Predicting the Effect of Proton Beam Therapy Technology on Pulmonary Toxicities for Patients With Locally Advanced Lung Cancer Enrolled in the Proton Collaborative Group Prospective Clinical Trial

PURPOSE

This study aimed to predict the probability of grade ≥2 pneumonitis or dyspnea within 12 months of receiving conventionally fractionated or mildly hypofractionated proton beam therapy for locally advanced lung cancer using machine learning.

METHODS AND MATERIALS

Demographic and treatment characteristics were analyzed for 965 consecutive patients treated for lung cancer with conventionally fractionated or mildly hypofractionated (2.2-3 Gy/fraction) proton beam therapy across 12 institutions. Three machine learning models (gradient boosting, additive tree, and logistic regression with lasso regularization) were implemented to predict Common Terminology Criteria for Adverse Events version 4 grade ≥2 pulmonary toxicities using double 10-fold cross-validation for parameter hyper-tuning without leak of information. Balanced accuracy and area under the curve were calculated, and 95% confidence intervals were obtained using bootstrap sampling.

RESULTS

The median age of the patients was 70 years (range, 20-97), and they had predominantly stage IIIA or IIIB disease. They received a median dose of 60 Gy in 2 Gy/fraction, and 46.4% received concurrent chemotherapy. In total, 250 (25.9%) had grade ≥2 pulmonary toxicity. The probability of pulmonary toxicity was 0.08 for patients treated with pencil beam scanning and 0.34 for those treated with other techniques (P = 8.97e-13). Use of abdominal compression and breath hold were highly significant predictors of less toxicity (P = 2.88e-08). Higher total radiation delivered dose (P = .0182) and higher average dose to the ipsilateral lung (P = .0035) increased the likelihood of pulmonary toxicities. The gradient boosting model performed the best of the models tested, and when demographic and dosimetric features were combined, the area under the curve and balanced accuracy were 0.75 ± 0.02 and 0.67 ± 0.02, respectively. After analyzing performance versus the number of data points used for training, we observed that accuracy was limited by the number of observations.

CONCLUSIONS

In the largest analysis of prospectively enrolled patients with lung cancer assessing pulmonary toxicities from proton therapy to date, advanced machine learning methods revealed that pencil beam scanning, abdominal compression, and lower normal lung doses can lead to significantly lower probability of developing grade ≥2 pneumonitis or dyspnea.

A domain-agnostic approach for characterization of lifelong learning systems

Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed. This critical gap may be addressed through the development of "Lifelong Learning" systems that are capable of (1) Continuous Learning, (2) Transfer and Adaptation, and (3) Scalability. Unfortunately, efforts to improve these capabilities are typically treated as distinct areas of research that are assessed independently, without regard to the impact of each separate capability on other aspects of the system. We instead propose a holistic approach, using a suite of metrics and an evaluation framework to assess Lifelong Learning in a principled way that is agnostic to specific domains or system techniques. Through five case studies, we show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems. We highlight how the proposed suite of metrics quantifies performance trade-offs present during Lifelong Learning system development - both the widely discussed Stability-Plasticity dilemma and the newly proposed relationship between Sample Efficient and Robust Learning. Further, we make recommendations for the formulation and use of metrics to guide the continuing development of Lifelong Learning systems and assess their progress in the future.

Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer

Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong learning method based on coupled dictionary learning that utilizes high-level task descriptions to model inter-task relationships. We show that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of learning problems. Given only the descriptor for a new task, the lifelong learner is also able to accurately predict a model for the new task through zero-shot learning using the coupled dictionary, eliminating the need to gather training data before addressing the task.

A Recap of the AAAI and IAAI 2018 Conferences and the EAAI Symposium

The 2018 AAAI Conference on Artificial Intelligence, the 2018 Innovative Applications of Artificial Intelligence, and the 2018 Symposium on Educational Advances in Artificial Intelligence were held February 2–7, 2018 at the Hilton New Orleans Riverside, New Orleans, Louisiana, USA.  This report, based on the prefaces contained in the AAAI-18 proceedings and program, summarizes the events of the conference.

Teaching Integrated AI through Interdisciplinary Project-Driven Courses

Different subfields of AI (such as vision, learning, reasoning, planning, and others) are often studied in isolation, both in individual courses and in the research literature. This promulgates the idea that these different AI capabilities can easily be integrated later, whereas, in practice, developing integrated AI systems remains an open challenge for both research and industry. Interdisciplinary project-driven courses can fill this gap in AI education, providing challenging problems that require the integration of multiple AI methods. This article explores teaching integrated AI through two project-driven courses: a capstone-style graduate course in advanced robotics, and an undergraduate course on computational sustainability and assistive computing. In addition to studying the integration of AI techniques, these courses provide students with practical applications experience and exposure to social issues of AI and computing. My hope is that other instructors find these courses as useful examples for constructing their own project-driven courses to teach integrated AI.

MediBoost: a Patient Stratification Tool for Interpretable Decision Making in the Era of Precision Medicine

Machine learning algorithms that are both interpretable and accurate are essential in applications such as medicine where errors can have a dire consequence. Unfortunately, there is currently a tradeoff between accuracy and interpretability among state-of-the-art methods. Decision trees are interpretable and are therefore used extensively throughout medicine for stratifying patients. Current decision tree algorithms, however, are consistently outperformed in accuracy by other, less-interpretable machine learning models, such as ensemble methods. We present MediBoost, a novel framework for constructing decision trees that retain interpretability while having accuracy similar to ensemble methods, and compare MediBoost’s performance to that of conventional decision trees and ensemble methods on 13 medical classification problems. MediBoost significantly outperformed current decision tree algorithms in 11 out of 13 problems, giving accuracy comparable to ensemble methods. The resulting trees are of the same type as decision trees used throughout clinical practice but have the advantage of improved accuracy. Our algorithm thus gives the best of both worlds: it grows a single, highly interpretable tree that has the high accuracy of ensemble methods.

