1. Disease Heterogeneity: Alzheimer's disease is not a one-size-fits-all condition. It manifests with varying degrees of severity, different rates of progression, and can present with diverse symptoms. This heterogeneity makes it challenging to identify suitable candidates for clinical trials and to group them effectively for research purposes.

2. Diagnostic Accuracy: Accurate diagnosis of Alzheimer's disease can be challenging, especially in the early stages. Misdiagnosis or uncertainty in diagnosis can lead to the inclusion of inappropriate candidates in clinical trials, potentially diluting the study's outcomes and hampering the development of targeted therapies.

3. Informed Consent: Obtaining informed consent from AD patients can be complicated due to cognitive impairments that affect their capacity to understand the study's objectives and risks. Researchers must navigate ethical considerations and ensure that participants and their caregivers fully understand the implications of participation.

4. Limited Awareness: Many patients and caregivers are unaware of clinical trial opportunities or may have misconceptions about them. Raising awareness and providing education about clinical trials is crucial to increasing enrollment rates.

5. Caregiver Burden: Alzheimer's patients often rely on caregivers to make decisions on their behalf and provide support. Caregivers may be overwhelmed by the responsibilities of caregiving, making participation in clinical trials logistically challenging.

6. Fear and Stigma: There is often fear and stigma associated with Alzheimer's disease. Patients and their families may be hesitant to acknowledge the diagnosis or seek research opportunities due to concerns about social judgment. With new treatments arriving on the market this fear and stigma may dissipate. 

7. High Dropout Rates: Alzheimer's clinical trials typically require long-term commitments, and patients' cognitive and physical decline can lead to high dropout rates. These dropouts can significantly impact the study's validity and hinder data collection.

8. Comorbid Conditions: Alzheimer's patients frequently have comorbid health conditions, such as cardiovascular disease or diabetes, which may require multiple medications and complicate their eligibility for clinical trials. Managing these comorbidities alongside the study intervention can be challenging.

9. Ethical Considerations: Patients with Alzheimer's disease are considered a vulnerable population, which necessitates stringent ethical safeguards. Researchers must ensure that the rights and well-being of these individuals are protected throughout the trial process.

10. Recruitment Timelines: Clinical trials often have strict recruitment timelines, which may not align with the natural progression of Alzheimer's disease. Patients may not be diagnosed early enough to participate in certain trials, limiting the pool of eligible participants.

11. Biomarker Use Still not Prevalent: Currently, there is no definitive biomarker for Alzheimer's disease, which means that diagnosing and tracking the progression of the disease can be imprecise. This uncertainty can complicate patient recruitment for trials that require specific disease stage or progression criteria. In addition to digital biomarkers there are also blood-based biomarkers becoming more effective. 

12. Access to Specialized Centers: Many Alzheimer's clinical trials are conducted at specialized research centers, which may be geographically distant from potential participants. This creates barriers related to transportation, especially for older patients and their caregivers.

13. Regulatory Challenges: Clinical trials involving Alzheimer's disease often need to meet stringent regulatory requirements due to the vulnerability of the patient population. This can result in lengthy approval processes that delay the start of trials.

Addressing these challenges requires a multifaceted approach. Researchers and organizations conducting clinical trials in Alzheimer's disease must develop strategies to improve patient identification, enhance caregiver support, streamline informed consent processes, and foster collaboration between research centers. Here are some potential solutions:

1. Early Detection and Diagnosis: Promote early detection and accurate diagnosis through increased public awareness and reliable digital biomarkers such as Novoic’s Storyteller.

2. Supportive Care for Caregivers: Provide resources and support for caregivers to reduce their burden and make trial participation more feasible.

3. Simplified Informed Consent: Develop simplified informed consent processes and materials that accommodate the cognitive impairments of AD patients while ensuring their autonomy and ethical treatment.

4. Outreach and Education: Increase outreach efforts to educate patients, caregivers, and healthcare professionals about clinical trial opportunities and the importance of research in advancing Alzheimer's treatments.

