MIT Horizon ’s Post

🔬 Excited to share our latest journal paper! 🧠 Our study, "A Time-Dependent Explainable Radiomic Analysis from the Multi-Omic Cohort of CPTAC-Pancreatic Ductal Adenocarcinoma", explores how combining radiomic, clinical, and mutational data can improve risk stratification for PDA prognosis. We used survival machine learning models and time-dependent explainability techniques to understand how multi-omic predictors impact prognosis at different timeframes. 📜 Read more: https://lnkd.in/d3iiGzRg #AI #Radiomics #MultiOmics #PancreaticCancer #SurvivalMachineLearning

🌟 Harnessing AI for Patient Benefit 🌟 I was honored to present on behalf of the Pathways development team at the #Bayer #researchanddevelopment science conference in Berlin, Germany, our clinical decision support system (#CDSS) designed for healthcare professionals managing Chronic Kidney Disease (#CKD) patients. During my presentation, I highlighted three critical lessons learned in developing this explainable AI tool: 𝟏. 𝐄𝐱𝐩𝐥𝐚𝐢𝐧𝐚𝐛𝐢𝐥𝐢𝐭𝐲: It’s essential that such algorithms provide clear, understandable results for both healthcare professionals and patients. 𝟐. 𝐔𝐬𝐚𝐛𝐢𝐥𝐢𝐭𝐲 𝐚𝐧𝐝 𝐀𝐜𝐭𝐢𝐨𝐧𝐚𝐛𝐢𝐥𝐢𝐭𝐲: The insights generated must be practical and actionable, guiding clinical decisions effectively. 𝟑.𝐓𝐫𝐮𝐬𝐭𝐰𝐨𝐫𝐭𝐡𝐢𝐧𝐞𝐬𝐬: Robust validation is key, as many algorithms currently lack sufficient testing and reliability. I had the privilege of sharing the stage with experts in drug discovery, clinical development, gene therapy, artificial intelligence, and data sciences. Together, we explored groundbreaking scientific advancements that address the pressing medical challenges faced by patients and healthcare providers. A special shout out to Ghaith Sankari for pioneering the implementation of graph neural networks (#GNN) in our explainable AI model (#XAI), and to Paula Salme Sandrak, Nicolas Bertrand, and the entire integrated care team for turning our vision into reality. Let’s continue to innovate for better patient outcomes! 💡🤝 #AIinHealthcare #MedicalInnovation #PatientCare #ChronicKidneyDisease #Cardiology #Prediction #scienceoftomorrow #healthforall

I want to bring your attention to the fifth seminar of the "AI & Health" series hosted by HC@AIxIA, i.e., the "Artificial Intelligence for Healthcare" working group of the Italian Association for Artificial Intelligence. Save the date: May 9th, 4:30 PM (CEST). Please feel free to share this with anyone who is interested. All information for participating is available at https://lnkd.in/eQp963bf #AI #digitalhealth #prediction #oncology

Exploration of Targeted Anti-tumor Therapy | Open Exploration A Noteworthy Review---Just Published👇 📢 Artificial intelligence and classification of mature lymphoid neoplasms ------------------------- 📖 This paper showed several examples of the use of machine learning and neural networks to predict the prognosis and to classify mature B-cell neoplasms. Prediction of lymphoma subtypes based on conventional cell-of-origin markers was also calculated using a neural network. In the future, it is expected that AI will be incorporated into the classification as another bioinformatics tool to analyze complex data. From: Joaquim Carreras*, Rifat Hamoudi, Naoya Nakamura 🍸 Enjoy reading！ https://lnkd.in/gKtNGdka #ArtificialIntelligence, #MachineLearning, #DeepLearning, #ArtificialNeuralNetworks, #NonHodgkinLymphomas, #PanCancerSeries, #Prognosis, #GeneExpression

