Understanding Prosody in Autism Spectrum Disorder

Kayla Poggi, Verrazzano Class of 2025, completed major in English Linguistics and minor in ASL

Throughout the completion of my capstone project, I learned things that will be beneficial to my future career as a Speech Language Pathologist, and learned more about Autism Spectrum.
For example, understanding prosody, which refers to the rhythm, pitch, volume, and intonation of speech, and plays an essential role in how we convey meaning, emotion, and intent in communication. In autism, prosody can be affected in various ways, which may lead to differences in how speech sounds to others. Many individuals with autism experience differences in prosody, such as monotone speech, which is a lack of variation in pitch, atypical speech rhythm, or inappropriate stress on words. These differences can sometimes make it harder for others to interpret their emotional state, intentions, or level of engagement.
This research taught me how social communication can have its challenges for someone with autism. The differences in prosody in individuals with autism may contribute to challenges in social communication. For instance, their speech might not align with social expectations of tone, such as speaking too loudly or softly, which can affect social interactions and lead to misunderstandings.
Prosody in autism could be due to difficulties in both producing and perceiving prosodic cues. Research could focus on whether individuals with autism struggle more with prosodic production (e.g., monotone speech) or perception (e.g., difficulty recognizing emotional tones in speech).
In addition to learning about prosody and how it impacts individuals with autism, I also learned a great deal about writing an in-depth research paper. I learned about writing structure, paying attention to details and making sure what I am writing aligns with my evidence. I learned how to do research on certain databases, handling citations, and how best to utilize my sources.
If I continued research on this topic, I think it could be further developed by observing people with autism in a social setting and focusing on expressive and receptive language.

The Effect of Spinal Electrical Cord Stimulation for Neurogenic Bladder

Karina Toska, Verrazzano Class of 2025, completed major in Biology and minor in Spanish

My research was motivated by an interest in anatomy and a curiosity of understanding the body systems and how they affect each other. My objective explored urinary incontinence due to spinal cord injury. Urinary incontinence is the leakage of urine from the bladder due to an individual losing control over the muscles in the bladder due to weakness. The urinary system and central nervous system are involved because the damage to nerves in the spinal cord create a miscommunication with the bladder which ultimately leads to patients urinating involuntarily, when their bladder isn’t full.

Methods such as electrical muscle stimulation are used, where shocks are applied from patches placed on top of or under the skin. Studies found that the electrical muscle stimulation had a positive impact, where events of involuntary urination decreased by 64%.

I was anticipating my capstone being difficult, because many studies had to be conducted and reviewed. It was challenging to read through multiple articles and create one cohesive paper based on many different data sets. Learning about and writing about the anatomy of the human body was easy since I had already learned that, and reading through articles gave me a refresher.

I think research on this topic could be further expanded to test if electrical muscle stimulation is able to provide more function to other limitations in the body, such as paralysis. Individuals who have gone through many unfortunate events that left them with paralyzed body parts might feel like they have lost hope, that they’ll never be able to move as they did before. Now, with new technological advancements, they will be able to regain function.

 After this research experience, I have been very appreciative of the physicians and physical therapists that work to help patients live happier lives and allow them to get therapy to gain more control over their bodies, therefore allowing them to have more control over their lives. I’ve been working as an EMT and many of the older patients I have had to transport have urinary incontinence, and many are bed-ridden, with diapers or tubes to catch their urine into a jug.

I was surprised yet elated with the results; in the beginning I had no idea if shocks delivered to the spinal cord would actually have a noticeable effect on a patient being able to hold in their urine, but in a relatively short time, I found that it was possible.

Capricorn AI: An Automated Deep Learning Approach for Histopathological Tissue Classification

Moshe Newman, Verrazzano Class of 2025, completed major in Molecular & Cellular Biology

I identified my research topic at the intersection of oncology, bioinformatics, and artificial intelligence, motivated by my longstanding passion for cancer research and precision medicine. My goal was to contribute toward improving the diagnostic accuracy and efficiency of cancer detection, ultimately aiming to benefit patient outcomes. The idea of utilizing advanced technology like deep learning to tackle histopathological classification inspired me, especially since the method holds potential for significant clinical impact.

Early on, I had expected the capstone to be straightforward training and testing of deep learning models. Instead, it turned out to be far more complicated and involved frequent troubleshooting and optimization. The capstone required heavy preprocessing, model architecture exploration, and close attention to model outputs. The complexity of converting results into clinical understanding was deeper than anticipated but ultimately more rewarding.

Among the greatest challenges was handling dataset imbalances and hyperparameter tuning of the neural network to avoid overfitting, and it took a lot of experimenting and statistical exploration. In contrast, understanding the theoretical background of deep learning was relatively easier to me given my background in bioinformatics as well as programming. What was most surprising to me was the complexity involved in adequately visualizing and representing the model output predictions, which necessitated creativity and more statistical expertise than expected.

To further expand this work, I plan to incorporate patient metadata and clinical history to enhance the predictive capability of Capricorn AI, effectively making it a more detailed diagnostic and prognostic tool. Exploring real-time imaging and adaptive training techniques could significantly improve clinical utility and specificity of the model. Lastly, conducting larger validation studies with more varied datasets will be necessary to facilitate generalizability.

Through this experience, I am developed a greater appreciation of the challenges and opportunities of interdisciplinary research. It reinforced my passion for bioinformatics and oncology and expanded my expertise in machine learning, particularly the importance of meticulous data handling, model verification, and successive experimentation. Professionally, it established my analytical skills, research endurance, and ability to present sophisticated scientific outcomes succinctly and persuasively to different audiences.