Connie Kasari, PhD, details what contemporary research reveals about supporting non-speaking or minimally verbal autistic children. She highlights how far the field has come in the past two decades and emphasizes the need for contemporary research to focus on what strategies benefit whom and why. The speaker discusses JASPER, a modular intervention based on social communication. She outlines recent studies and video examples showing positive language outcomes for JASPER on its own and in tandem with other interventions. Kasari underscores the usefulness of AAC devices in spoken language development, noting the lack of interventions that use even low-tech augmentative supports. The speaker summarizes her presentation and focus for future research before the Q&A.

Handouts are online HERE

In this webinar

2:00 – Early intervention in autism
7:00 – Core challenges: Video
14:16 – Study: JASPER intervention outcomes
26:00 – Intervention trajectories
31:50 – Study: Intervention combinations and AAC
36:11 – Implications for practice
45:45 – AAC case studies
46:45 – Summary
48:00 – Q&A

Early intervention and social communication

Kasari explains that nearly all autistic children will require support/intervention on engagement, imitation, joint attention, and play (2:00). She states that the goal of early intervention is to reduce the number of autistic children who have significant language impairment by the time they start school. Language ability remains one of the strongest predictors of positive long-term outcomes, making support strategies that target social communication skills—such as joint attention, engagement, and play—especially critical (4:00). Importantly, Kasari notes that research hasn’t focused on for whom an intervention works or why a particular intervention provides benefit for certain people. Understanding this is critical to expanding care and assessment across the board (5:30).

The speaker discusses core challenges that may trigger an intervention and shows videos comparing social communication in an autistic and a non-autistic child at 18 months old. Kasari highlights differences between the videos, noting the child with autism is more interested in looking at the objects than communicating (7:00). She explains how this pattern often translates to parent play, making it feel frustrating or not enjoyable for many parents/caregivers, and discusses two video examples of this (9:30).

Social Communication Research

The speaker says we know the least about children who are most delayed in development, who have limited language skills, and those whose families have less access to information about studies in their communities. She explains that most autistic children have never been in a research study. As a result, our evidence base does not represent the entire spectrum of autism (13:15). Kasari and her team focus on researching interventions for non-speaking and minimally verbal autistic children that can be conducted in community settings.

JASPER: Joint Attention, Symbolic Play, Engagement, and Regulation

The presenter describes JASPER, a comprehensive social communication/language intervention that can float inside other interventions, be used on its own or used sequentially (14:60). Kasari presents one of her recent publications comparing outcomes in 164 children, 3 -5 years old, across three sites after four months receiving Discrete Trial Training (DTT) or JASPER (video examples) (19:00). Results from the study show that both groups made significant language gains, and 45% moved toward phrased speech (putting words together).

Intervention trajectories

The goal of the intervention was to avoid the label of minimally verbal or profound autism by school age. Kasari defines profound autism as children with a developmental quotient (DQ) below 50, aged 8 or older, with poor adaptive skills (often minimally verbal or non-speaking). She notes that this is a relatively new term and considers how early we can predict these outcomes (26:00). The speaker reviews DQ data for a group of 264 children at very young ages. By age 8, 47% did not meet criteria for profound autism, although 25% of this group had a DQ lower than 50 at age 4 (28:30).

Kasari summarizes study takeaways, noting that DQ can help predict later development but is not a perfect predictor on its own. She reiterates the importance of early intervention and highlights understanding the 25% who moved off trajectory as a critical next step (29:25).

Combination interventions and assistive technology (AAC)

The presenter reiterates the heterogeneity in response to interventions, underscoring the need to personalize, tailor, and target interventions according to each person. This will also help us address for whom the intervention works and why. Kasari defines adaptive intervention designs as a sequence of decision rules that specify whether, how, when (timing), and based on which measures, to alter the dosage (duration, frequency, or amount), type, or delivery of treatment(s) at decision stages in the course of care – this is what her group employs (29:45).