5. Diverse Study Designs: Consider diverse study designs that accommodate the heterogeneity of Alzheimer's disease, including trials focused on specific subtypes or stages of the disease.

6. Remote Digital Assessments Approach at Screening: With high screen/fail rates at the clinics, clinical trialists should explore remote options that allow patients to be partially screened from their homes to reduce the number of patients visiting clinics only to be told they don’t qualify for a clinical trial. Novoic’s Storyteller is a 10 minute assessment that can be taken online to predict MCI and early Alzheimer’s Disease. 

Recruiting patients with Alzheimer's disease for clinical trials is undoubtedly challenging, but it is a crucial endeavor in the quest to develop effective treatments and ultimately find a cure for this devastating condition. By addressing these challenges with innovative approaches and a commitment to ethical research, progress can be made in advancing Alzheimer's disease research and improving the lives of affected individuals and their families.

Understanding new treatments:

Infusion treatments, such as the newly approved Leqembi, are novel therapeutic compounds designed to target specific protein misfolding and aggregation in the brain, which are characteristic hallmarks of Alzheimer's disease. Developed by dedicated researchers and pharmaceutical experts, they hold promise as breakthrough treatments to slow the progression of the disease and potentially ameliorate its symptoms.

One of the primary pathological features of Alzheimer's disease is the accumulation of amyloid-beta protein, leading to the formation of amyloid plaques in the brain. New treatments exhibit a remarkable ability to target and break down these amyloid plaques, which may help prevent or slow down the neurodegenerative processes associated with Alzheimer's.

In addition to its plaque-reducing properties, these treatments also demonstrate anti-inflammatory effects within the brain. Neuroinflammation is a significant contributor to neuronal damage in Alzheimer's disease. By reducing inflammation, they can potentially protect nerve cells from further harm, preserving cognitive function in patients.

The Promise of Novoic's Technology in Early Prediction:

Novoic is a pioneering technology company that has harnessed the power of artificial intelligence and machine learning to analyze speech and detect subtle changes that may indicate early-stage Alzheimer's disease. Leveraging sophisticated algorithms and large datasets, Novoic's technology provides a non-invasive, efficient, and cost-effective method for early prediction of the disease.

Studies have shown that speech patterns and linguistic features undergo subtle changes in individuals experiencing early cognitive decline. Novoic's technology can analyze speech samples and identify specific linguistic markers that may be indicative of Alzheimer's disease before conventional diagnostic methods detect noticeable symptoms.

One of the key advantages of Novoic's technology is its potential for remote monitoring and accessibility. Novoic’s Storyteller can quickly capture speech samples from the comfort of each patient’s home, eliminating the need for frequent in-person visits to medical facilities. This convenience may increase the likelihood of early detection and intervention, leading to improved treatment outcomes.

The combined power of new Alzheimer’s Disease treatments and Novoic's technology offers a synergistic approach to Alzheimer's disease management. Novoic's early prediction capabilities enable pharmaceutical companies to identify individuals at risk of developing Alzheimer's at an earlier stage. Early intervention with these treatments could potentially delay the onset or slow the progression of the disease, preserving cognitive function for an extended period.

Moreover, Novoic's technology can play a crucial role in clinical trials and drug development for Alzheimer's treatments. By accurately identifying early-stage patients for clinical trials, researchers can gather essential data more efficiently, potentially expediting the approval and availability of treatments like Leqembi.

Alzheimer's disease remains an immense challenge in modern healthcare, demanding innovative solutions to diagnose and treat the condition at its earliest stages. New treatments and Novoic's technology exemplify the power of groundbreaking research and technological advancement in the pursuit of a world without Alzheimer's disease. The potential benefits of treatments in targeting amyloid plaques and reducing neuroinflammation, combined with Novoic's ability to provide early and non-invasive prediction, create a compelling synergy. Together, these treatments and Novoic's technology offer a ray of hope in the fight against Alzheimer's, paving the way for a future with improved patient outcomes, enhanced quality of life, and a step closer to finding a cure for this devastating neurological disorder

