Analysis of Survival Times

The fast replication rate and lack of repair mechanisms of human immunodeficiency virus (HIV) contribute to its high mutation frequency, with some mutations resulting in the evolution of resistance to antiretroviral therapies (ART). As such, studying HIV drug resistance allows for real-time evaluation of evolutionary mechanisms. Characterizing the biological process of drug resistance is also critically important for sustained effectiveness of ART. Investigating the link between "black box" deep learning methods applied to this problem and evolutionary principles governing drug resistance has been overlooked to date. Here, we utilized publicly available HIV-1 sequence data and drug resistance assay results for 18 ART drugs to evaluate the performance of three architectures (multilayer perceptron, bidirectional recurrent neural network, and convolutional neural network) for drug resistance prediction, jointly with biological analysis. We identified convolutional neural networks as the best performing architecture and displayed a correspondence between the importance of biologically relevant features in the classifier and overall performance. Our results suggest that the high classification performance of deep learning models is indeed dependent on drug resistance mutations (DRMs). These models heavily weighted several features that are not known DRM locations, indicating the utility of model interpretability to address causal relationships in viral genotype-phenotype data.

Drug Resistance Prediction Using Deep Learning Techniques on HIV-1 Sequence Data.

http://www.thelancet.com/article/S2589750021002296/pdf

Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review

Technology and medicine follow a parallel path during the last decades Technological advances are changing the concept of health and health needs are influencing the development of technology Artificial intelligence (AI) is made up of a series of sufficiently trained logical algorithms from which machines are capable of making decisions for specific cases based on general rules This technology has applications in the diagnosis and follow-up of patients with an individualized prognostic evaluation of them Furthermore, if we combine this technology with robotics, we can create intelligent machines that make more efficient diagnostic proposals in their work Therefore, AI is going to be a technology present in our daily work through machines or computer programs, which in a more or less transparent way for the user, will become a daily reality in health processes Health professionals have to know this technology, its advantages and disadvantages, because it will be an integral part of our work In these two articles we intend to give a basic vision of this technology adapted to doctors with a review of its history and evolution, its real applications at the present time and a vision of a future in which AI and Big Data will shape the personalized medicine that will characterize the 21st century

La inteligencia artificial y sus aplicaciones en medicina II: importancia actual y aplicaciones prácticas

Adverse drug events (ADEs) represent one of the most prevalent types of health-care-related harm, and there is substantial room for improvement in the way that they are currently predicted and detected. We conducted a scoping review to identify key use cases in which artificial intelligence (AI) could be leveraged to reduce the frequency of ADEs. We focused on modern machine learning techniques and natural language processing. 78 articles were included in the scoping review. Studies were heterogeneous and applied various AI techniques covering a wide range of medications and ADEs. We identified several key use cases in which AI could contribute to reducing the frequency and consequences of ADEs, through prediction to prevent ADEs and early detection to mitigate the effects. Most studies (73 [94%] of 78) assessed technical algorithm performance, and few studies evaluated the use of AI in clinical settings. Most articles (58 [74%] of 78) were published within the past 5 years, highlighting an emerging area of study. Availability of new types of data, such as genetic information, and access to unstructured clinical notes might further advance the field.

Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review.

Fuzzy-multidimensional deep learning for efficient prediction of patient response to antiretroviral therapy.

A transfer learning approach to drug resistance classification in mixed HIV dataset

Understanding pharmacology and drug resistance patterns plus appropriate use of laboratory testing is vital for managing treatment-experienced patients with new agents. While we acknowledge that patients with extensive drug resistance now have multiple options for suppressive therapy, and expert care is essential to avoid the rapid emergence of resistance to these new agents, clinicians are unaware of the inherent (hidden) patterns created by combined drug regimens that could trigger adverse drug reactions. This paper proposes a novel hybrid system framework that combines soft computing techniques, for drugs interaction modelling and precise patient response optimisation. A Fuzzy Logic system was developed to address the uncertainty in treatment change episodes (TCEs). A weighted least-squares cost function was then employed to auto-tune hyperparameters for training the neural network. After acceptable tuning, the final hyperparameters served the neural network—to efficiently learn the ensuing patterns for precice drug interaction classification. The proposed framework was experimented with clinical data of TCEs from two disparate sources: a publicly available HIV database (the Stanford HIV database: 
https://hivdb.stanford.edu

), and clinical data collected from 13 health centers managing HIV cases in Akwa Ibom State of Nigeria (the Akwa-Ibom HIV database). In both databases, a correlation of prognostic markers suggests strong association between first line CD4 and follow-up CD4 counts; while a moderately weak association was observed for first line and follow-up viral loads. Correlation of physiological feature gave very strong association between first line and follow-up body mass index in Akwa-Ibom database. Analysis of the patients progress explains the decreased potency of CD4 count and body mass index as HIV predictors. The root mean square error (RMSE) and classification accuracy were used as performance metrics for measuring the precision of our hybrid framework. Results obtained showed improved RMSE and classification accuracy for both databases, when compared with existing works.

Philip I. Etebong

Papers

Fuzzy-multidimensional deep learning for efficient prediction of patient response to antiretroviral therapy.

A transfer learning approach to drug resistance classification in mixed HIV dataset

Modelling drugs interaction in treatment-experienced patients on antiretroviral therapy

Processed HIV prognostic dataset for control experiments.