AI-Driven Predictive Models

Hot off our recent transformer paper, we're excited to share another AI model for precision medicine! Biological data collected from patients has exploded in recent years, presenting a challenge: how do we decipher that data to understand which patients will benefit most from specific therapies?  We in the Applied Data Science team at AstraZeneca are thrilled to share our paper in Cancer Cell called "AI-Driven Predictive Biomarker Discovery with Contrastive Learning to Improve Clinical Trial Outcomes." Here, we introduce the *Predictive Biomarker Modeling Framework (PBMF)*, a neural network-powered contrastive learning process that: 🔍 Explores vast multimodal datasets to uncover predictive biomarkers in an automated, systematic, and unbiased manner  🧠 Distinguishes predictive biomarkers (which indicate a likely benefit from a specific therapy) from prognostic biomarkers (which indicate general disease outlook)  💡 Distills its outputs into an interpretable decision tree, showing what drives treatment response In our studies, the PBMF:  📊 Surpassed existing methods in finding predictive biomarkers for immunotherapy success across various cancers in clinical trial and real-world data  📈 Discovered a predictive biomarker in an early-stage trial that boosted efficacy by 15% when retrospectively applied to the corresponding phase 3 clinical trial  📈 Discovered predictive biomarkers in single-arm early phase trial data with synthetic control arms, retrospectively improving the efficacy of the corresponding phase 3 trials by at least 10% We believe the PBMF has the potential to improve the way we design clinical trials and match patients to the right therapies. It can integrate with other models like our Clinical Transformer, creating exciting possibilities to someday discover biomarkers of adverse events, dosing strategies, and even to back-translate new drug targets. Read the full paper here: https://lnkd.in/eveAnVRY   Thanks to all the co-authors: Gustavo Arango, Damian Bikiel, Gerald Sun, Elly Kipkogei, Kaitlin Smith, Sebastian Carrasco Pro, Elizabeth Choe #PrecisionMedicine #ClinicalTrials #AIinHealthcare #Biomarkers #Immunotherapy

Traditional surrogate-based design optimization (SBDO) is hitting a wall, especially with high-dimensional, complex designs. In this new paper, Dr. Namwoo Kang presents a next-gen framework using generative AI, integrating three key models: - Generative model (design synthesis) - Predictive model (performance estimation) - Optimization model (iterative or generative) Rather than optimizing directly in a high-dimensional design space (x), the workflow introduces a low-dimensional latent space (z) learned via generative models. ➡️ z → x → y z = latent variables x = CAD geometry y = performance (drag, stress, etc.) This means we’re no longer hand-coding design parameters or doing trial-and-error with simplified surrogate models. 🧠 Why this matters: - Parametric modeling is no longer a bottleneck - Complex shapes are learned directly from CAD - Dynamic and multimodal performance data (1D, 2D, 3D) can be used - Near real-time optimization is possible #AI #GenerativeDesign #CAE #DesignOptimization

You might have seen news from our Google DeepMind colleagues lately on GenCast, which is changing the game of weather forecasting by building state-of-the-art weather models using AI. Some of our teams started to wonder – can we apply similar techniques to the notoriously compute-intensive challenge of climate modeling? General circulation models (GCMs) are a critical part of climate modeling, focused on the physical aspects of the climate system, such as temperature, pressure, wind, and ocean currents. Traditional GCMs, while powerful, can struggle with precipitation – and our teams wanted to see if AI could help. Our team released a paper and data on our AI-based GCM, building on our Nature paper from last year - specifically, now predicting precipitation with greater accuracy than prior state of the art. The new paper on NeuralGCM introduces 𝗺𝗼𝗱𝗲𝗹𝘀 𝘁𝗵𝗮𝘁 𝗹𝗲𝗮𝗿𝗻 𝗳𝗿𝗼𝗺 𝘀𝗮𝘁𝗲𝗹𝗹𝗶𝘁𝗲 𝗱𝗮𝘁𝗮 𝘁𝗼 𝗽𝗿𝗼𝗱𝘂𝗰𝗲 𝗺𝗼𝗿𝗲 𝗿𝗲𝗮𝗹𝗶𝘀𝘁𝗶𝗰 𝗿𝗮𝗶𝗻 𝗽𝗿𝗲𝗱𝗶𝗰𝘁𝗶𝗼𝗻𝘀. Kudos to Janni Yuval, Ian Langmore, Dmitrii Kochkov, and Stephan Hoyer! Here's why this is a big deal: 𝗟𝗲𝘀𝘀 𝗕𝗶𝗮𝘀, 𝗠𝗼𝗿𝗲 𝗔𝗰𝗰𝘂𝗿𝗮𝗰𝘆: These new models have less bias, meaning they align more closely with actual observations – and we see this both for forecasts up to 15 days, and also for 20-year projections (in which sea surface temperatures and sea ice were fixed at historical values, since we don’t yet have an ocean model). NeuralGCM forecasts are especially performant around extremes, which are especially important in understanding climate anomalies, and can predict rain patterns throughout the day with better precision. 𝗖𝗼𝗺𝗯𝗶𝗻𝗶𝗻𝗴 𝗔𝗜, 𝗦𝗮𝘁𝗲𝗹𝗹𝗶𝘁𝗲 𝗜𝗺𝗮𝗴𝗲𝗿𝘆, 𝗮𝗻𝗱 𝗣𝗵𝘆𝘀𝗶𝗰𝘀: The model combines a learned physics model with a dynamic differentiable core to leverage both physics and AI methods, with the model trained directly on satellite-based precipitation observations. 𝗢𝗽𝗲𝗻 𝗔𝗰𝗰𝗲𝘀𝘀 𝗳𝗼𝗿 𝗘𝘃𝗲𝗿𝘆𝗼𝗻𝗲! This is perhaps the most exciting news! The team has made their pre-trained NeuralGCM model checkpoints (including their awesome new precipitation models) available under a CC BY-SA 4.0 license. Anyone can use and build upon this cutting-edge technology! https://lnkd.in/gfmAx_Ju 𝗪𝗵𝘆 𝗧𝗵𝗶𝘀 𝗠𝗮𝘁𝘁𝗲𝗿𝘀: Accurate predictions of precipitation are crucial for everything from water resource management and flood mitigation to understanding the impacts of climate change on agriculture and ecosystems. Check out the paper to learn more:  https://lnkd.in/geqaNTRP