Introduction

Dementia affects millions of people worldwide, and it is estimated that over 850,000 people in the UK live with dementia. Dementia is a term used to describe a group of symptoms that affect memory, thinking, and social abilities. Alzheimer's Disease, which is the focus of this blog post, is the most common type of dementia and is characterised by the following symptoms:

• Memory loss

• Difficulty communicating

• Difficulty with familiar tasks

• Disorientation and confusion

• Wandering

• Mood changes

• Personality changes

• Difficulty with problem-solving and decision-making

• Difficulty with self-care

If you think a loved one has dementia it's important to get a proper diagnosis from a doctor so the patient and their caregivers can receive professional advice and support. Earlier diagnoses have more benefits than later diagnoses and this blog post will highlight some of the benefits an early diagnosis can afford patients, caregivers, and clinical researchers.

Benefits for Patients

Improved Health Outcomes

Current treatments for Alzheimer's disease, such as acetylcholinesterase inhibitors and memantine, do not cure the condition but can help slow the progression of the disease. Additional treatments, Leqembi and Aduhelm, received partial approval from the United States’ FDA in 2021 and 2023 and are currently under review for full approval.  Receiving an early diagnosis will ensure that the patient is prescribed these medications as soon as possible and that they receive the maximum possible benefit from these treatments.

The patient's consultant or GP might also recommend non-pharmacological treatments to help slow the progression of Alzheimer’s disease. For example, in cognitive stimulation therapy, patients participate in group exercises designed to improve memory and problem-solving skills. Starting these types of therapies early can delay the need to start taking medications that can have unwanted side effects.

Patients often forget that lifestyle factors also influence the progression of the disease and when they receive an official diagnosis their doctor might recommend they make some lifestyle changes to slow the progression of the disease. For example, stopping smoking, exercising, lowering your blood pressure, and staying mentally and socially active can all help to slow cognitive decline.

Psychological and Emotional Support

Symptoms associated with cognitive decline can be confusing for patients and it’s not uncommon for patients to feel anxious. Receiving an early diagnosis can help reduce those anxieties as patients will have a better understanding of why they’re experiencing those symptoms. Patients will also have more time to spend with their families and access support.

Future Planning

Future planning goes beyond making a Will where an individual outlines what will happen to their personal belongings after their death. Patients should consider making advanced decisions, also known as living wills, and registering a Lasting Power of Attorney, which is a document where they formally designate a person to make decisions on their behalf if they’re unable to due to a lack of mental capacity. These are legal documents and to officially register them patients must have full mental capacity. Receiving an early Alzheimer’s diagnosis gives patients plenty of time to think about the future and ensures they don’t have to make rushed decisions or miss out on the opportunity to make these decisions altogether.

An early Alzheimer’s diagnosis also gives the patient and their family time to plan for the costs associated with dementia care. Dementia care can be expensive and currently, there is little government funding available in the United Kingdom or the United States. Tiggo Care has written a complete Guide to Care Funding Options that readers exploring funding options in the UK might find useful.

Benefits for Caregivers

Improved Care Planning

Knowing that an individual has an early Alzheimer’s diagnosis makes it much easier to organise appropriate care. For example, the early diagnosis gives the patient and their family time to decide if they want to organise a live-in care service sooner rather than later, such that the patient can build a professional relationship with a live-in carer while they still have good cognitive function. Alternatively, the patient and their family may decide to use a specialist dementia home care service or look for a room at a specialist dementia care facility. The early diagnosis makes it easier for the patient to be involved in these decisions and can alleviate any stress resulting from changes to their daily routine.

An early diagnosis makes it easier for caregivers to encourage patients to adopt healthy behaviours, such as healthy diets and regular exercise, to slow the onset of dementia symptoms. Caregivers can also encourage patients to stay mentally active by completing puzzles and jigsaws, or even escort them on trips in the community to ensure they remain socially active. At later stages, caregivers may struggle to encourage patients to make these beneficial lifestyle changes.