Kasari details a study with 61 children, 5-8 years old, who are minimally verbal and had received 2 years of intensive early intervention (most ABA). All children received JASPER plus EMT, a spoken language intervention. Half of the children were randomized to receive AAC devices to test if these supports help with spoken language. Children attended two sessions per week, and at the 12-week follow-up, those assessed as slow responders were re-randomized to either add AAC or to up to 3 sessions per week. Outcomes for socially communicative utterances were assessed after another 12 weeks (31:50). Those who used AAC devices from the beginning showed significant increases and also had more novel words and joint attention language. Those with only JASPER and EMT made slow but steady progress. Researchers also found that from entry to midpoint to exit, parent-initiated engagement stayed the same while child-initiated engagement increased (34:15).

Implications for practice

The speaker notes that assistive technology are still not used regularly with children, be it a device, sign language, or another low-tech augmentative device; they are not being used as much as they should (36:11). Kasari returns to the child from the first video and describes how they changed tactics the second day by lowering the play level and adding an AAC device with button-words (video provided) (40:00). She notes that this child entered regular education at age 7, speaking full sentences. He used the AAC for a few years as a transition to spoken language. The presenter describes another case in which a child used AAC to support communication. He made progress over time, eventually asking the therapist to put phrases that he hears in the AAC device so he can listen to them and learn the sounds. In a follow-up video, the child is speaking in full sentences (45:45).

Kasari summarizes her presentation, highlighting that we can improve social communication and language outcomes for delayed autistic children and that these early skills need to be direct targets for support/intervention strategies. She reiterates how research must inform practice and, therefore, focus on answering questions about personalized interventions (how long do we wait, what do we change to?) (46:45) before the Q&A (48:00).

As our knowledge about autism continues to evolve, so does our understanding of its root causes. For many years, professionals blamed “refrigerator parents” and prescribed psychoanalytic therapy. Once the psychogenic theory was debunked, genetic research began to dominate autism science. Today, while we know that genes play a significant role in autism, we are beginning to recognize the critical importance of another factor: the environment (Rimland, 1964).

Currently, questions persist about the relative influence of genetics and environment on autism, with many people still viewing it as a purely genetic condition. However, as research findings mount, a clearer picture is forming. It is apparent that in many if not most cases, the condition arises from a complex interplay between genetic susceptibility and environmental influences (Hallmayer et al., 2011). Research increasingly shows that invisible yet potentially harmful substances can have long-lasting impacts on the fetus before birth and in the early stages of life, highlighting the need for us to take meaningful steps to reduce exposure to these substances—especially during crucial formative months in prenatal and early childhood development.

I believe it is time for the autism field to move beyond the vague use of the word “environment” and begin focusing on specific environmental toxins implicated in autism. Identifying and drawing attention to these toxins will help us to guide public policy, develop targeted interventions, and protect future generations of children.

The interplay of genes and environment

When discussing the causes of autism, it is useful to frame the issue in terms of genetic susceptibility and environmental influences.

Genetic susceptibility helps to explain why many individuals exposed to the same environmental toxin may experience little or no effect, while a small portion develop long-term disabilities. It is likely that there is no specific “autism gene,” but rather, a combination of genetic vulnerabilities that increase susceptibility to certain environmental influences. These vulnerabilities may affect systems such as the immune system, which protects the body from foreign substances, and the metabolic system, which affects the body’s ability to detoxify harmful substances.

Environmental risk factors currently implicated by research

Controlled studies on the effects of human exposure to toxins are of course neither ethical nor feasible, and correlational studies can only suggest an association rather than a cause-and-effect relationship. For example, autism appears to be more common in cities than in rural areas; however, this does not necessarily indicate a causal link, as better access to diagnostic services in cities likely accounts for this pattern.

What adds credibility is that many of these risk factors show a distance or dispersion effect. The closer one is to a source—such as pesticides or particulate matter from vehicle exhaust—the higher the risk of autism (Shelton et al., 2014; Volk et al., 2011). In addition, replication by independent research groups in different regions of the country provides relatively strong evidence supporting a possible causal relationship (Becerra et al., 2013; von Ehrenstein et al., 2019).