Reports on the 2015 AAAI Workshop Program

AAAI's 2015 Workshop Program was held Sunday and Monday, January 25–26, 2015 at the Hyatt Regency Austin Hotel in Austion, Texas, USA. The AAAI-15 workshop program included 15 workshops covering a wide range of topics in artificial intelligence. Most workshops were held on a single day. The titles of the workshops included AI and Ethics, AI for Cities, AI for Transportation: Advice, Interactivity and Actor Modeling, Algorithm Configuration, Artificial Intelligence Applied to Assistive Technologies and Smart Environments, Beyond the Turing Test, Computational Sustainability, Computer Poker and Imperfect Information, Incentive and Trust in E-Communities, Multiagent Interaction without Prior Coordination, Planning, Search, and Optimization, Scholarly Big Data: AI Perspectives, Challenges, and Ideas, Trajectory-Based Behaviour Analytics, World Wide Web and Public Health Intelligence, Knowledge, Skill, and Behavior Transfer in Autonomous Robots, and Learning for General Competency in Video Games.

Computational Sustainability: Editorial Introduction to the Summer and Fall Issues

Computational sustainability problems, which exist in dynamic environments with high amounts of uncertainty, provide a variety of unique challenges to artificial intelligence research and the opportunity for significant impact upon our collective future. This editorial introduction provides an overview of artificial intelligence for computational sustainability, and introduces the special issue articles that appear in this issue and the previous issue of AI Magazine.

Computational Sustainability

Computational sustainability problems, which exist in dynamic environments with high amounts of uncertainty, provide a variety of unique challenges to artificial intelligence research and the opportunity for significant impact upon our collective future. This editorial provides an overview of artificial intelligence for computational sustainability, and introduces this special issue of AI Magazine.

Reports of the 2013 AAAI Spring Symposium Series

The Association for the Advancement of Artificial Intelligence was pleased to present the AAAI 2013 Spring Symposium Series, held Monday through Wednesday, March 25-27, 2013. The titles of the eight symposia were Analyzing Microtext, Creativity and (Early) Cognitive Development, Data Driven Wellness: From Self-Tracking to Behavior Change, Designing Intelligent Robots: Reintegrating AI II, Lifelong Machine Learning, Shikakeology: Designing Triggers for Behavior Change, Trust and Autonomous Systems, and Weakly Supervised Learning from Multimedia. This report contains summaries of the symposia, written, in most cases, by the cochairs of the symposium.

Cloning and characterization of murine p53 upstream sequences reveals additional positive transcriptional regulatory elements

Transcriptional regulation of the p53 gene plays an important role leading to elevated expression of mutant p53 alleles in tumor cells. In addition, alterations in p53 transcription levels occur in response to changes in the cell cycle. Previous work had identified a number of regulatory sites at the 5'-end of the murine p53 promoter. During the characterization of the 5'-end of the cloned murine p53 promoter, we identified a 28 bp positive regulatory element that participates in three distinct DNA-protein complexes. The binding by nuclear factors to each one of these sites contributes to the overall activity of the p53 promoter. One site is a potential recognition sequence for members of the ETS family of transcription factors, which are known regulators of the human p53 promoter. Since six nucleotides in the middle of this required element were not present in the previously published sequence of the murine promoter, we recloned this region from C57/BL6 cells and confirmed their presence in the genome. The removal of this regulatory element completely abolishes p53 promoter activity.

Inhibition of telomerase limits the growth of human cancer cells

Telomerase is a ribonucleoprotein enzyme that maintains the protective structures at the ends of eukaryotic chromosomes, called telomeres. In most human somatic cells, telomerase expression is repressed, and telomeres shorten progressively with each cell division. In contrast, most human tumors express telomerase, resulting in stabilized telomere length. These observations indicate that telomere maintenance is essential to the proliferation of tumor cells. We show here that expression of a mutant catalytic subunit of human telomerase results in complete inhibition of telomerase activity, reduction in telomere length and death of tumor cells. Moreover, expression of this mutant telomerase eliminated tumorigenicity in vivo. These observations demonstrate that disruption of telomere maintenance limits cellular lifespan in human cancer cells, thus validating human telomerase reverse transcriptase as an important target for the development of anti-neoplastic therapies.

Dysphoric response to neuroleptics as a predictor of treatment outcome with schizophrenics. A comparative study of haloperidol versus mesoridazine

In a double-blind comparison of haloperidol and mesoridazine in the treatment of 39 recently hospitalized schizophrenic patients, the two drug treatment groups showed comparable antipsychotic effects, though they did differ in side effects in expected manners. Analysis of the Brief Psychiatric Rating Scale to calculate an index of dysphoric response previously found predictive of poor ultimate outcome failed to predict outcome in this 4-week trial though patients with a dysphoric response to neuroleptics did prove to include a higher proportion of process schizophrenics, who might ultimately show poorer outcome, than did nondysphoric responders.

Teaching anaesthetics in the operating theatre

During an anaesthetic procedure the anaesthetist's main concern is for the patient and his vigilance ensures that the patient is given the best care possible. When a trainee anaesthetist is administering an anaesthetic a tutor is often present to further improve the trainee's practical knowledge or technique. This report presents the results of an investigation of the typical patterns of trainee anaesthetist's behaviour when a tutor is either present or absent in order to establish whether the teaching which occurs in the operating theatre affects the pattern of activity and vigilance. Results indicate that the patterns of behaviour are unaffected by a tutor's presence, and that teaching anaesthetics in the operating theatre may be a legitimate activity which does not interfere with the trainee's prime function of patient care.