Home Adaptations

In most cases, patients will need to make some adaptations to their homes to ensure that they can continue to live safely at home. An occupational therapist will advise the patient on the specific adaptations and equipment best suited to their specific needs. An early diagnosis allows patients to make these changes ahead of time before an accident happens. It also allows the billpayer to spread the cost of these adaptations over a longer period of time.

Benefits for Researchers

Participant Selection & Evaluation of Early Therapeutic Interventions

Early diagnoses ensure researchers can include individuals in the earliest stages of Alzheimer's disease in their studies, allowing them to identify potential biomarkers and underlying mechanisms from the earliest detectable changes. Ultimately this allows researchers to study the effectiveness of early interventions and early treatments to slow the progression of the disease and potentially even find a cure for the disease.

Identification of Risk Factors

Early diagnosis contributes to the identification of risk factors and the development of early detection methods for Alzheimer’s disease. By studying patients with an early diagnosis, researchers can examine genetic, environmental, and lifestyle factors associated with the disease’s onset. The findings of these research studies can be used to help those most at risk modify their behaviours and environment to reduce their chances of developing or accelerating the symptoms of Alzheimer’s disease. 

Understanding Disease Progression

The later stages of Alzheimer’s disease progression are better understood than the early stages of the disease. Earlier diagnoses allow researchers to study the sequence of changes that occur in the brain and body at the onset of the disease. This knowledge helps researchers understand the underlying mechanisms, identify potential targets for intervention, and develop strategies to accurately predict disease progression. It also contributes to the development of staging systems for clinical trials and individualised clinical care planning.

Conclusion

Receiving an early Alzheimer's diagnosis has significant benefits for patients, caregivers, and researchers alike. For patients, early diagnosis can improve health outcomes through timely access to medications and other non-pharmacological treatments, as well as the opportunity to make lifestyle changes that can slow cognitive decline. Caregivers benefit from improved care planning, enabling them to establish support systems and implement safety measures. For researchers, using patients in their studies with very early-onset Alzheimer's disease allows for the evaluation of earlier therapeutic interventions and greater insight into associated risk factors. Ultimately, early diagnosis plays a pivotal role in enhancing care, improving outcomes, and advancing research efforts in the fight against Alzheimer's disease.

Traditionally, impairments in these domains are measured with neuropsychological tests that rely on simple response indices and have had limited sensitivity to subtle cognitive changes.

There’s now a new paradigm emerging that subtle impairment in these domains can be measured in connected speech. And this can be done in an automated fashion with software and natural language processing.

How do we elicit connected speech? Our approach has been focussed on story recall (retelling a short story), which is widely known as an episodic memory task, but which has also been shown as the optimal speech elicitation protocol for connected speech.

Skirrow et al. 2022 JMIR Aging – task design and psychometric properties

The Automated Story Recall Task (ASRT) is a story recall task designed for elicitation of connected speech, with more natural sentence structure and balancing for key linguistic and discourse variables. The task is automatically administered via a web-app on a smartphone, tablet or computer. User spoken responses are captured, then automatically analysed with a robust NLP pipeline. In Skirrow et al. 2022, we describe the task design and demonstrate excellent psychometric properties, including test-retest reliability, parallel forms reliability and high convergent validity with the CDR and PACC5.

Weston et al. 2022 ACL – advanced AI models for better linguistic biomarkers

Our approach diverges from prior work focussed on feature engineering with signal processing and statistical parsers. Instead we develop clinically-informed custom Transformer models, pre-trained on large non-clinical datasets. One of our models is described in Weston et al. 2022.

Fristed et al. 2022a/b Brain Communications and A&D DADM – predicting MCI and amyloid from speech with AI

Applying this class of novel models has allowed us to achieve a number of breakthroughs, including predicting MCI, preclinical AD and amyloid PET positivity from speech. We’ve done this in different settings and setups, indicating robustness of the approach (Fristed et al. 2022a, Fristed et al. 2022b).

Moving into the real world

Based on this work, we developed an abbreviated AI speech test for scalable testing online. This is now used in the largest cohorts in early AD globally, including ADNI4, where the digital screener will support recruitment of underrepresented groups at scale (Weiner et al. 2022).

