#machinelearning Tag

07 Jun

Posted at 00:31h in Author Interviews, Diabetes, Technology
MedicalResearch.com Interview with: [caption id="attachment_74111" align="alignleft" width="92"]Luis A. Rodriguez, PhD, MPH, RDResearch Scientist, Kaiser Permanente Northern California Division of Research Assistant Professor, Department of Health System Sciences Kaiser Permanente Bernard J. Tyson School of Medicine Assistant Adjunct Professor, Department of Epidemiology & Biostatistics University of California, San Francisco Dr. Rodriguez[/caption] Luis A. Rodriguez, PhD, MPH, RD Research Scientist, Kaiser Permanente Northern California Division of Research Assistant Professor, Department of Health System Sciences Kaiser Permanente Bernard J. Tyson School of Medicine Assistant Adjunct Professor, Department of Epidemiology & Biostatistics University of California, San Francisco ADA 2026 Poster Presentation: Machine-Learning Modeling for T2DM Prediction in over 3 Million Adults American Diabetes Association 85th Scientific Sessions, June 2026
MedicalResearch.com: What is the background for this study? What are the risk factors used to develop the prediction model? Response: Type 2 diabetes develops gradually over many years, often without clear warning signs. As a result, it can be difficult for health systems to identify which adults are most likely to benefit from prevention efforts before the disease develops. In this study, we used electronic health record data from more than 3 million adults in Kaiser Permanente Northern California to develop a prediction model that estimates an individual's risk of developing type 2 diabetes over 1, 3, and 10 years. The model is based on information routinely collected during clinical care, including age, sex, race/ethnicity, body mass index, blood glucose levels, smoking, physical activity, medical and family history, and medication use. By combining these clinical, biological and behavioral factors, the model provides a more comprehensive assessment of diabetes risk than traditional screening approaches.

11 Mar

Posted at 17:32h in Trials
clinical-trials-faster-research-outcomes Clinical trials are essential for advancing medical science and developing new treatments. However, the process can often be slow and cumbersome, delaying the delivery of innovative therapies to patients in need. Emerging technologies are transforming this landscape, providing tools that make clinical trials more efficient and effective. As you explore the world of clinical trials, understanding the importance of efficient tools becomes paramount. These tools significantly accelerate clinical trial timelines, ensuring quicker access to vital medical interventions. The healthcare industry is witnessing a rapid evolution in how research is conducted, with technology playing a pivotal role in this transformation. Platforms like Patiro are instrumental in this shift, offering innovative ways to connect qualified patients with clinical trials.

The Impact of Technology on Clinical Trials

Technology is reshaping the way clinical trials are conducted, primarily by reducing enrollment delays. This crucial phase often poses significant challenges due to stringent criteria and the necessity for a diverse pool of participants. With advanced platforms leveraging data analytics and AI-driven solutions, researchers can swiftly identify and recruit suitable candidates. This expedites the process and enhances the quality of research outcomes by ensuring a representative sample. The integration of digital tools has further enabled remote monitoring and virtual trials, reducing geographical barriers that traditionally hindered participant enrollment. This shift broadens access and allows continuous data collection in real-time, increasing accuracy and reliability. The time saved in these processes directly contributes to faster trial completion and quicker dissemination of results. In addition to enrollment efficiencies, technological innovations facilitate better data management throughout the trial phases. Automation in data entry and processing minimizes human error, maintaining high standards of accuracy and compliance. Consequently, this fosters a more streamlined workflow, significantly cutting down on administrative burdens faced by research teams. Machine learning algorithms have revolutionized patient matching and protocol optimization, reducing the time spent on manual screening processes by up to 60%. These intelligent systems can analyze vast amounts of electronic health records, identifying potential participants who meet specific trial criteria within minutes rather than weeks. Additionally, predictive analytics help researchers anticipate and address potential bottlenecks before they impact trial timelines, ensuring smoother execution throughout the study lifecycle.

05 May

Posted at 23:27h in Author Interviews, Cancer Research, COVID -19 Coronavirus, Technology
MedicalResearch.com Interview with: [caption id="attachment_57335" align="alignleft" width="150"]Saket Navlakha PhD Simons Center for Quantitative Biology Cold Spring Harbor Laboratory Cold Spring Harbor, NY Dr. Navlakha[/caption] Saket Navlakha PhD Simons Center for Quantitative Biology Cold Spring Harbor Laboratory Cold Spring Harbor, NY  MedicalResearch.com: What is the background for this algorithm? How does it aide in patient care? Response: The machine learning algorithm helps to predict if and when a patient will develop severe COVID symptoms, based on information on how the patient presents on the day of infection. This could lead to improved patient outcomes, by getting a “heads up” on what may happen in the near future.