AI, Transforming Patient Care or Raising Alarm?
Published in Healthcare & Nursing, Computational Sciences, and Biomedical Research
In the era of rapid technological advancements, Artificial Intelligence (AI) is revolutionizing the healthcare industry. But as we welcome this new era, it brings along questions and concerns. On "AI Rx: Transforming Patient Care or Raising Alarm?" we delve deep into the dual facets of AI in healthcare. Each episode explores how AI is enhancing patient care, from cutting-edge diagnostics and personalized treatment plans to robotic surgeries and virtual health assistants. We feature experts, practitioners, and patients who share their firsthand experiences and insights on how AI is shaping the future of medicine. However, every silver lining has its cloud. We also tackle the ethical dilemmas, privacy issues, and potential pitfalls of relying on AI. Will AI's involvement lead to a more efficient healthcare system, or are we venturing into a territory fraught with risks? Join us on this journey as we unravel the promises and perils of AI in patient care, bringing you stories that inform, inspire, and provoke thought. Whether you're a healthcare professional, tech enthusiast, or simply curious about the future of medicine, this podcast is for you. Please refer to the systematic review for a more comprehensive view and share your thoughts.
There is a fine balance between ethics, privacy, and healthcare innovation. Overattention to on one side of the equation can compromise the other. My research is focused on finding the right balance so that we can provide physicians with AI-assisted guidance during expert discussions. You can hear more about it in the "AI | Balancing Data and Ethics in Healthcare Innovation
(A brief summary of the main aspects is also presented in the Techno-Docs | Bridging Medicine and AI short episode).
Background: Recent reviews on the use of AI for improving healthcare have predominantly focused on data sources such as electronic health records (EHR) and individual patient care in areas such as automatic image analyses (e.g., skin cancer), surgery, oncology, psychiatry, and clinical decision support. Over the past decade, there has also been considerable investment and attention in the field of physician-patient communications. Nevertheless, a recent systematic review of the literature suggests that inter-physician collaboration is still in the development stage. This study was conducted in a niche within this space. Thus, we anticipated that a small number of articles would address the research question. A limited body of literature has investigated how AI systems can collaborate with physicians to (a) assist in decision-making and (b) generate new data based on physicians’ experiences and knowledge so that the broader medical community (and additional stakeholders) can leverage that knowledge to drive innovation and better outcomes in healthcare. By stakeholders, we refer to the participating and interested entities that are either responsible for or affected by health- and healthcare-related decisions. While patients and physicians are the main stakeholders in this context, other potential stakeholders include policymakers, healthcare providers, payers, medical research entities, and pharmaceutical companies. This literature review aimed to synthesize evidence of the potential of leveraging physician-generated real-world data (RWD) captured through secure and HIPAA-compliant Professional Medical Chats (PMCs) for real-time AI-based insights.
Research Question: This study aims to address the following research question: How can physician-generated real-world data and cutting-edge AI be combined to generate valuable insights for healthcare stakeholders to create new business opportunities and/or improve patient care outcomes?
Contribution: This SLR builds upon and contributes to the growing research interest in AI and NLP for communication between physicians and patients, providing an additional perspective by tapping into the opportunities and challenges of applying AI to real-world data (RWD) generated by physician-to-physician communication. It provides future directions for healthcare leaders and researchers: physician-generated data through spontaneous, informal, and unsupervised professional communication may generate insights based on physicians’ real-life experiences that are not widely available or accessible and unfold the considerable, yet underleveraged, potential of physician-generated RWD to improve patient outcomes and healthcare efficiency.
I graduated with honors in computer engineering from PUC-Rio, with an MBA at the Wharton School of the University of Pennsylvania and a specialization in innovation through AI in healthcare from Harvard T.H. Chan School of Public Health. Over the past two decades, I led global initiatives at Microsoft Research—Health Solutions Group and co-founded the Microsoft Azure global business development team. I am passionate about the intersection of AI and medicine, and in particular how we can best empower physicians with AI in a responsible, ethical, innovative, and trustworthy manner. I believe in collaboration between academia and industry, and I am an advisor for several startup founders and a mentor in global organizations like MassChallenge and TechStars.