Other papers

• Weston et al. 2021 ICML: Learning De-identified Representations of Prosody from Raw Audio

• Lenain et al. 2020 INTERSPEECH: Surfboard: Audio Feature Extraction for Modern Machine Learning

• Shivkumar et al. 2020 INTERSPEECH: BlaBla: Linguistic Feature Extraction for Clinical Analysis in Multiple Languages

Results from two clinical trials published today in the scientific journal Brain Communications provide evidence that very early stages of Alzheimer’s disease can be detected through the way people speak using AI-based speech analysis. The speech-based system could detect the presence or absence of brain amyloid protein at the very early stages of Alzheimer’s disease (preclinical and prodromal stage), typically requiring PET scans, and did so better than the Preclinical Alzheimer’s Cognitive Composite with semantic processing (the “PACC5”), a sensitive clinical measure of subtle cognitive impairment that requires long in-person administration by highly trained staff.

Importantly the speech-based system was fully automated and can be run in a browser on any standard mobile, tablet, or computer. It could therefore offer a more accessible and affordable method for testing for early Alzheimer’s at scale.

One of the underlying disease processes of Alzheimer’s disease, accumulation of amyloid protein in the brain, begins up to decades before usual diagnosis. Amyloid protein has been a key target for new Alzheimer’s treatments, including the drug Lecanemab that was recently the first disease-modifying treatment to demonstrate positive treatment effect on cognitive decline. Clinical trials typically use PET scans to detect amyloid protein. But with a cost of thousands of dollars per PET scan, this method has been limited to clinical research. In the broader healthcare system, clinicians most often rely on simple pen-and-paper-based tests with limited ability to detect early cognitive decline, causing long delays in diagnosis.

Now researchers from Novoic, Harvard Medical School and Strategic Global R&D have demonstrated that the presence of amyloid protein in the brain can be detected during the earliest stages of Alzheimer’s disease from how people speak, using AI-based speech analysis, potentially reducing the time to diagnosis and the costs to detect the presence of amyloid protein.

The published data comes from two recently completed clinical trials in the UK and the US run by Novoic: Amyloid Prediction in Early Stage Alzheimer’s Disease From Acoustic and Linguistic Patterns of Speech (NCT04828122, NCT04928976). Whereas previous work has considered speech changes in dementia, the AMYPRED trials focussed specifically on early stage cognitive impairment (preclinical and prodromal stage), where the presence or absence of amyloid biomarkers had been confirmed as the underlying cause – matching the disease-stages where new disease-modifying treatments such as Aducanumab, Lecanemab and Donanemab are being tested today.

“We set up the AMYPRED trials to test if there is a speech phenotype at the earliest stages of Alzheimer’s disease, and whether there are speech differences in amyloid biomarker positive individuals, who may be at greater risk for developing cognitive problems or Alzheimer’s Dementia in the future” said Emil Fristed, CEO of Novoic, “Using a novel class of clinically informed deep learning models we reveal a distinct speech phenotype at both the prodromal and preclinical stage.”

To test patients’ speech, the researchers used a recently published speech-testing protocol called the Automated Story Recall Task (ASRT) (Skirrow 2022, JMIR Ageing), where patients are played one or more pre-recorded short stories via a smartphone or computer and asked to tell them back. The spoken responses are recorded and can then be analysed for episodic memory function and language use.

Turning to the task of predicting the presence of amyloid biomarkers in the brain from the spoken responses, the researchers found that the methods traditionally used for speech analysis had limited use. Instead, they developed an approach based on a recent breakthrough in natural language processing, in the area of large language models, and applied the current state-of-the-art deep learning model for evaluating text pairs (Weston 2022, ACL) to the spoken responses. Novoic’s CTO, Dr. Jack Weston, explained:

“Traditional statistics extracted from speech lack the sensitivity we need to detect changes associated with the earliest stages of the disease. Off-the-shelf foundation models, like BERT and its derivatives, also don’t cut it when we’re dealing with dataset sizes typical of clinical research. Instead, we developed a custom AI model primed to detect clinically-relevant patterns, fusing the latest research in clinical neuroscience and large language models. When we used this model to evaluate the quality, content and form of the responses to predict the participant’s amyloid biomarker status, the model performed remarkably well.”

