est 110 padlet by Destiny Vega

destinyvega — 2025-10-13 00:56:06 UTC

Artificial intelligence is one factor that has been changing our healthcare field in many ways. Whether it's from diagnosing diseases, managing patients, or just simply doing normal hospital tasks. Machine learning and deep learning models can analyze medical images like X-rays, CT scans, and MRIs to help doctors make faster and more accurate diagnoses. AI also uses data from “AI-powered wearables” to monitor patients remotely and predict health problems before they worsen. It even helps with scheduling and billing, so that doctors can spend more time focusing on their patients. I chose healthcare because I am currently a health science major on the pre-med track, eventually aiming to go to PA school or med school. Therefore, I am curious about how AI can help improve patient care while also changing the role of doctors. In this Padlet, I’ll look at different examples of AI in healthcare. The ones that seem most of interest to me are the diagnostic imaging tools that assist radiologists, different medicine platforms that use genomic and clinical data to personalize cancer treatments, and the use of AI-powered wearables that help manage chronic conditions and monitor patients from home. My goal is to explain how this technology works, the benefits and challenges it comes with, and also discuss its future trends in healthcare with the help of AI.

AI in Diagnostic Imaging

destinyvega — 2025-10-13 01:14:24 UTC

Description: AI is now changing how radiologists read medical images by helping identify things like lung nodules, fractures, or early signs of stroke. This helps doctors get a head start with the more “urgent” cases.

Technology: Use of deep learning and computer vision, mainly convolutional neural networks (CNNs), trained on large imaging datasets. These tools are often built into hospital systems like PACS or clinical decision support software.

Benefits: Faster, better detection of small or early abnormalities reduces workload for radiologists and helps with earlier diagnoses for patients.

Challenges: Its real-world performance can drop compared to lab results, training data can be biased, and regulations are complex; therefore, incorporating AI into hospital workflows can be overall difficult.

Personal Insight: I think this is important because medical imaging produces so much data, and even small time savings can make a huge difference in saving lives. But it’s important to make sure these tools are clinically validated and work fairly across different patient populations.

AI in Precision Medicine

destinyvega — 2025-10-13 01:30:45 UTC

Description: These platforms take in genomic sequencing data, pathology reports, and clinical records to suggest personalized cancer treatments or clinical trials for each patient.

Technology: They use machine learning on large datasets, natural language processing (NLP) to read clinical notes, and predictive models that help match patients to the most effective therapies.

Benefits: More accurate treatment recommendations, quicker identification of key genetic mutations, and better matching to clinical trials.

Challenges: Issues like patent and legal disputes, privacy concerns with sensitive data, inconsistent data quality between hospitals, and high costs that limit accessibility.

Personal Insight: I think personalized medicine really shows the potential of AI in healthcare, but it also raises tough questions about access and fairness. For example, when I first learned about this, the one thing that came to mind was, who actually gets to benefit from these advanced tests?

Video Link: https://www.youtube.com/watch?v=CcDHQFIT5bQ

AI in Wearables/Patient Monitoring

destinyvega — 2025-10-13 01:39:21 UTC

Description: AI can analyze continuous vital sign data from wearables or bedside monitors to spot early warning signs such as heart rhythm changes or declining patient health. It even supports hospital-at-home programs.

Technology: Time series machine learning, sensor fusion, and edge computing to send real-time alerts, with cloud-based analytics to process large amounts of data.

Benefits: Helps detect problems earlier, reduces hospital readmissions, improves management of chronic conditions, and expands access to remote care.

Challenges: Accuracy can vary depending on skin tone or activity level, and there are still issues with device validation, regulatory approval, and protecting patient privacy.

Personal Insight: I think continuous monitoring could really transform how and where patients receive care, but it needs to be both clinically proven and fair for everyone to use safely