Environmental toxins that currently are strongly implicated in autism (see Goines & Ashwood, 2013; Landrigan et al., 2012) include:

Air pollutants: particulate matter, nitrogen dioxide, ozone, carbon monoxide
Pesticides: organophosphates, pyrethroids, permethrin, malathion, avermectin
Metals: lead, lithium, mercury, cadmium, aluminum, chromium, arsenic, manganese
Plastics and industrial chemicals: phthalates, bisphenol A, polychlorinated biphenyls (PCBs)

Patterns emerging from well-documented research

In addition to identifying environmental toxins that can alter fetal and early childhood development, it is important to understand the mechanisms by which they cause harm.

We know that when toxins enter the body, their effects depend on several factors, particularly the ability of the immune and metabolic systems to defend against them. In addition, the level of exposure is critical. This includes both the duration and amount of exposure, as well as the timing. For example, there is evidence suggesting that certain adverse neurological events may occur during the second trimester of pregnancy (Bilder, 2019).

Once toxic agents begin circulating in the body, they can trigger several well-documented biological processes linked to autism. These include brain inflammation (Vargus et al., 2005), oxidative stress (a marker of neuroinflammation; Usui et al., 2023), maternal immune activation (Ayoub, 2025; Usui et al., 2023), and disrupted cellular function. Naviaux (2020) has shown that cellular responses to toxins can initiate what is known as the cell danger response, in which the body enters a defensive state that can impair communication between cells.

Interestingly, emerging research indicates that the effects of particulate matter extend to the gut microbiome (Filardo et al., 2022). Exposure to particulate matter has been associated with disruptions in gut microbial balance that are also reported in autism, including reductions in microbial diversity (Fouladi et al., 2020; Kang et al., 2017). Furthermore, decreases in Bacteroidetes and Lactobacillus—both reported in autism—have also been associated with exposure to particulate matter (Li et al., 2023; Strati et al., 2017; Liu et al., 2021; Mihailovich et al., 2024).

Building on this understanding, a major study published earlier this year identified four distinct subtypes of autism (Litman et al., 2025; see ARRI 2025, Vol. 3). One subgroup, termed “broadly affected,” was characterized by severe delays in reaching developmental milestones such as walking and talking, along with pronounced social-communication challenges and marked restrictive and repetitive behaviors. This subtype closely corresponds to what is often referred to as profound or severe autism (Lord et al., 2024). Notably, autism that arises in the context of maternal immune activation during pregnancy—which can be triggered by toxic exposures or infections—is also frequently described as severe or profound (Ellul et al., 2023).

What is very interesting is that both maternal immune activation profiles and de novo mutations were most prevalent in the “broadly affected” group. De novo mutations are not inherited from parents but instead arise spontaneously as errors during cellular replication, often occurring during early embryonic development. Their occurrence can be influenced by factors such as advanced parental age—a well-documented risk for both mothers and fathers (Croen et al., 2007)—as well as environmental exposures that disrupt genomic stability (Pugsley et al., 2022).

This raises an important question: Could many individuals who are severely affected by autism represent cases in which toxic exposures during pregnancy trigger maternal immune activation and simultaneously contribute to the emergence of de novo mutations? Research exploring this possibility is urgently needed, as it may be relevant to more than one-quarter of the autism population (Hughes et al., 2023).

In a related ongoing research project, Judith Miller, a clinical psychologist at the Children’s Hospital of Philadelphia, is conducting a comprehensive study of environmental factors to which individuals are exposed over time. She is leading a multi-year project that integrates genomic and exposomic data (the latter focusing on lifetime exposures to environmental factors) from more than 100,000 children, including about 4,000 autistic children, and links this data to detailed maternal health records. The study incorporates geospatial data on air and water quality, green space access, and a wide range of other environmental exposures to explore how genetic susceptibility and environmental context may interact in autism.

Final thoughts

Can we realistically reduce harmful exposures when they are so deeply tied to economic and political forces? Cleaning up pollution in the air, water, and soil is an enormous undertaking and often prohibitively expensive, but there are many practical and cost-effective steps we can take.

In the near term, the highest priority should be protecting those most vulnerable: pregnant women and very young children. One promising effort in this area is P2i (Preconception to Infancy), a new initiative launched by the Northwest Autism Foundation. This comprehensive program is designed to support couples from the preconception stage through their children’s infancy, with the goal of promoting safer pregnancies and fostering healthier early development. One of the key goals of P2i is to reduce the body burden of toxic chemicals in mothers and their children.

