom dimensions, and other outcomes may reveal distinct grouping characteristics.

“In other words the low and high performing groups, identified in the current work, are tied to the relevant symptom dimensions, and other outcomes (e.g, prognosis, response to therapy, etc), may reveal distinct grouping characteristics.”

Probably not a substantial claim: may not pass S3 (load-bearing).

A small body of work dedicated to EF has revealed some information about EF relationships across tasks and within cognitive domains.

“A small body of work dedicated to EF has revealed some information about EF relationships across tasks and within cognitive domains (Friedman & Miyake, 2017).”

• cites Friedman & Miyake, 2017 sourceNot checked yet

  Not checked in the free run.

May combine two claims.

These results demonstrate that despite identification of lower and higher performing groups, such behavioral manifestations are not entirely attributable to a global theme of over- or under-connected functional networks per group, suggesting a more intricate mechanistic interaction.

“These results demonstrate that despite identification of lower (HSG-Severe, ISG-Severe) and higher (HSG-Mild, ISG-Mild) performing groups, such behavioral manifestations are not entirely attributable to a global theme of over- or under-connected functional networks per group, suggesting a more intricate mechanistic interaction.”

Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

This difference in task negative and sensory networks may suggest varying strategies participants engage to manage their attention to internal and external stimuli.

“This difference in task negative and sensory networks may suggest varying strategies participants engage to manage their attention to internal and external stimuli.”

Probably not a substantial claim: may not pass S3 (load-bearing).

In a prior study, the FRF identified 3 ASD and 4 TD subgroups based on measures of EF and facial/vocal affect recognition and processing.

“In that study the model identified 3 ASD and 4 TD subgroups (Feczko et al., 2018) based on measures of EF and facial/vocal affect recognition and processing.”

• cites Feczko et al., 2018 sourceNot checked yet

  Not checked in the free run.

Classified as probably not a substantial claim.

A growing body of evidence suggests multiple pathways lead to shared symptoms among a given disorder.

“A growing body of evidence suggests multiple pathways lead to shared symptoms among a given disorder (Castellanos et al., 2006; Feczko et al., 2019).”

• cites Castellanos et al., 2006 sourceNot checked yet

  Not checked in the free run.

• cites Feczko et al., 2019 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

The findings here are not that dissimilar with other modeling approaches such as latent class analysis that often derive low and high performing groups.

“The findings here are not that dissimilar with other modeling approaches such as latent class analysis that often derive low and high performing groups ( Karalunas et al., 2014, Katuwal et al., 2016).”

• cites Karalunas et al., 2014 sourceNot checked yet

  Not checked in the free run.

• cites Katuwal et al., 2016 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S3 (load-bearing).

The ASD group was significantly older than the ADHD group.

“In the present report, while we aimed to match participants on various demographic phenomenon, the ASD group was significantly older than the ADHD group.”

Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

One strength of the FRF is the ability to parse patterns in data that are difficult to detect with other methods.

“One strength of the FRF is the ability to parse patterns in data that are difficult to detect with other methods.”

May combine two claims.

These findings highlight the potential implications for the SMm+SMh, attentional, and response inhibition networks and their relationship to EF domains such as behavioral regulation and initiation.

“These findings highlight the potential implications for the SMm+SMh, attentional, and response inhibition networks and their relationship to EF domains such as behavioral regulation and initiation, which were shown to be different between groups (Table 6, Fig. 5).”

Probably not a substantial claim: may not pass S3 (load-bearing).

The FRF does not model variable interactions in ways that detect clusters, such as with latent variable analysis.

“Yet it does not model variable interactions in ways that detect clusters, such as with latent variable analysis.”

May combine two claims.

The authors' findings are more akin to a scenario wherein brain networks do not follow along one dimension from high to low connectivity leading to high and low performers; rather, a fundamentally different organization is seen between the high and low performing subgroups.

“Our findings are more akin to the latter scenario wherein brain networks do not follow along one dimension from high to low connectivity (or vice versa) leading to high and low performers; rather, a fundamentally different organization is seen between the high and low performing subgroups.”

May combine two claims.

The difference between the FRF approach and other methods is that the FRF may discover any number of groups or none at all, as demonstrated in prior work.

“The difference between the FRF approach and other methods is that the FRF may discover any number of groups or none at all, as demonstrated in our prior work (Feczko et al., 2018).”

• cites Feczko et al., 2018 sourceNot checked yet

  Not checked in the free run.

May combine two claims.

This supports the transdiagnostic approach and is consistent with previous work indicating that the underlying mechanisms leading to observed symptoms are likely shared across ASD and ADHD, even though there may be more than one.

“This supports the transdiagnostic approach and is consistent with previous work indicating that the underlying mechanisms leading to observed symptoms are likely shared across ASD and ADHD, even though there may be more than one (Chan et al., 2008; Feczko et al., 2019; Leitner, 2014; Molitor et al., 2018).”

• cites Chan et al., 2008 sourceNot checked yet

  Not checked in the free run.

• cites Feczko et al., 2019 sourceNot checked yet

  Not checked in the free run.

• cites Leitner, 2014 sourceNot checked yet

  Not checked in the free run.

Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

It's important for any machine learning model, in particular those using cross-validation, to further validate identified subgroups.

“It's important for any machine learning model, in particular those using cross-validation, to further validate identified subgroups (Feczko et al., 2019).”

• cites Feczko et al., 2019 sourceNot checked yet

  Not checked in the free run.