Video Link: https://www.youtube.com/watch?v=RVD8Ir-8q6I

destinyvega — 2025-10-13 01:49:16 UTC

AI in healthcare is rapidly advancing toward systems that combine multiple types of medical data, such as imaging, genomics, electronic health records, and wearable device data, to create more complete predictive models and individualized treatment plans. By connecting these different data sources, AI could one day provide doctors with a real-time overview of a patient’s health. Another major development is the use of federated learning. This allows hospitals and research institutions to train AI models together without sharing sensitive patient data. This will then help improve performance while protecting privacy. Edge AI is also becoming more common, where algorithms run directly on medical devices like these wearables that were previously discussed or bedside monitors to provide faster responses and reduce the need for constant internet access. In the future, we can expect stronger regulations requiring clinical trials and evaluations to make sure AI tools actually perform well in real-world conditions and not just in controlled research studies. Ethical challenges tend not to change though. For example, algorithmic bias is one major issue since some AI models can produce less accurate results for certain populations. Data privacy and consent are also huge concerns with questions like, “Who owns and controls genomic and health data, and how is it shared responsibly?” Patients and any healthcare worker need to understand how AI systems reach their diagnosis to trust them. Lastly, there’s the risk of over-automation. Relying too much on AI could reduce human judgment or widen health inequalities if advanced tools are only available to certain groups. Therefore, building transparent, diverse, and patient-centered AI systems will be crucial to making sure that technology is just a tool in healthcare and not just replacing providers.

destinyvega — 2025-10-13 02:03:58 UTC

Artificial intelligence has the potential to improve healthcare efficiency and patient outcomes, but it also brings several societal challenges that need attention. AI is likely to change the way healthcare professionals work. For example, radiologists might focus less on routine image reviews and more on analyzing complicated cases or collaborating with other healthcare providers, while new jobs like clinical AI specialists and data managers start to appear. At the same time, some administrative positions, such as scheduling or billing, could become automated, potentially reducing certain job opportunities. Privacy is another major concern because AI relies on large datasets, including genomic information and electronic health records, which can be misused or hacked. Strong security measures and patient consent are crucial to maintain trust. Equity is also a pressing issue. For example, AI models trained on incomplete or biased data can unintentionally make healthcare disparities worse, giving underrepresented groups less accurate predictions or treatment recommendations. Access and cost are also major issues. Advanced AI diagnostics and genomic tools are often only available at large hospitals or private companies, which could widen the gap between resource-rich and resource-poor communities if reimbursement policies and public funding don’t support broader availability. Patient trust can also be affected, since some AI systems don’t explain their reasoning, which can make patients and even providers less confident. Finally, laws and regulations need to adapt to make it clear who is responsible and accountable when AI systems are used to make healthcare decisions. Overall, the societal impact of AI depends less on the technology itself and more on its well-planned policies, design, and public service that prioritize equity, privacy, and access, to ensure that AI benefits all patients possible.

destinyvega — 2025-10-13 02:09:55 UTC

Researching AI in healthcare showed me how quickly these tools are moving from prototypes to real clinical use and how important it is to validate them properly. I realized that AI has a lot of technical potential, like improving detection, personalizing treatments, and monitoring patients. But, it also comes with ethical responsibilities such as privacy, fairness, and transparency. One challenge I faced was that there were many sources that were reliable, so it was a bit difficult to just choose a few because there was still so much information out there to dive into. This project also helped make me more aware of the importance of AI in healthcare, which made me interested in how policies and hospital settings need to adapt so that AI benefits all patients, not just those who have access to advanced medical centers.

destinyvega — 2025-10-13 02:19:38 UTC

Bajwa, J., Munir, U., Nori, A., & Williams, B. (2021, July). Artificial Intelligence in healthcare: Transforming the practice of medicine. Future healthcare journal. https://pmc.ncbi.nlm.nih.gov/articles/PMC8285156/

D’Adderio, L., & Bates, D. W. (2025, January 24). Transforming diagnosis through Artificial Intelligence. Nature News. https://www.nature.com/articles/s41746-025-01460-1

Ai in clinical research: Opportunities, limitations, and what comes next. AI in Clinical Research: Opportunities, Limitations, and What Comes Next | Harvard Medical School Professional, Corporate, and Continuing Education. (2025, June 24). https://learn.hms.harvard.edu/insights/all-insights/ai-clinical-research-opportunities-limitations-and-what-comes-next

Characterizing the clinical adoption of medical AI devices through U.S. insurance claims | Nejm AI. (n.d.). https://ai.nejm.org/doi/full/10.1056/AIoa2300030

Ai-enabled Precision Medicine. Tempus. (2025, September 24). https://www.tempus.com/?srsltid=AfmBOooDW7JI0JzYHcdAnxr6zZ39Ltug9jdzDyvbojeR2ZQVT4Wh8guD

How AI is changing The way your doctor performs surgery. Medtronic News. (n.d.). https://news.medtronic.com/how-ai-is-changing-the-way-your-doctor-performs-surgery-newsroom

destinyvega — 2025-10-13 03:09:37 UTC

**It did not allow me to upload videos or create a video unless I paid for the upgraded version, so I just did a voice recording.**