
Alexandru FloaresIndependent Researcher · Artificial Intelligence
Alexandru Floares
MD, PhD
About
52
Publications
18,971
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
448
Citations
Introduction
Additional affiliations
March 2017 - January 2024
Artificial Intelligence Expert
Position
- CEO
Description
- I am the CEO of the company.
Publications
Publications (52)
64
Background: Colorectal cancer (CRC), the second most deadly cancer, underscores the critical need for early detection to significantly improve treatment outcomes and survival rates. Colonoscopy, flexible sigmoidoscopy, and the fecal immunochemical tests (FIT), often fail to capture early disease, significantly decreasing the survival chance. Cir...
Cancer is one of the most common and deadly diseases worldwide, claiming millions of lives yearly. Despite significant advances in treatment, the overall survival rate remains low, primarily due to late-stage diagnosis. In the high-throughput, high-dimensional omics data era, Biomedical Knowledge should be combined with Data Science best practices...
5
Background: Breast cancer is requires early and accurate detection for effective treatment and improved patient outcomes. Current methods, such as mammography and biopsy, have limitations in accuracy, invasiveness, and accessibility. Circulating microRNAs (miRNAs) are promising non-invasive biomarkers for cancer detection, including breast cancer...
High-quality omics tests can be developed by using machine learning. As high-throughput molecular determinations are costly, we want to build the best models, utilizing the minimal number of samples. Here, we specify a set of criteria for high-quality models and select the algorithms which best satisfy them. Boosted C5, Random Forest and Stochastic...
This is the presentation of the paper with the same title
This contribution, part of a larger project, was motivated by the fact that we want highly accurate OMICS tests, for diagnosis, prognosis, & response to treatment prediction, based on various omics data. e.g., microarray, NGS or PCR. For these goals, we should use machine learning and artificial intelligence (deep learning) tools to analyze the dat...
Cancer signatures can be discovered from omics Big Data with machine learning. How big this costly data should be? For a given dataset and biomedical problem is the signature unique? We investigated the miRNA NGS data of the largest breast cancer cohort from TCGA, to develop decision trees (C5 and CART) models discriminating between cancer and norm...
Precision Medicine’s goals cannot be reached without discovering molecular signatures from omics Big Data, using machine learning. The prevailing conception is that, for a given biomedical condition and class of biomolecules, there should be a unique, highly accurate signature. Following the best practice, for whet lab determinations and predictive...
Functional redundancy is a fundamental property of living systems, ensuring their amazingly robust complexity. Both Cancer and Normal cells are robust, and this is partially due to the functional redundancy of their regulatory systems, e.g., many different microRNAs regulate the same mRNA. To explore the redundancy, we propose a computational intel...
Functional redundancy is a fundamental property of
living systems, ensuring their amazing robust complexity. Both
cancer and normal cells are robust, and this is partially due to
their regulatory subsystems which are functionally redundant,
i.e. many different microRNAs regulate the same mRNA. To
explore the redundancy, this paper proposes a comput...
Most molecular diagnosis tests are based on small studies with about twenty patients, and use classical statistics. The prevailing conception is that such studies can indeed yield accurate tests with just one or two predictors, especially when using informative molecules like microRNA in cancer diagnosis. We investigated the relationship between ac...
In this contribution, we investigated the relationship between the accuracy of a molecular test and the sample size of the study. Using some simple but powerful decision trees algorithms, we discovered some unexpected aspects. This paper received the ”Best Paper Award”.
MicroRNAs (miRNAs) are small, noncoding RNA species with a length of 20–22 nucleotides that are recognized as essential regulators of relevant molecular mechanisms, including carcinogenesis. Current investigations show that miRNAs are detectable not only in different tissue types but also in a wide range of biological fluids, either free or trapped...
This paper investigates the integration of clinico-pathological and microRNA data for breast cancer relapse prediction. Clinical and pathological data proved to be relevant in making predictions about cancer disease outcome. The most accurate predictive models can be obtained by using clinico-pathological information together with genomic informati...
Reverse
engineering
of transcription networks
is a challenging bioinformatics problem. Ordinary differential equation (ODEs) network models have their roots in the physicochemical base of these networks, but are difficult to build conventionally. Modeling automation is needed and knowledge discovery in data using computational intelligence methods...
The purpose of the study is to identify and validate ultrasound criteria for parotid tumors evaluation, as well as to elaborate a multimodal, multi-criteria and integrative ultrasound approach for allowing tumor discrimination in a non-invasive manner.