🚨 Welcome to your mid-week AI news roundup 🚨 Here is this week’s selection of top AI stories that you DO NOT want to miss 👇🏻 🩺 Researchers have received a $27.8 million grant to use AI for precision treatment of rectal cancer. Using AI to analyse MRI scans, scientists aim to derive specific metrics to understand rectal tumour responses to therapy better, helping evaluate tumour regression. 👵🏻 Using GPT-3.5, MIT Researchers have developed a chatbot that allows individuals to have conversations with simulations of their future selves, aiming to provide insights and facilitate personal growth by envisioning future experiences and outcomes. 💊 An AI-powered programme named TopoFormer has been developed by researchers, it aims to revolutionise drug discovery by efficiently predicting the interactions between proteins and small molecules, essentially anticipating how effective a drug might be. 🍟 McDonald's is discontinuing AI-powered ordering at its US drive-throughs following widespread unreliability, with plans to end its current partnership with system developer IBM by July while exploring future voice ordering solutions by year-end. Which news story has captivated your attention the most this week? Let us know in the comments below 💬 #aiupdates #ainews #ai #artificialintelligence #digitalinnovation

https://lnkd.in/d6n8ntnf AI traces mysterious metastatic cancers to their source (Prediction of tumor origin in cancers of unknown primary origin with cytology-based deep learning) https://lnkd.in/dedzexRY A very nice technical accomplishment. But I challenge the notion that "Accurate prediction of primary sites by pathologists and oncologists is a top priority for effective and personalized treatment." The "personalized" part may be correct in that statement; The "Effective" inference is a vast overreach in solid malignancies.

Diagnosis of ovarian cancer using the application of AI Artificial intelligence (AI), including machine learning (ML) and deep learning, has the potential to revolutionize biomedical research. Defined as the ability to “mimic” human intelligence by machines executing trained algorithms, AI methods are deployed for biomarker discovery. Most AI models associated with ovarian cancer have yet to be applied in clinical settings, and imaging data in many studies are not publicly available. Low disease prevalence and asymptomatic disease limit the data availability required for AI models.

@FrontiersIn this is not enough. You do not reveal what the comments were from this review process from reviewers and editors nor you respond to the comments that suggested that the text might have been generated with #AI. You do not provide either an open forum on this post where scientists can express their concerns and worries due to the serious breach that this article may have caused on the quality of the science generated by this house’s journals. For those who did not see this, there was an outcry from the community due to #AI generated images containing garbled text and strange images for an article in a Frontiers journal with an impact factor of 5.5. This blog entry by an independent reader describes the problem: https://lnkd.in/dkBUe3wZ As Associated Editor of Frontiers in Genetics, I am questioning my association to this publisher given the gravity of this issue. https://lnkd.in/dZrNyhD6

The advancement of AI in healthcare is making strides, particularly in diagnostics and personalized medicine. Major tech companies are collaborating with medical research institutes to leverage AI in areas like early cancer detection, drug discovery, and genetic analysis. Machine learning algorithms now assist in analyzing vast datasets from clinical trials, radiology scans, and genomics to provide more accurate and faster diagnoses. The use of AI is also helping in developing personalized treatment plans, improving patient outcomes, and reducing healthcare costs globally #ai #innovations #technology

I am particularly proud of sharing with you our latest paper on the segmentation of individual plasma cells in Multiple Myeloma. Three are the reasons that make me proud of it: 1. we showed that our hybrid approach combining heuristic methods and AI offers superior performance compared to the state-of-the-art 2. we carefully demonstrated the performance in instance segmentations and not only at pixel level, particularly on fused or poorly represented cells 3. we worked with a group of Master Degree students (Cristina Cattelino, Bruna Cotrufo, Matteo Giacosa, and Chiara Giovanzana) attending the course on Medical Imaging @ #PoliTO, whom are co-Authors of the paper That's our proposal for merging technical improvement to innovative teaching methods. Special thanks to prof. Kristen M. Meiburger, Dr. Nicola Michielli and Prof. Massimo Salvi. https://lnkd.in/dFCaDF4q #ai #medicalimaging #polito #digitalpathology #imageprocessing