There is also growing interest in interventions to reduce the harmful effects of environmental toxic exposures in autism. Strategies focus on enhancing detoxification pathways, such as increasing glutathione synthesis and strengthening antioxidant defenses. Additional approaches that support mitochondrial function, lower oxidative stress, and modulate immune responses may further reduce toxicant burden and its neurodevelopmental impact (see Rossignol & Frye, 2012).

Given the importance of efforts such as these, I believe it is time for the autism field to speak more openly and directly about specific environmental toxins and exposures. Greater transparency about these risk factors—such as exposure to certain heavy metals, pesticides, air pollutants, and prenatal stressors—will foster better public understanding and help guide prevention and policy efforts.

Researchers and clinicians have a responsibility to communicate emerging evidence clearly and without unnecessary delay. Open dialogue among scientists, policymakers, and the public will accelerate progress toward reducing harmful exposures and improving outcomes for future generations.

Stephen M. Edelson, Ph.D.
Executive Director, Autism Research Institute

References available at www.ARRIReferences.org.

This editorial is available in PDF format – Download Here
It originally appeared in Autism Research Review International, Vol. 39, No. 4, 2025

Contributors (listed in alphabetical order)

Vanessa H. Bal, Ph.D., Graduate School of Applied & Professional Psychology, Rutgers University; Margaret L. Bauman, M.D., Associate Professor of Anatomy and Laboratory Medicine, Boston University School of Medicine; Mary Doherty, M.D., Clinical Associate Professor, University College Dublin School of Medicine; Stephen M. Edelson, Ph.D., Autism Research Institute, San Diego, CA; Dena L. Gassner, Ph.D. (c), Senior Research Scientist, AJ Drexel Autism Institute: Drexel University; Robert L Hendren, DO, Professor of Psychiatry Emeritus, UCSF, Autism Research Institute; Wenn Lawson, Ph.D., A/Prof, Curtin University, Western Australia; David B. Nicholas, Ph.D., Faculty of Social Work, University of Calgary; Christopher Palmer, M.Sc., Commission for the Rights of Persons with Disability, Malta; Gaetano Alistair Savour, Ph.D., Chairperson, Autism Advisory Council, Ministry for Inclusion and the Voluntary Sector, Malta; Fakhri Shafai, Ph.D., AIDE Canada, Richmond, BC

For many years, the autism community focused nearly all of its attention on the needs of children and adolescents. As the prevalence of pediatric autism diagnoses has increased over the past three decades, researchers and service providers have broadened their focus to include the needs of individuals transitioning to adulthood and young adults. Today, there is increasing recognition of the importance of supporting autistic individuals throughout the entire lifespan, including old age.

In a 2017 report to Congress, the U.S. Department of Health and Human Services estimated that approximately 50,000 autistic youth are expected to transition into adulthood each year in the United States. Over the coming decades, a growing wave of these individuals will be entering later adulthood. Medicaid enrollment data has shown a steady increase in service use for this group.

The issue of aging in autism began to gain attention about a decade ago, and continues to grow in importance as rising numbers of autistic individuals age into their senior years. Prominent autistic individuals who are now over 60 years of age—including Temple Grandin, Stephen Shore, John Elder Robison, Wenn Lawson, Cos Michael, and Mark Rimland, the son of Dr. Bernard Rimland—highlight the relevance of this issue.

Some of the needs of autistic seniors, such as the requirement for appropriate living arrangements and good health care, appear straightforward. However, many less-obvious challenges are becoming clear as we are now hearing from autistic individuals approaching their senior years as well as from clinical and community researchers who are studying aging.

To explore these challenges, a dedicated group of autistic individuals and researchers has been meeting nearly monthly for approximately five years to discuss aging-related issues. This group has organized two major think tanks, resulting in published articles discussing their findings and conclusions (Edelson et al., 2023; Nicholas et al., 2025).

This group is currently planning a third think tank meeting at the United Nations, scheduled for next month (October 3, 2025). In preparation for this upcoming event, several additional autistic individuals have joined the planning committee to help determine important topics for discussion.

Recently, during one of their planning meetings, I was struck by the sheer number and complexity of senior-related issues identified by participants. To help prioritize these topics for the upcoming U.N. think tank, I asked the participants to rank these topics based on their perceived importance.