Twenty patients with solid parotid tumors (12 benign, 8 malignant) were examined by ultrasound: r...
Early and non-invasive diagnosis and prognosis are important but challenging problems in cancer clinical management.Our results suggest that the most accurate solutions could be developed combining Artificial Intelligence with OMICS technologies. The new i-Biomarker concept and the methodology for developing panels of i-Biomarkers will be presented...
Understanding and eventually controlling the dynamics of microRNA (miRNA) networks via drug treatments are important yet challenging biomedical research issues. Ordinary differential equations (ODEs), the main mathematical framework of dynamical systems theory, even though considered adequate models for such biomedical networks, are difficult to bu...
Modeling complex networks with ordinary differential equations systems is an appropriate
approach, particularly suited for dynamical systems represented by time series data. The main
challenge of this approach is the difficulty of determining the suitable form of the differential
equations which represent the network. In this chapter, we propose...
Computational intelligence aims to emulate aspects of biological systems for developing software and/or hardware that learns and adapts. Such systems primarily include neural networks, fuzzy logic systems and evolutionary computation each of them including multiple active and fast growing research directions. This book presents new and ground-break...
The aim of this study is to propose a methodology for
developing intelligent systems for cancer diagnosis and evaluate it
on bladder cancer. Owing to recent advances in high-throughput
experiments, large data repositories are now freely available for
use. However, the process of extracting information from these
data and transforming it into clinic...
Bladder cancer is the fourth most common malignancy in men in the western
countries. The aim of this study was to develop intelligent systems for invasive bladder
cancer progression prediction. The proposed methodology combines knowledge discov-
ery in data using artificial intelligence and knowledge mining. These are used both in
feature selection...
Bladder cancer is the fourth most common malignancy in men in the western countries. The aim of this study was to develop intelligent systems for invasive bladder cancer progression prediction. The proposed methodology combines knowledge discovery in data using artificial intelligence and knowledge mining. These are used both in feature selection a...
Currently, there are some paradigm shifts in medicine, from the search for a
single ideal biomarker, to the search for panels of molecules, and from a reductionistic to
a systemic view, placing these molecules on functional networks. There is also a general
trend to favor non-invasive biomarkers. Identifying non-invasive biomarkers in high-
through...
Currently, there are some paradigm shifts in medicine, from the search for a single ideal biomarker, to the search for panels of molecules, and from a reductionistic to a systemic view, placing these molecules on functional networks. There is also a general trend to favor non-invasive biomarkers. Identifying non-invasive biomarkers in high-throughp...
Currently, there are some paradigm shifts in medicine, from the search for a single ideal biomarker, to the search for panels of molecules, and from a reductionistic to a systemic view, placing these molecules on functional networks.
There is also a general trend to favor non-invasive biomarkers. Identifying non-invasive biomarkers in high-throughp...
Clinical Decision Support Systems have the potential to optimize medical decisions, improve medical care, and reduce costs.
An effective strategy to reach these goals is by transforming conventional Clinical Decision Support in Intelligent Clinical
Decision Support, using knowledge discovery in data and computational intelligence tools. In this pap...
In chronic hepatitis C and B, which can progress to cirrhosis and liver cancer, Interferon is the only effective treatment, for carefully selected patients, but it is very expensive. Some of the selection criteria are based on liver biopsy, an invasive, costly and painful medical procedure. Developing an efficient selection system, based on non-inv...
Mathematical modeling gene regulatory networks is important for understanding and controlling them, with various drugs and their dosage regimens. The ordinary differential equations approach is sensible but also very difficult. Our reverse engineering algorithm (RODES), based on neural networks feedback linearization and genetic programming, takes...
An important goal of modern medicine is to replace invasive, painful procedures with non-invasive techniques for diagnosis.
We investigated the possibility of a knowledge discovery in data approach, based on computational intelligence tools, to integrate
information from various data sources - imaging data, clinical and laboratory data, to predict...
Motivation: Various drugs and their dosage regimens. The ordinary differential
equations approach is probably the most sensible. Unfortunately, this is also the
most difficult, tedious, expensive, and time-consuming approach. There is a need
for algorithms to automatically infer such models from high-throughput temporal
series data. Computational i...
Automatically inferring drug gene regulatory networks models from microarray time series data is a challenging task. The ordinary differential equations models are sensible, but difficult to build. We extended our reverse engineering algorithm for gene networks (RODES), based on genetic programming, by adding a neural networks feedback linearizatio...
