Review
Health Care Sciences & Services
Alfredo Cesario, Marika D'Oria, Francesco Bove, Giuseppe Privitera, Ivo Boskoski, Daniela Pedicino, Luca Boldrini, Carmen Erra, Claudia Loreti, Giovanna Liuzzo, Filippo Crea, Alessandro Armuzzi, Antonio Gasbarrini, Paolo Calabresi, Luca Padua, Guido Costamagna, Massimo Antonelli, Vincenzo Valentini, Charles Auffray, Giovanni Scambia
Summary: Personalized Medicine challenges the traditional top-down approach by considering genetic, genomic, and lifestyle factors in understanding complex diseases. Clinical phenotyping can be difficult when different pathophysiological mechanisms produce the same manifestation, and the potential of Systems Medicine using Artificial Intelligence tools is highlighted for personalized clinical phenotyping.
JOURNAL OF PERSONALIZED MEDICINE
(2021)
Article
Health Care Sciences & Services
Chi-Shin Wu, Albert C. Yang, Shu-Sen Chang, Chia-Ming Chang, Yi-Hung Liu, Shih-Cheng Liao, Hui-Ju Tsai
Summary: This study developed machine learning-based prediction models for personalized pharmacological treatment of patients with depressive disorder, which effectively reduced treatment failure rates.
JOURNAL OF PERSONALIZED MEDICINE
(2021)
Article
Automation & Control Systems
Hengrui Cai, Chengchun Shi, Rui Song, Wenbin Lu
Summary: This paper proposes an individualized interval-valued decision rule (I2DR) in the continuous treatment setting. The jump interval-learning method is used to derive an optimal I2DR, which maximizes the expected outcome. Compared to traditional decision rules, I2DR provides an interval of treatment options for each individual, offering greater flexibility in practice.
JOURNAL OF MACHINE LEARNING RESEARCH
(2023)
Article
Computer Science, Information Systems
Pouya Ghiasnezhad Omran, Kerry Taylor, Sergio Rodriguez Mendez, Armin Haller
Summary: This article introduces a novel algorithm, OPRL, for learning Open Path (OP) rules that can generate relevant queries for Knowledge Graph completion, even when there is no closed rule to answer the query. This demonstrates the first solution for active knowledge graph completion.
INFORMATION SCIENCES
(2022)
Article
Health Care Sciences & Services
Christian A. Webb, Matthew J. Hirshberg, Richard J. Davidson, Simon B. Goldberg
Summary: This study developed and tested a data-driven algorithm to predict who is most likely to benefit from a meditation app. The results showed that Personalized Advantage Index scores moderated group differences in outcomes, indicating the potential of the algorithm to inform which individuals are most likely to benefit. This algorithm can be used to objectively communicate expected benefits to individuals, helping them make informed decisions about using a meditation app.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2022)
Article
Statistics & Probability
Shanghong Xie, Thaddeus Tarpey, Eva Petkova, R. Todd Ogden
Summary: This article proposes an approach to improve the accuracy of individualized treatment rules (ITRs) by using multiple kernel functions to describe the similarity of features. The method takes into account the heterogeneity of each data domain and combines data from multiple domains optimally. The approach can estimate optimal ITRs and identify the most important domains for determining ITRs.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2022)
Article
Statistics & Probability
Yinghao Pan, Ying-Qi Zhao
Summary: Individualized treatment rules recommend treatment based on patient characteristics. An improved doubly robust estimator is proposed for optimal ITRs, achieving the smallest variance among a class of doubly robust estimators when the propensity score model is correctly specified. Simulation studies show better results than current popular methods.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2021)
Article
Computer Science, Artificial Intelligence
Zhengxiao Du, Jie Tang, Yuhui Ding
Summary: This study focuses on the personalized article recommendation issue when the user's preference data is missing or limited, known as the user cold-start problem in recommender systems. The proposal of POLAR++, an active recommendation framework utilizing Bayesian neural networks and one-shot learning, effectively addresses this problem. By designing an attention-based CNN to quantify the similarity between user preference and recommended articles, the model's effectiveness has been successfully validated.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2021)
Article
Health Care Sciences & Services
Yeonhee Park
Summary: This paper proposes a personalized risk-based screening design using Bayesian covariate-adjusted response-adaptive randomization for improved clinical trial outcomes under personalized medicine. The design effectively controls error rates and allocates more patients to better interventions.