AI trained on 400,000 health records can model how multiple diseases progress across a lifetime, sometimes matching or beating standard risk tools. 1️⃣ Delphi-2M, a GPT-style model, predicted over 1,000 diseases with accuracy similar to CVD and dementia scores, and better for mortality. 2️⃣ It generated realistic health trajectories up to 20 years ahead and created synthetic patient data without exposing real identities. 3️⃣ Cancers drove long-term mortality risk, while heart attacks and sepsis risks faded within 5 years. 4️⃣ Biases in the UK Biobank (younger, healthier, less diverse) carried into the model, showing limits of training data. ✍🏻 Artem Shmatko, Alexander Wolfgang Jung, Kumar Gaurav, Søren Brunak, Laust Hvas Mortensen, Ewan Birney, Tom Fitzgerald, Moritz Gerstung. Learning the natural history of human disease with generative transformers. Nature. 2025. DOI: 10.1038/s41586-025-09529-3

Researchers have developed an AI model, Delphi-2M, capable of predicting a person’s risk of more than 1,000 diseases up to a decade in advance by analysing patterns in medical records. The model, trained on UK Biobank data and tested in Denmark, reportedly performs with impressive accuracy for conditions such as type 2 diabetes, heart attacks and sepsis. The idea is simple but transformative: a probabilistic “health forecast” akin to a weather report that identifies those at highest risk early enough for intervention and prevention. Beyond individual predictions, such models could help health systems anticipate population-level demand and plan services more effectively. Yet, as with all predictive AI, excitement should be tempered by caution. The model’s accuracy depends heavily on the completeness and representativeness of the underlying data. UK Biobank data, for example, skews toward middle-aged, healthier and higher-income participants, which may limit generalisability. There are also deeper questions: How do we ensure predictions empower rather than alarm patients? Who decides how and when preventive action should be taken? This research marks an important step toward predictive and preventive medicine. But realizing its potential will require rigorous validation, ethical oversight, transparent communication and trust between patients, clinicians and the technology. #AIinHealthcare #PredictiveAnalytics #DigitalHealth #HealthData #PrecisionMedicine #PreventiveHealth #HealthEquity #EthicsInAI #HealthcareInnovation #FutureOfMedicine https://lnkd.in/dB5kNxrc

Generative AI and simulations are revolutionizing forecasting by transforming it from a static, historical-based approach into a dynamic, adaptive system. Traditional forecasting methods struggle to handle complex interactions, sudden market shifts, and limited data. In contrast, AI-driven simulations can integrate real-time data, generate multiple possible future scenarios, and adjust predictions continuously as new information becomes available. By leveraging synthetic data generation, businesses can forecast even in situations where historical data is lacking, such as emerging markets or new product launches. AI also enhances risk management by enabling organizations to explore best-case, worst-case, and most likely scenarios, making forecasts more realistic and actionable. In the example below, we see AI agents mimicking the behavior of traders in the futures market, each assuming different roles with distinct behaviors and interests. These agents must open or close positions as various factors influence their strategies. The feedback mechanism relies on real market data, using mathematical approximations based on daily Open Interest, trading volume, price direction, volatility, and other key indicators.