As the result of this ranking, the identified topics have been grouped under five key areas:

In the area of Physical and Mental Health in Aging, participants noted concerns related to dementia, Parkinson’s disease, extrapyramidal symptoms, and other age-related medical conditions (e.g., cancer, cardiac disease, stroke). They also stressed the importance of understanding the impact of medications on aging autistic individuals and exploring implications of hypermobility in older autistic adults (for example, those with Ehlers-Danlos syndrome). The broader spectrum of physical and mental health challenges associated with aging was recognized as posing concerns requiring urgent attention.

Regarding Healthcare Access, Navigation, and Delivery, participants highlighted menopause as an area in which there are significant unmet healthcare needs. They also emphasized the importance of making healthcare systems easier to navigate and reducing administrative burdens and bureaucratic barriers. Additionally, there was considerable concern about addressing the needs of autistic seniors requiring long-term care or acute medical treatment, including issues involving hospital admissions. Preparing autistic adults to communicate effectively with healthcare providers during medical visits was also identified as a critical area, along with addressing sensory sensitivities and nutritional needs in outpatient surgery units, long-term care facilities, and other healthcare environments. Participants noted that differences in sensory processing, communication, and stress response among autistic individuals may complicate the recognition and treatment of age-related health conditions, often leading to misdiagnosis or delayed care. They also stressed that autistic individuals should receive routine preventive care, including colonoscopies, prostate screening, and mammograms. Tailored clinical approaches that account for neurodivergent aging trajectories are urgently needed.

In the domain of Community, Autonomy, and Daily Life, the benefits of receiving a late autism diagnosis and self-recognition in older adults were highlighted. Community living options, regular health screenings, and protection from financial vulnerability were viewed as crucial for maintaining autonomy and quality of life. Participants noted the importance of supporting autistic individuals’ rights and legal capacity, while examining mechanisms such as guardianship and newer avenues such as supported decision-making and co-decision-making. Additionally, loneliness, social isolation, and parenting challenges faced by aging autistic adults—particularly those diagnosed later in life—were identified as vital areas of concern.

Social Determinants of Health and Discrimination also emerged as critical issues, with contributors expressing deep concern about ableism, ageism, housing insecurity, retirement, and forced retirement. Intersectionality, especially involving LGBTQIA+ and other multi-marginalized identities, was underscored as needing more focused attention. Participants also suggested learning from other sectors, such as the LGBTQIA+ community, in order to better address systemic issues.

Finally, End-of-Life and Palliative Care was recognized as an essential area needing more comprehensive planning and support. Participants emphasized the importance of respectful and informed end-of-life decision-making and palliative care tailored specifically for autistic individuals, including making clear and accessible communication readily available.

The richness and complexity of the issues discussed illuminate an undeniable reality: Proactive engagement and systemic preparation are vital. Addressing these topics not only will aid autistic adults in navigating their later years but also will help to build an essential framework for policymakers, caregivers, support persons, healthcare providers, and society at large. Enhanced research, informed policy development, and dedicated resources will ensure that autistic seniors can live with dignity, autonomy, and comprehensive support. Critical to this aim is the key role and contribution of autistic people themselves in determining their priorities and what is needed in their middle and later years.

It is crucial that ongoing dialogues and forthcoming initiatives foster increased awareness among autistic individuals, families, support networks, healthcare practitioners, and policymakers. Collectively, these collaborative efforts can drive meaningful changes in both practice and policy, ultimately creating a world where autistic seniors can thrive throughout their aging process.

Although awareness of the needs of the aging autistic community is increasing, the time for action is now. We must seize this momentum to ensure that autistic seniors experience the highest possible quality of life, made possible by informed, compassionate care, oversight, and support and a well-designed infrastructure capable of meeting their evolving needs.

References available at www.ARRIReferences.org.

This editorial originally appeared in Autism Research Review International, Vol. 39, No. 3, 2025

Aging introduces numerous challenges for autistic individuals, and one issue of concern—as it is for the general population—is the potential for rapid cognitive decline. This decline, commonly associated with dementia or Alzheimer’s disease, may pose unique difficulties for autistic individuals, who often contend with additional challenges such as anxiety, depression, gastrointestinal issues, insistence on sameness, memory impairments, sensory sensitivities, limited ability to communicate, and sleep disturbances.

