ON-DEMAND
Session Videos
& Presentations 

AI in Ultrasound: The Value in Imaging Centers, Home Care and Rural Settings 

AI in ultrasound practice and approved technologies will be covered in the first segment of this talk.

Current challenges in ultrasound practice and the role of AI enhanced ultrasound in addressing these challenges will be covered on the second segment.

The future role of AI ultrasound in home care and rural settings will be covered on the third segment of this talk. 

• How can semi-supervised learning techniques be utilized for image classification in radiology?
• What are the advantages and limitations of semi-supervised learning compared to traditional supervised learning in radiology image classification?
• How can unlabeled data be effectively leveraged in combination with limited labeled data to improve the performance of image classification models?
• What are the common semi-supervised learning algorithms and methodologies employed in radiology image classification?

• How can high-throughput screening (HTS) techniques be accelerated and optimized using AI in the context of drug discovery?
• What are the challenges and limitations of traditional HTS approaches, and how can AI help overcome them?
• How can AI algorithms and machine learning models be applied to analyze and interpret large-scale HTS data for identifying potential drug candidates?
• What are the different strategies and methodologies for integrating AI with HTS workflows to improve the efficiency and effectiveness of drug discovery?
• How can AI-driven virtual screening techniques be utilized to prioritize and identify promising compounds for further experimental validation?

• How does bias in AI affect healthcare decision making?
• How can we measure bias?
• How can we think about mitigating it?

Marginalized patient populations continue to experience healthcare disparities based on racial and cultural identities, and socioeconomic segregations. There is a pressing need to dismantle the healthcare privileges of those different patient communities within the same geographic population.  The goal of this research is to bridge the gap between healthcare access and different marginalized patient groups.

The proposed research will use information gathered to identify the root causes of health inequities among different patient groups using modern artificial intelligence (AI) methodologies. Then recommend sustainable and practical interventions based on the AI driven integrated frameworks. These interventions and solutions are intended to create more equitable access to medical care, and improve healthcare outcomes in our local marginalized populations. 

• Unveiling AI’s transformative potential in healthcare: Tailored strategies to alleviate nursing burnout.
• Real-life success stories: How AI adoption can lead to a more manageable workload and improved nurse well-being.
• Building the future of nursing: Leveraging AI to foster a resilient, supportive, and efficient nursing work environment.

What are the challenges of traditional manual approaches for adjudication of adverse events?

How can AI support the adjudication of adverse events?

What are the potential applications of natural language processing (NLP) and machine learning in automating adverse event adjudication?

• What are the benefits of using AI and IoT in remote patient monitoring compared to traditional methods?
• How can wearable devices equipped with sensors and AI algorithms collect and analyze real-time patient data, such as vital signs, activity levels, sleep patterns, or medication adherence?
• What are the challenges and considerations in implementing AI-powered remote patient monitoring, including data security, data integration, and user acceptance?
• How can AI algorithms detect and alert healthcare providers to anomalies or critical events in patient data, enabling timely interventions and proactive care?
• How can remote patient monitoring using AI and IoT improve patient outcomes by enabling early detection of deteriorating health conditions and reducing hospital readmissions?

• How can machine learning-based Clinical Decision Support Systems (CDSS) be utilized to predict patient outcomes?
• What are the advantages of using machine learning in predicting patient outcomes compared to traditional methods?
• What types of data sources, such as electronic health records, imaging data, or genomic data, can be integrated into machine learning models for outcome prediction?
• How can machine learning algorithms be trained to analyze and interpret complex patient data to predict clinical outcomes, such as disease progression, treatment response, or adverse events?
• What challenges and considerations are in developing machine learning models for predicting patient outcomes, including data quality, feature selection, and model explainability?

In an era defined by rapid technological advancements, "Navigating the Future: A Blueprint for Ethical and Responsible AI Governance" delves into the pivotal intersection of artificial intelligence and governance.

This abstract invites participants to explore strategies and frameworks aimed at steering AI development towards ethical horizons. Addressing the challenges of bias, transparency, and accountability, the session seeks to cultivate a nuanced understanding of responsible AI governance. Attendees will embark on a journey to construct a robust blueprint for their organizations, that not only guides the ethical deployment of AI but also fosters inclusivity and social responsibility in the ever-evolving landscape of technological innovation. Furthermore, the session will explore principles of fairness, transparency, and ethical stewardship and current progress in making AI explainable.

• How can machine learning be used to predict drug response and optimize personalized treatment plans?
• What are the advantages of using machine learning in predicting drug response compared to traditional approaches?
• What types of data sources, such as genomic data, clinical data, or biomarker data, are utilized in machine learning models for predicting drug response?
• How can machine learning algorithms be trained to analyze and interpret complex data to predict individual patient responses to specific drugs or treatments?