SINGAPORE: In a first, scientists have used a powerful artificial intelligence (AI) platform, to successfully treat a patient with advanced cancer, completely halting disease progression. The research team successfully utilised a platform called CURATE.AI to continuously identify the optimal doses of each drug to result in a durable response, allowing the patient to resume a completely normal and active lifestyle. The patient with metastatic castration-resistant prostate cancer (MCRPC) was given a novel drug combination consisting of investigational drug ZEN-3694 and enzalutamide, an approved prostate cancer drug. "Dynamic dosing in cancer therapy is not commonly used. In fact, drug dosing changes in oncology are typically performed only to reduce toxicity," said Dean Ho, from National University of Singapore (NUS).
You are free to share this article under the Attribution 4.0 International license. Researchers have harnessed a powerful artificial intelligence platform to successfully treat a patient with advanced cancer, completely halting disease progression. The development represents a big step forward in personalized medicine, they say. In this clinical study, researchers gave a patient with metastatic castration-resistant prostate cancer (MCRPC) a novel drug combination consisting of the investigational drug ZEN-3694 and enzalutamide, an approved prostate cancer drug. The research team successfully used the platform, called CURATE.AI, to continuously identify the optimal doses of each drug to result in a durable response, allowing the patient to resume a completely normal and active lifestyle.
Artificial intelligence stopped prostate cancer from spreading in a patient with an advanced form of the disease, new research shows. An unnamed patient with tumours that had spread outside his prostate was given a combination of an experimental drug and an approved cancer medication. AI technology, known as CURATE.AI, was used to continuously assess how well the patient responded to the drugs, with the medications' doses being adjusted accordingly. These dose changes reduced cancer markers in his blood to the lowest levels they had ever been, with CT scans also revealing the patient's tumours had not spread further. Lead author Professor Dean Ho, from the National University of Singapore, said: 'The unique ability for CURATE.AI to rapidly identify the drug doses that result in the best possible treatment outcomes allows for optimised personalised medicine.
Combining two recent technologies can markedly improve the performance outcomes and cost-effectiveness of aviation training. The first is a well-tested design methodology for developing cognitive tutors (Anderson et al. 1995, Anderson and Schunn 2000) based on modern theories of skill acquisition. The second is the advent of high-fidelity PCbased part-task simulators on which pilots can "learn by doing" and "progress to real-world performance," two essential guidelines for designing cognitive tutors. An experimental flightcrew automation training program (McLennan et al. submitted) produced results consistent with non-aviation training results using Anderson's cognitive tutors, implying that pilots trained on cognitive tutors can attain the same or higher level of competence in approximately one-third the training time for traditionally trained pilots.
This paper describes the development and empirical testing of an intelligent tutoring system (ITS) with two emerging methodologies: (1) a partially observable Markov decision process (POMDP) for representing the learner model and (2) inquiry modeling, which informs the learner model with questions learners ask during instruction. POMDPs have been successfully applied to non-ITS domains but, until recently, have seemed intractable for large-scale intelligent tutoring challenges. New, ITS-specific representations leverage common regularities in intelligent tutoring to make a POMDP practical as a learner model. Inquiry modeling is a novel paradigm for informing learner models by observing rich features of learners’ help requests such as categorical content, context, and timing. The experiment described in this paper demonstrates that inquiry modeling and planning with POMDPs can yield significant and substantive learning improvements in a realistic, scenario-based training task.