It is important to note that dementia is a general term for cognitive impairments affecting memory, reasoning, and daily life. It can be caused by a variety of conditions, such as Alzheimer’s, vascular dementia, or Lewy body dementia. Alzheimer’s, the leading cause of dementia, accounts for 60-80% of cases. Understanding the distinction between dementia as a set of clinical symptoms and signs and Alzheimer’s as a specific disorder is essential for accurate diagnosis and treatment.

While research on the topic of dementia or Alzheimer’s disease in autistic individuals remains limited, emerging evidence presents a complicated picture. Some studies point to the possibility of a biological protective factor, noting a rarity of dementia or Alzheimer’s disease in the autism population. In contrast, other studies suggest a relatively higher prevalence rate than in the general population. This discussion will briefly summarize these findings and explore their potential implications.

Finding 1: Some data suggest that autistic individuals may be less susceptible to dementia

For some time, there has been speculation that autistic individuals might not experience dementia or Alzheimer’s, based on a lack of cases identified by experienced clinicians (Margaret Bauman, personal communication, December 2024). Over the past decade, several studies have supported this view.

Barnard-Brak et al. (2019) analyzed records of 1,754 autistic individuals from the National Vital Statistics System, spanning the years from 1999 to 2015. Their research focused on age at death and the prevalence of dementia-related disorders. The findings revealed that autistic individuals were less likely than the general population to develop dementia or Alzheimer’s disease.

In both longitudinal and cross-sectional studies, Torenvliet and colleagues administered a range of cognitive assessments, including assessments of memory, verbal fluency, processing speed, and self-reported cognitive issues, among others. Their findings revealed no significant evidence of sudden cognitive decline (Torenvliet et al.,2022, 2023).

Finding 2: Some data suggest that autistic individuals may be more susceptible to dementia

In a sample of 210 middle-aged and older autistic adults, participants completed a self-rated dementia questionnaire to assess cognitive decline. In contrast to the research cited above, the findings revealed that 30% reported experiencing cognitive decline (Klein et al., 2023). The most commonly reported symptoms included a reduced interest in leisure-type activities and increased difficulties with judgment in daily life, memory, and thinking.

Giacomo Vivanti and colleagues at A.J. Drexel Autism Institute published two large-scale studies involving insurance claims. In one study, they analyzed U.S. Medicaid claims data for both autism spectrum disorder (ASD) and Alzheimer’s disease and found that autistic individuals were approximately 2.6 times more likely to be diagnosed with early-onset Alzheimer’s disease and related dementias compared to the general population (Vivanti et al., 2021).

In a more recent study, Vivanti et al. (2025) analyzed both Medicare and Medicaid data from 2014 to 2016, involving 114,582 autistic individuals aged 30 years
and older, and reported that 8% of autistic individuals and nearly 9% of those with both autism and intellectual disabilities received dementia diagnoses. In addition, the prevalence of dementia increased sharply among those over 64 years of age, with 35% of individuals with ASD alone and 31% of those with both ASD and intellectual disabilities showing signs of dementia.

While Vivanti et al.’s studies were based on insurance claims data without clinical assessments, previous research indicates a high correspondence between claims-based and clinical diagnoses for autism (Burke et al., 2014) and for Alzheimer’s disease (McCarthy et al., 2022).

Interestingly, Rhodus et al. (2022) evaluated 56 individuals with mild cognitive impairment or dementia near the end of life using the Gilliam Autism Rating Scale, 2nd Edition, followed by postmortem neuropathologic assessments. Individuals categorized as “Autism Possible/Very Likely” exhibited higher neurofibrillary tangle density, increased tau burden in the frontal and temporal lobes, and a more significant neuritic plaque burden compared to those in the “Autism Unlikely” group. These findings may suggest a potential association between autism and increased tau pathology, a common characteristic linked to late-life dementia. However, the researchers did not report evidence of amyloid-containing plaques, which are considered a common marker of Alzheimer’s disease.