Background and aims: The gold standard in evaluating fibrosis stage in chronic hepatitis C (CHC) patients is liver biopsy, a costly and invasive procedure. Alternatively, transient elastography (FibroScan®) performs well in identifying severe fibrosis or cirrhosis, but is less accurate in identifying lower degrees of fibrosis. We recently built a p...
Modeling neural networks with ordinary differential equations systems is a sensible approach, but also very difficult. This paper describes a new algorithm based on linear genetic programming which can be used to reverse engineer neural networks. The RODES algorithm automatically discovers the structure of the network, including neural connections,...
Chronic hepatitis B can evolve to cirrhosis and liver cancer. Interferon is the only effective treatment, for carefully selected patients, but it is very expensive. Some of the selection criteria are based on liver biopsy, an invasive, costly and painful medical proce-dure. Therefore, developing efficient non-invasive selection systems, could be in...
The ordinary differential equations approach to neutral networks modeling is one of the most sensible approach but also very difficult. We proposed a reverse engineering algorithm for neural networks based on linear genetic programming. This algorithm allows the automatic discovery of the structure, estimation of the parameters, and even identifica...
Automatically inferring gene regulating networks models from microarray time series data is one of the most challenging tasks of bioinformatics. The ordinary differential equations models are the most sensible, but very difficult to build. We introduced the more general concept of drug gene regulating networks, where the regulation is exerted also...
Modern pharmacology, combining pharmacokinetic, pharmacodynamic, and pharmacogenomic data, is dealing with high dimensional,
nonlinear, stiff systems. Mathematical modeling of these systems is very difficult, but important for understanding them.
At least as important is to adequately control them through inputs – drugs’ dosage regimens. Genetic pr...
Recently, magnetic resonance imaging and proton magnetic resonance spectroscopy studies of major depression identified structural and neurochemical alterations in several brain regions, including the hippocampus and prefrontal cortex. However, many contradictory endings exist. Most previous studies used a few cases and features, and conventional st...
Pharmacogenomic systems (PG) are very high dimensional, nonlinear, and stiff systems. Mathematical modeling of these systems, as systems of nonlinear coupled ordinary differential equations (ODE), is considered important for understanding them; unfortunately, it is also a very difficult task. At least as important is to adequately control them thro...
Pharmacogenomic systems (PG) are very high dimensional, nonlinear, and stiff systems. Mathematical modeling of these systems, as systems of nonlinear coupled ordinary differential equations (ODE), is considered important for understanding them; unfortunately, it is also a very difficult task. At least as important is to adequately control them thro...
Recently, magnetic resonance imaging and proton magnetic resonance spectroscopy studies of major depression identified structural and neurochemical alterations in several brain regions, including the hippocampus and prefrontal cortex. However, many contradictory endings exist. Most previous studies used a few cases and features, and conventional st...
Pharmacological modeling is developing from an empirical discipline into a mechanistic science. Also, new and important fields like pharmacogenomics appeared. As a consequence, pharmacology is dealing with high dimensional, nonlinear, control systems. The intent of this paper is to show that all this systems, being based on a limited array of mecha...
2134 Background: An important problem in cancer chemotherapy is the design of drug dosage regimens such that at the end of treatment, the tumor burden is minimized, and the benefits are balanced against the toxic effects. We propose an approach based on neural networks (NN) control to optimize chemotherapy regimens. Methods: The tumor growth and th...
This paper presents the optimal control chemotherapy scheduling in cancer using neural networks. Unlike conventional methods, the proposed neural networks methodology, feedback linearization, is simple and capable of automatically finding the optimal solutions for complex cancer chemotherapy problems. Also, it allows the application of the well dev...
Questions
Questions (4)
It is clear that miRNA are informative molecules for cancer diagnosis, and there is a desire for non-invasive tests. It is also clear that NGS is a real progress. However, the known advantages of miRNA NGS vs microarray are not important for my study, as I do not want to discover new miRNAs or isoforms. I want just to discriminate, with the highest possible accuracy, between cancer and normal, using advanced Artificial Intelligence (AI) methods. Prelimiary results suggest that microrna data are better than NGS. Moreover, microarray profiling is cheaper. Searching the literature, I found some papers corroborationg this idea: microarray is a better choice if you are interested in miRNA cuantification. What is your opinion? Thank you!
I would like to know your answer to the following questions:
Why most omics (e.g., microarray, NGS, PCR) studies concerning disease diagnosis, or prognosis, or response to treatment end up with lists of differentially expressed molecules. Is this the most relevant and/or practically useful result?
I will tell you my opinion later, as I do not want to influence your answers.
Thank you