AI Is Rapidly Catching—And Beating—Elite Human Forecasters Introduction Artificial intelligence is advancing beyond language generation into high-stakes prediction. In forecasting tournaments once dominated by elite human “superforecasters,” AI systems are now climbing leaderboards—and may soon outperform even the most accurate human teams. From Novelty to Contender • In 2024, no AI ranked within the top 100 of major forecasting competitions. • By late 2025, Mantic’s AI placed eighth in Metaculus’s Summer Cup. • In the Fall Cup, an upgraded version finished fourth, outperforming the weighted average of human predictions. • A medal finish in 2026 could mark the first time an AI places in the top three of a major forecasting tournament. How AI Forecasting Works • Platforms like Metaculus ask participants to assign probabilities to real-world events, from geopolitical conflicts to box-office outcomes. • Mantic’s system uses a “scaffolding” of multiple large language models with different specialties. • One model may analyze elections; another may scan weather, economic data, or historical trends. • The models collaborate to generate a final probability estimate. • AI systems process vast volumes of information rapidly and without fatigue or emotional bias. Specialized Models Raise the Bar • Lightning Rod Labs developed domain-specific predictive models, including one trained to forecast Donald Trump’s behavior. • That tailored model outperformed some of the most advanced general-purpose LLMs. • Benchmarking efforts now continuously evaluate model performance against live prediction markets. Why AI Has the Edge • Rapid ingestion and synthesis of massive data streams. • Lack of cognitive bias or attachment to prior predictions. • Ability to recalibrate probabilities dynamically as new information emerges. • Structured probabilistic reasoning applied consistently across domains. Human Response and Outlook • Elite human forecasters increasingly acknowledge AI’s strengths. • On Metaculus, forecasters now estimate a 95% probability that AI will outperform elite human teams by 2030, up from 75% just a year ago. Why This Matters Forecasting influences capital allocation, national security, disaster response, and financial markets. If AI consistently outperforms humans in anticipating complex events, decision-making may increasingly rely on systems whose internal reasoning is opaque. The shift signals not just incremental improvement, but a potential redefinition of who—or what—guides our understanding of the future. I share daily insights with tens of thousands of followers across defense, tech, and policy. If this topic resonates, I invite you to connect and continue the conversation. Keith King https://lnkd.in/gHPvUttw

"Real-Time AI Model Inference with Kafka & Flink: Scaling Predictive & Generative AI" #ArtificialIntelligence is only as good as the #DataPipelines that power it. Model training gets most of the attention, but #Modelnference - the process of making predictions in real time - is where business value is realized. Whether it’s #FraudDetection in financial services, #PredictiveMaintenance in manufacturing, or context-driven customer support with #GenerativeAI, reliable model inference determines if #AI can truly deliver. This is where #DataStreaming with #ApacheKafka and #ApacheFlink becomes essential. A Data Streaming Platform ensures low latency, scalability, and robustness so that predictive AI and GenAI applications run with the SLAs that modern enterprises require. Two main approaches define model inference today: - Remote model inference: centralized management and easier updates, but often limited by latency and network dependencies. - Embedded model inference: ultra-low latency and offline capability, but more complex to manage at scale. Kafka and Flink enable both, giving organizations the freedom to design architectures that balance latency, cost, robustness, and operational complexity. In predictive AI, streaming data enhances real-time forecasting for fraud detection, condition monitoring, and demand planning. In #GenAI, data streaming supports Retrieval Augmented Generation (RAG) to deliver context-aware outputs that avoid hallucinations and remain business-relevant. The takeaway: AI without data streaming is incomplete. A data streaming platform is the backbone for making predictions and generative outputs actionable, reliable, and aligned with business goals. How is your organization approaching real-time model inference - remote, embedded, or a hybrid of both? https://lnkd.in/eEAyc8ce

AI model forecasts risk of 1,000 diseases a decade ahead >> 🔮Scientists have developed Delphi-2M, a generative AI tool that predicts the probability of more than 1,000 medical conditions from cancer and diabetes to cardiovascular and respiratory disease 🔮The model learns from medical histories, lifestyle factors, and the sequence and timing of “events” like diagnoses, smoking, or alcohol use 🔮 It was trained on 400,000 anonymised UK Biobank records and tested on 1.9 million patient records in Denmark, showing strong accuracy across different health systems 🔮 Like a weather forecast, risks are expressed as probabilities over time, with shorter-term predictions proving more reliable than long-range forecasts 🔮Delphi-2M is especially accurate for diseases with consistent progression such as diabetes, heart attacks, and certain cancers, and less so for more variable issues like mental health or pregnancy-related complications 🔮 Unlike current single-disease tools, it can forecast multiple conditions at once and model possible health trajectories up to 20 years 🔮It is likely the tool still is 5–10 years from clinical use but already shows how generative AI could model disease progression and enable more personalised prevention and treatment #digitalhealth #ai