There is also indirect evidence suggesting that autistic individuals may have a predisposition to Alzheimer’s disease. Research from the general population shows that visual memory deficits can predict Alzheimer’s disease up to a decade before diagnosis (Kawas et al., 2003). Additionally, studies have documented significant visual memory impairments in autistic individuals. For example, Geurts and Vissers (2012) identified pronounced visual memory deficits in a group of 23 autistic seniors aged 51 to 83 years compared to a control group.

Making sense of this supposed discrepancy

Defining study populations and ensuring accurate diagnosis. To draw meaningful statistical inferences, it is important to clearly define the study population, whether it consists of a single group or multiple groups, such as controls and treatment groups. However, the cited studies demonstrate inconsistency in population definitions, ranging from Medicare/Medicaid recipients to high-functioning individuals with autism and, in some cases, broadly encompassing “all” individuals with autism.

In addition, there are issues regarding the accuracy of dual diagnoses in insurance claims. Autism and Alzheimer’s disease share substantial symptom overlap (Khan et al., 2016; Rhodus et al., 2020a, 2020b), which may lead to diagnostic misclassification. Additionally, valid statistical methods or results comparing dementia/Alzheimer’s prevalence between the autistic population under study and the general population are often lacking. Proper data analysis requires that measurements be well-defined, consistently applied, and representative of a random sample—criteria that are not always met in the current literature.

Recognizing the role of autism’s heterogeneity. When evaluating discrepancies in research findings, it is important to recognize the broad spectrum of autism presentations. While individuals formally diagnosed with autism share core symptoms, they vary significantly in the severity of their symptoms, their level of independence, and other factors. This heterogeneity may contribute to differences in dementia risk. Some autistic individuals may experience a sudden cognitive decline resembling dementia or Alzheimer’s disease, while others may not—mirroring the variability observed in the general population.

Moreover, the ability to diagnose dementia or Alzheimer’s in autistic individuals may depend on their baseline challenges. Those with fewer difficulties in social communication may exhibit more recognizable declines in orientation, memory, planning, problem solving, and personality. In contrast, for those with more pronounced lifelong challenges, these declines may be harder to detect, as they overlap with preexisting difficulties.

Moving toward more accurate diagnosis. To better understand the potential connection between autism and Alzheimer’s, research should prioritize examining specific brain regions associated with Alzheimer’s pathology. The study by Rhodus et al. (2022) highlights how neuroimaging may help identify impairments characteristic of Alzheimer’s disease. However, postmortem brain studies remain essential for confirming the presence of actual cases of dementia or Alzheimer’s disease. For further discussion on the importance of postmortem brain tissue research, see Natowicz et al. (2024).

Finally, given the limitations of research relying on insurance claims, a more refined approach to diagnosis is needed. Autism and dementia, including Alzheimer’s disease, share overlapping characteristics, which complicates classification. Developing a specialized behavioral checklist to document past and current behaviors may enhance the accuracy of identifying individuals with co-occurring autism and dementia or Alzheimer’s.

Final thoughts

Individuals with autism and dementia or Alzheimer’s disease will likely require considerable guidance and support, potentially exceeding the needs of those with only one condition or the other. Moreover, given the rapid decline typically associated with dementia and Alzheimer’s, it would be wise to implement appropriate procedures promptly. To adequately address this issue, healthcare providers will need specialized training to recognize dementia in individuals with autism, as well as to understand the potential for overlapping or masking of signs. It will be crucial to develop communication strategies that accommodate the individual’s sensory challenges and cognitive capabilities and to create environments that minimize stress and overstimulation.

Furthermore, caregivers and families of autistic individuals must be supported with resources and education tailored to this dual diagnosis. This includes guidance on managing behavioral changes, providing consistent routines, and accessing appropriate medical and therapeutic services.

Even if individuals with autism do not have an elevated risk for dementia—an issue still to be better understood—the high population prevalence of autism necessitates that specialists in autism, dementia, and Alzheimer’s work together to design interventions that address the unique needs of this population while promoting the best possible quality of life.

References available at www.ARRIReferences.org.

Stephen M. Edelson, Ph.D.
Chief Science Officer, Autism Research Institute

This editorial originally appeared in Autism Research Review International, Vol. 39, No. 1, 2025