Follow the Topic
-
Neural Processing Letters
Neural Processing Letters is an international journal for rapid exchange of research on artificial neural networks and machine learning. It covers novel architectures, learning algorithms, deep nets, optimization, and applications in AI, robotics, big data, and more.
Related Collections
With Collections, you can get published faster and increase your visibility.
Machine Learning for Human Activity Recognition and Analysis
Human Activity Recognition (HAR) has emerged as a critical research domain at the intersection of sensing technologies, biomedical engineering, and artificial intelligence. By leveraging diverse signal modalities and advanced machine learning algorithms, HAR systems enable the analysis and interpretation of complex human behaviors across multiple application domains, including remote health monitoring, rehabilitation, assisted living, occupational safety, and adaptive human-computer interaction. Data-driven insights from HAR systems can inform clinical decision-making, optimize personalized health interventions, enhance elderly care, and improve user experiences in interactive technologies.
Recent advancements in sensing technologies and data collection methods—such as wearable sensors, mobile devices, and Internet of Things (IoT) systems—have revolutionized the HAR landscape. Modern systems now integrate multiple signal modalities, including inertial measurements (accelerometry, gyroscopy, magnetometry), physiological biosignals (ECG, EMG, EEG, PPG, respiration), acoustic and environmental signals, as well as video and radar data. When combined with sophisticated machine learning and deep learning techniques, these multimodal datasets facilitate accurate and context-aware recognition and analysis of human activities.
Despite rapid progress, challenges remain in developing comprehensive, well-annotated databases of physiological and behavioral signals. Ensuring data quality, annotation consistency, sensor placement standardization, and population diversity are essential for generalizable and reliable HAR models. Future advancements are expected to emphasize multimodal data fusion, explainable and interpretable AI models, edge computing for real-time processing, and privacy-preserving learning techniques such as federated learning. These innovations will be critical in enabling robust, adaptive, and personalized HAR systems.
This Collection aims to advance the state-of-the-art in HAR by exploring innovative approaches to signal processing, feature engineering, and machine learning. We welcome contributions addressing critical challenges, including:
- Identifying which signal modalities provide the most discriminative information for specific activity classes
- Developing multimodal fusion strategies to combine heterogeneous sensor streams
- Advancing deep learning architectures suited for temporal and spatial activity modeling
- Enhancing model interpretability, generalization, and energy efficiency
- Addressing real-world deployment constraints in clinical, industrial, and consumer applications
Topics of Interest Include (but are not limited to):
- Signal Modalities and Sensing Technologies: Inertial, physiological, acoustic, radar, and vision-based sensing
- Data Collection and Benchmarking: Sensing protocols, annotation methodologies, database construction, data quality assessment
- Signal Processing and Feature Engineering: Time-series analysis, wavelet transforms, feature selection, dimensionality reduction
- Multimodal Data Fusion: Early, late, and hybrid fusion strategies; attention-based fusion mechanisms
- Machine Learning and Deep Learning: CNNs, RNNs, LSTMs, Transformers, GNNs, attention mechanisms for activity recognition
- Transfer Learning and Domain Adaptation: Cross-subject, cross-dataset, and cross-device generalization
- Real-World Implementation: Edge AI, energy-efficient models, privacy-preserving and federated learning techniques
- Clinical and Healthcare Applications: Fall detection, gait and posture analysis, rehabilitation assessment, mental health monitoring
This Collection supports and amplifies research related to- SDG 11: Sustainable Cities & Communities; SDG 9: Industry, Innovation & Infrastructure; SDG 3: Good Health & Well-Being
We invite researchers to submit their work to this Collection, which will showcase innovative research addressing these and related topics in machine learning-driven human activity recognition and analysis.
Publishing Model: Open Access
Deadline: Jul 15, 2026
Please sign in or register for FREE
If you are a registered user on Research Communities by Springer Nature, please sign in