Human retinal ganglion cell neurons generated by synchronous BMP inhibition and transcription factor mediated reprogramming

Agarwal, Devansh; Dash, Nicholas; Mazo, Kevin W.; Chopra, Manan; Avila, Maria P.; Patel, Amit; Wong, Ryan M.; Jia, Cairang; Do, Hope; Cheng, Jie; Chiang, Colette; Jurlina, Shawna L.; Roshan, Mona; Perry, Michael W.; Rho, Jong M.; Broyer, Risa; Lee, Cassidy D.; Weinreb, Robert N.; Gavrilovici, Cezar; Oesch, Nicholas W.; Welsbie, Derek S.; Wahlin, Karl J.

doi:10.1038/s41536-023-00327-x

Cited by 4 publications

(1 citation statement)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning and deep learning breakthroughs in recent years have revolutionized the area of medical data analysis 15,16,17 . These strategies have shown great potential in a variety of healthcare applications, including medical picture analysis, disease diagnosis, drug development, and personalized medical care recommendations 18,19,20 . Support Vector Machines, Random Forests, Decision Trees, K-Nearest Neighbors, Gaussian Naïve Bayes, Gradient Boosting, Adaptive Boosting, Random Undersampling Boosting, and Logistic Regression are examples of machine learning algorithms that have proved successful in discovering patterns and predicting outcomes in medical datasets 21,22,23 .…”

Section: Introductionmentioning

confidence: 99%

Identification of Myocardial Infarction (MI) Probability from Imbalanced Medical Survey Data: An Artificial Neural Network (ANN) with Explainable AI (XAI) Insights

Akter,

Pias

et al. 2024

Preprint

View full text Add to dashboard Cite

In the healthcare industry, many artificial intelligence (AI) models have attempted to overcome bias from class imbalances while also maintaining high results. Firstly, when utilizing a large number of unbalanced samples, current AI models and related research have failed to balance specificity and sensitivity – a problem that can undermine the reliability of medical research. Secondly, no reliable method for obtaining detailed interpretability has been put forth when addressing large numbers of input features. The present research addresses these two critical research gaps with a proposed lightweight Artificial Neural Network (ANN) model. Using 43 input features from the 2021 Behavioral Risk Factor Surveillance System (BRFSS) dataset, the proposed model outperforms prior models in producing balanced outcomes from markedly unbalanced large survey data. The efficacy of this proposed ANN model is attributed to its simplified design, which reduces processing demands, and its resilience in identifying the probability of myocardial infarction (MI). This is demonstrated by its 80% specificity and 77% sensitivity, and is substantiated by a Receiver Operating Characteristic Area Under the Curve (AUC) of 0.87. The outcomes across the scopes of each specified data domain were also separately represented, thus demonstrating the proposed model’s robust sensitivity. The interpretability of the model, as measured by Shapley values, reveals substantial correlations between myocardial infarction (MI) and its risk factors, including long-term medical conditions, socio-demographic factors, personal health habits, economic and social status, healthcare availability and affordability, as well as impairment statuses, providing valuable insights for improved cardiovascular risk assessment and personalized healthcare strategies.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Myocardial Infarction (MI) Probability from Imbalanced Medical Survey Data: An Artificial Neural Network (ANN) with Explainable AI (XAI) Insights

Akter,

Pias

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Traumatic Optic Neuropathy: Challenges and Opportunities in Developing Neuroprotective and Neuroregenerative Therapies

Tsai,

Gallo,

Pelaez

et al. 2024

Curr Ophthalmol Rep

View full text Add to dashboard Cite

Purpose of Review Traumatic optic neuropathy (TON) is a devasting disorder that can result in irreversible vision loss. Understanding the current research to promote neuroprotection and neuroregeneration of the optic nerve after injury may shed light on promising therapeutic avenues. Recent Findings With evolving methods to model traumatic optic neuropathy, recent work manipulating signal transduction and cell damage response pathways reveals new clinical opportunities for patients with traumatic injury to the optic nerve. Summary Despite years of basic science and clinical research, no treatment for TON exists. The absence of therapies highlights the importance of a comprehensive understanding of molecular pathways involved in retinal ganglion cell survival. Promising therapeutic opportunities may arise from a multi-pronged approach, targeting multiple pathways simultaneously in this complex disease.

show abstract

Timing and Graded BMP Signalling Determines Fate of Neural Crest and Ectodermal Placode Derivatives from Pluripotent Stem Cells

Chung,

Millet,

Rouillon

et al. 2024

Biomedicines

View full text Add to dashboard Cite

Pluripotent stem cells (PSCs) offer many potential research and clinical benefits due to their ability to differentiate into nearly every cell type in the body. They are often used as model systems to study early stages of ontogenesis to better understand key developmental pathways, as well as for drug screening. However, in order to fully realise the potential of PSCs and their translational applications, a deeper understanding of developmental pathways, especially in humans, is required. Several signalling molecules play important roles during development and are required for proper differentiation of PSCs. The concentration and timing of signal activation are important, with perturbations resulting in improper development and/or pathology. Bone morphogenetic proteins (BMPs) are one such key group of signalling molecules involved in the specification and differentiation of various cell types and tissues in the human body, including those related to tooth and otic development. In this review, we describe the role of BMP signalling and its regulation, the consequences of BMP dysregulation in disease and differentiation, and how PSCs can be used to investigate the effects of BMP modulation during development, mainly focusing on otic development. Finally, we emphasise the unique role of BMP4 in otic specification and how refined understanding of controlling its regulation could lead to the generation of more robust and reproducible human PSC-derived otic organoids for research and translational applications.

show abstract

Human retinal ganglion cell neurons generated by synchronous BMP inhibition and transcription factor mediated reprogramming

Cited by 4 publications

References 83 publications

Identification of Myocardial Infarction (MI) Probability from Imbalanced Medical Survey Data: An Artificial Neural Network (ANN) with Explainable AI (XAI) Insights

Identification of Myocardial Infarction (MI) Probability from Imbalanced Medical Survey Data: An Artificial Neural Network (ANN) with Explainable AI (XAI) Insights

Traumatic Optic Neuropathy: Challenges and Opportunities in Developing Neuroprotective and Neuroregenerative Therapies

Timing and Graded BMP Signalling Determines Fate of Neural Crest and Ectodermal Placode Derivatives from Pluripotent Stem Cells

Contact Info

Product

Resources

About