Melissa Valaee

Ms. Melissa Valaee

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 July 2025 in bioRxiv
Verified
Preprint
Open access
MVMelissa Valaee
Melissa Valaee
SSShahram Shirani
Shahram Shirani
Background: With a 17.9 million annual mortality rate, cardiovascular disease is the leading global cause of death. As such, early detection and disease diagnosis are critical for effective treatment and symptom management. Cardiac auscultation, the process of listening to the heartbeat, often provides the first indication of underlying cardiac conditions. This practice allows for the identification of heart murmurs caused by turbulent blood flow. In this exploratory research paper, we propose an AI model to streamline this process that improves diagnostic accuracy and efficiency. Methods: We utilized data from the 2022 George Moody PhysioNet Heart Sound Classification Challenge, comprised of phonocardiogram recordings of individuals under 21 years of age in Northeast Brazil. Only patients who had recordings from all four heart valves were included in our dataset. Audio files were synchronized across all recordings and converted to Mel spectrograms before being passed into a pre-trained Vision Transformer, and finally a MiniROCKET model. Additionally, data augmentation was conducted on audio files and spectrograms to generate new data, bringing our total sample size from 928 spectrograms to 14,848. Results: Compared to existing methodologies, our model yielded significantly enhanced quality assessment metrics, including Weighted Accuracy, Sensitivity, and F-Score, as well as a faster evaluation speed of 0.02 seconds per patient. Conclusion: The implementation of our method for the detection of heart murmurs can supplement physician diagnosis and contribute to earlier detection of underlying cardiovascular conditions, faster diagnosis times, increased scalability, and enhanced adaptive abilities.

27 September 2025 in Diagnostics
Verified
Journal Article
Open access
PDF file
MVMelissa Valaee
Melissa Valaee
SSShahram Shirani
Shahram Shirani
Background/Objectives: With a 17.9 million annual mortality rate, cardiovascular disease is the leading global cause of death. As such, early detection and disease diagnosis are critical for effective treatment and symptom management. Cardiac auscultation, the process of listening to the heartbeat, often provides the first indication of underlying cardiac conditions. This practice allows for the identification of heart murmurs caused by turbulent blood flow. In this exploratory research paper, we propose an AI model to streamline this process to improve diagnostic accuracy and efficiency. Methods: We utilized data from the 2022 George Moody PhysioNet Heart Sound Classification Challenge, comprising phonocardiogram recordings of individuals under 21 years of age in Northeast Brazil. Only patients who had recordings from all four heart valves were included in our dataset. Audio files were synchronized across all recordings and converted to Mel spectrograms before being passed into a pre-trained Vision Transformer, and finally a MiniROCKET model. Additionally, data augmentation was conducted on audio files and spectrograms to generate new data, extending our total sample size from 928 spectrograms to 14,848. Results: Compared to the existing methods in the literature, our model yielded significantly enhanced quality assessment metrics, including Weighted Accuracy, Sensitivity, and F-Score, and resulted in a fast evaluation speed of 0.02 s per patient. Conclusions: The implementation of our method for the detection of heart murmurs can supplement physician diagnosis and contribute to earlier detection of underlying cardiovascular conditions, fast diagnosis times, increased scalability, and enhanced adaptability.

1 July 2025 in Orphanet Journal of Rare Diseases
Verified
Journal Article
Open access
PDF file
AVAnastasiia Vasileva
Anastasiia Vasileva
JWJoyce K. Y. Wu
Joyce K. Y. Wu
MVMelissa Valaee
Melissa Valaee
EOEthan Ortiz
Ethan Ortiz
ZHZoltán Hantos
Zoltán Hantos
CCChung-Wai Chow
Chung-Wai Chow
Background: Fibrodysplasia ossificans progressiva (FOP) is an ultra-rare genetic bone disease that is characterized by progressive heterotopic ossification of the thoracic cavity. Prognosis is poor with cardiopulmonary complications being the main cause of death. Spirometry is a well-established metric of functional exercise capacity and prognosis in lung diseases but its use is limited in this population. Accuracy and validity of spirometry is dependent on forced expiratory maneuvers which are difficult to perform for individuals with FOP. Oscillometry is an effort-independent pulmonary function test that is highly sensitive to changes in respiratory mechanics. Little is known about oscillometry in individuals with FOP. The purpose of this paper is to characterize FOP using oscillometry. Results: Eight participants with FOP were recruited for oscillometry prior to spirometry. Cumulative Analogue Joint Involvement Scale (CAJIS) scores were used to evaluate total body and regional FOP burden. Spirometry showed a uniform pattern of restrictive physiology in all eight participants with no significant difference amongst the group. Oscillometry revealed significant diversity in respiratory mechanics and chest wall involvement from normal, airway obstruction and ventilatory inhomogeneity to extra-thoracic airflow obstruction. We compared individuals with normal and abnormal oscillometry and found no statistically significant differences in functional status and clinical parameters. However, there is a tendency for lower CAJIS scores and fewer recent flare-ups in those with more normal respiratory mechanics. The tidal volumes were significantly higher in the group with more normal respiratory mechanics. Two wheelchair-dependent participants exhibited a pattern of high respiratory resistance that increased during both inspiration and expiration, to suggest presence of a fixed extra-thoracic defect. Conclusions: Oscillometry provides additional, more detailed information beyond spirometry in individuals with FOP. It is far easier than spirometry to complete and may be useful to help track disease progression and response to therapies in individuals with FOP.