Using this model, the researchers found that they were able to detect the presence or absence of brain amyloid protein at the very early stages of Alzheimer’s disease. The speech-based system outperformed the Preclinical Alzheimer’s Cognitive Composite with semantic processing (the “PACC5”), a sensitive clinical measure of subtle cognitive impairment that requires long in-person administration by highly trained staff, and which is used as an endpoint in several clinical trials today in preclinical Alzheimer’s disease.

Importantly the speech-based system was fully automated and can be run in a browser on any standard mobile, tablet, or computer. It could therefore offer a more accessible and affordable method for testing for early Alzheimer’s at scale.

The system is already being rolled out across the US, including as the digital screener for the fourth generation of the Alzheimer’s Disease Neuroimaging Initiative (ADNI4) – the largest and most diverse recruitment effort in early stage Alzheimer’s disease to date. Here Novoic’s Storyteller system will support screening of 20,000 patients online to inform participant selection across >50 sites, providing an early example of the scalability of the system.

The Automated Story Recall Task (ASRT) and the accompanying automated AI-based analysis, marketed together as “Storyteller by Novoic”, is available for researchers and for commercial use from Novoic.

About Novoic

Novoic is an Oxford-founded clinical stage digital medtech company developing clinical deep learning algorithms to detect early-stage neurological disease from how people speak. The company’s AMYPRED clinical studies were the first to test deep speech phenotyping in biomarker-confirmed early-stage Alzheimer’s disease, and its research team has developed the state-of-the-art clinical deep learning model for text evaluation. Novoic is working with organisations such as the Alzheimer’s Disease Neuroimaging Initiative (ADNI), Alzheimer’s Drug Discovery Foundation (ADDF) and the UK’s National Health Service (NHS) to accelerate clinical translation of speech biomarkers into impactful medical devices.

About Storyteller by Novoic

Storyteller (by Novoic) is an automated system for speech-based cognitive testing that uses AI-based natural language processing to quantify patterns of speech associated with subtle patterns of disease-specific, early cognitive decline. It runs AI-based speech-analysis on Novoic’s Automated Story Recall Task (ASRT), a digital and automatically administered story recall task, that’s been demonstrated to have excellent psychometric properties and good usability for remote self-testing on people’s own devices, including in an elderly, cognitively impaired population (Skirrow 2022, JMIR Ageing). The system runs as a browser-based app on any mobile device or computer and takes less than 10 minutes to complete, and can be used by patients themselves at home on their own devices. Storyteller uses automated quality control, audio processing and transcription, and AI-based analysis, to provide instantaneous results on subtle cognitive decline and risk of amyloid positivity. It’s been validated in a number of gold-standard clinical studies, including the AMYPRED studies (NCT04828122, NCT04928976). The system is already being rolled out across the US in a number of large-scale research efforts, including as the digital screener for the fourth generation of the Alzheimer’s Disease Neuroimaging Initiative (ADNI4) – the largest and most diverse recruitment effort in early stage Alzheimer’s disease to date. Here Novoic’s Storyteller system will support screening of 20,000 patients online to inform participant selection across >50 sites.

About the AMYPRED studies

The AMYPRED studies (NCT04828122, NCT04928976) are the first clinical studies to investigate deep speech phenotyping in a biomarker-confirmed, early stage Alzheimer’s disease population. The objectives of the studies were to test if a novel first-in-class clinical deep learning model can detect speech patterns specific to mild cognitive impairment and to the presence of amyloid biomarkers in the brain. In both the UK and US-based study, participants with mild cognitive impairment and normal cognition, and with confirmed positive and negative amyloid biomarker status, were recruited into four distinct cohorts. In the studies participants did a battery of speech tasks both under supervision of a clinician and remotely with unsupervised self-testing.