JOURNAL OF PERSONALIZED MEDICINE
(2022)
Article
Biochemistry & Molecular Biology
Taylor M. Weiskittel, Choong Y. Ung, Cristina Correia, Cheng Zhang, Hu Li
Summary: Despite the limited understanding of individual disease etiology and therapeutics, a novel computational pipeline has been proposed to collect potent disease gene cooperative pathways for individualized disease etiology and therapies. The importance of mutated genes in specific patients and the synthetic penetrance of these genes across patients can be elucidated through individualized disease modules. This study reveals the fluctuation of importance for notorious cancer drivers in breast cancers and the high disease module importance of rarely mutated genes in specific individuals. Furthermore, customized singular and combinatorial target therapies can be devised through individualized module disruption, emphasizing the need for precision therapeutics pipelines. This analysis demonstrates the power of individualized disease modules for precision medicine, offering deep novel insights on the activity of diseased genes in individuals.
Article
Medicine, Research & Experimental
Glen B. Taksler, Phuc Le, Bo Hu, Jay Alberts, Allen J. Flynn, Michael B. Rothberg
Summary: The Personalized Disease Prevention (PDP) trial aims to test a novel and holistic approach to prioritize the delivery of preventive services for patients and providers by utilizing patient risk factors stored in electronic health records.
Article
Computer Science, Software Engineering
Mofei Song
Summary: This paper proposes a novel interactive system for efficiently and flexibly classifying 3D shapes, incorporating active learning, online learning, and user intervention. The system iteratively alternates interactive annotation and verification until all shape labels are confirmed by users, providing faster interactive classification rates than alternative approaches.
Article
Biochemical Research Methods
Daniel Toro-Dominguez, Jordi Martorell-Marugan, Manuel Martinez-Bueno, Raul Lopez-Dominguez, Elena Carnero-Montoro, Guillermo Barturen, Daniel Goldman, Michelle Petri, Pedro Carmona-Saez, Marta E. Alarcon-Riquelme
Summary: This study developed MyPROSLE, an omic-based analytical workflow, to measure the molecular characteristics of individual patients and support therapeutic decisions. Through analysis of nearly 6100 lupus patients and 750 healthy samples, it was found that dysregulation of certain gene-modules is strongly associated with specific clinical manifestations, relapses, long-term remission, and drug response. Therefore, MyPROSLE can accurately predict these clinical outcomes.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Medicine, General & Internal
Naciye Cigdem Arslan, Aycan Gundogdu, Varol Tunali, Oguzhan Hakan Topgul, Damla Beyazgul, Ozkan Ufuk Nalbantoglu
Summary: The AI-assisted customized diet based on individual microbiome analysis showed significantly better outcomes compared to conventional therapy in the treatment of functional constipation. After 6 weeks, patients in the study group had a significant increase in complete bowel movements and improvements in quality of life scores.
JOURNAL OF CLINICAL MEDICINE
(2022)
Article
Statistics & Probability
Yuming Sun, Jian Kang, Chad Brummett, Yi Li
Summary: Preoperative opioid use is associated with negative outcomes and increased healthcare utilization and costs. Machine learning models have good predictive power but lack interpretability. The proposed interpretable neural network regression (INNER) combines the strengths of statistical and deep neural network models and accurately predicts preoperative opioid use. It also provides straightforward interpretations of the odds of opioid use without pain and the odds ratio of opioid use for a unit increase in overall body pain.
ANNALS OF APPLIED STATISTICS
(2023)
Article
Statistics & Probability
Stanislav Minsker
Article
Statistics & Probability
Stanislav Minsker
STATISTICS & PROBABILITY LETTERS
(2017)
Article
Computer Science, Information Systems
Larry Goldstein, Stanislav Minsker, Xiaohan Wei
IEEE TRANSACTIONS ON INFORMATION THEORY
(2018)
Article
Statistics & Probability
Stanislav Minsker
ANNALS OF STATISTICS
(2018)
Article
Automation & Control Systems
Mauro Maggioni, Stanislav Minsker, Nate Strawn
JOURNAL OF MACHINE LEARNING RESEARCH
(2016)
Proceedings Paper
Optics
Mauro Maggioni, Stanislav Minsker, Nate Strawn
WAVELETS AND SPARSITY XVI
(2015)