About

Vibha Mane is an Assistant Professor of Practice at the Department of Electrical and Computer Engineering at Stony Brook University. Her research focuses on machine learning, artificial intelligence, and the development of approximate solutions of the Master Equation with applications in biochemical networks.

Research topics

• Clinical psychology
• Medicine
• Artificial Intelligence
• Psychiatry
• Machine Learning
• Computer Science
• Psychology
• Family medicine

Selected publications

• Applying machine learning methods to psychosocial screening data to improve identification of prenatal depression: Implications for clinical practice and research

  Archives of Women s Mental Health · 2022 · 9 citations

  • Machine Learning
  • Artificial Intelligence
  • Machine Learning
  PublisherOA PDFDOI

• Missingness patterns in a comprehensive instrument identifying psychosocial and substance use risk in antenatal care

  Journal of Reproductive and Infant Psychology · 2021 · 4 citations

  • Medicine
  • Family medicine
  • Psychiatry

  BACKGROUND: Psychosocial vulnerabilities (e.g. inadequate social support, financial insecurity, stress) and substance use elevate risks for adverse perinatal outcomes and maternal mental health morbidities. However, various barriers, including paucity of validated, simple and usable comprehensive instruments, impede execution of the recommendations to screen for such vulnerabilities in the first antenatal care visit. The current study presents findings from a newly implemented self-report tool created to overcome screening barriers in outpatient antenatal clinics. METHODS: This was a retrospective chart-review of 904 women who completed the Profile for Maternal & Obstetric Treatment Effectiveness (PROMOTE) during their first antenatal visit between June and December 2019. The PROMOTE includes the 4-item NIDA Quick Screen and 15 additional items that each assess a different psychosocial vulnerability. Statistical analysis included evaluation of missing data, and exploration of missing data patterns using univariate correlations and hierarchical clustering. RESULTS: Three quarters of women (70.0%) had no missing items. In the entire sample, all but four PROMOTE items (opioid use, planned pregnancy, educational level, and financial state) had < 5% missing values, suggesting good acceptability and feasibility. Several respondent-related characteristics such as lower education, less family support, and greater stress were associated with greater likelihood of missing items. Instrument-related characteristics associated with missing values were completing the PROMOTE in Spanish or question positioning at the end of the instrument. CONCLUSIONS AND IMPLICATIONS: Conducting a comprehensive screening of theoretically and clinically meaningful vulnerabilities in an outpatient setting is feasible. Study findings will inform modifications of the PROMOTE and subsequent digitisation.

  PublisherOA PDFDOI

• MOMENT PROPAGATION METHODS FOR STOCHASTIC SIMULATION OF COMPLEX BIOCHEMICAL SYSTEMS

  SUNY Digital Repository Support (State University of New York System) · 2011-01-01

  articleOpen access1st authorCorresponding

  We are interested in predicting the time dependent behavior of biochemical networks such as interaction between proteins. These networks are represented by a system of chemical reactions. In the forward problem, we have knowledge of all the reactions and the associated rate constants. We want to determine the joint probability density of the populations of all the molecular species at any time instant. The given biochemical system is a discrete state, continuous time Markov process, and the time evolution of its probability density function is described by the chemical master equation (CME). We want to obtain the solution of the master equation in complex biochemical systems with a large number of species and reactions. Analytical solutions of the chemical master equation for first and second order reactions have only been obtained for select cases with a few species and reactions. Another approach to solving the problem is to approximate the CME with the Fokker-Planck equations. But this would require solving partial differential equations with a large number of variables. The present state of the art approaches for stochastic simulation of such systems are based on Monte Carlo methods. One such popular method is the Stochastic Simulation Algorithm (SSA) derived by Gillespie in 1976. Several authors have developed accelerated versions of the SSA such as the Next Reaction Method and time leaping methods, in order to reduce the computation time of SSA. The Monte Carlo methods provide approximations of the complete distribution, but they require simulations of many realizations of the Markov process and many time steps. Hence their computation times are prohibitively long for very complex systems. Methods for modeling the biochemical networks based on moment propagation is a relatively unexplored area. We propose a new method for propagating the first two moments of the joint probability distribution of the number of molecules. In many systems, the distribution can be approximated as Gaussians and therefore computing the first two moments is sufficient. Simulation results show that our method yields accurate results for first order and second order reactions. Compared with the Monte Carlo methods, our method yields significant savings in computation time. Compared with other moment propagation methods, the recursive expressions in our method can be implemented by specifying rate constants and stoichiometries, without having to derive or solve any differential equations. Whereas other moment propagation methods with similar accuracy have been demonstrated for a few species, we demonstrate our method for complex biochemical systems with hundreds of species.

  PublisherDOI

• Stochastic modeling of second order reactions using a moment propagation method

  2009-05-01 · 1 citations

  article1st authorCorresponding

  The traditional methods for solving the chemical master equation are based on Monte Carlo methods, such as the stochastic simulation algorithm (SSA) and its accelerated versions. Methods for modeling biochemical networks based on moment propagation are a relatively unexplored area. In a prior paper, we addressed first-order reactions and presented a new method for propagating the first two moments of the probability distributions of the number of molecules over time. In this paper we extend this method to second order reactions and demonstrate its performance on some simple networks.

  PublisherDOI

• A stochastic approach to studying biochemical reactions without Monte Carlo simulations

  2009 IEEE/SP 15th Workshop on Statistical Signal Processing · 2009-08-01

  article1st authorCorresponding

  The time evolution of molecular species in a biochemical system is a discrete-state continuous-time Markov process, which can be described by a chemical master equation. The traditional methods for solving the chemical master equation are based on Monte Carlo methods, such as the stochastic simulation algorithm (SSA). In prior work, we proposed a method for simulation of the time evolution based on the propagation of the first two moments of the molecules in the biochemical system over time. In this paper we present a generalization of our previous result. We also compare our method with other methods such as the stochastic hybrid systems (SHS).

  PublisherDOI

• Stochastic simulation of coupled chemical reactions using recursive methods

  Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing · 2008-03-01 · 1 citations

  articleOpen access1st authorCorresponding

  In this paper, we present a new method for stochastic simulation of coupled chemical reactions. In this method we obtain recursive expressions for propagating the first two moments of the probability distributions over time. Its advantage over other simulation methods is that it does not require Monte Carlo simulations, and hence it performs several orders of magnitude faster than existing Monte Carlo methods. Simulation results are presented for some examples of coupled first-order reactions.

  PublisherOA PDFDOI

• On new stochastic approaches for solving forward and backward problems of biochemical networks

  2008-05-01

  articleSenior author

  There are two distinct problems in the stochastic analysis of biochemical networks, and they are known as the forward and inverse problems. Solutions of the former problem are used for simulating a system of molecular species in time according to the random laws that govern the reactions in which the species participate. Solutions of the latter problem provide estimates of the unknowns in the system that is represented by the biochemical network. The estimates are obtained from measurements that are functions of the number of molecules of some of the species. In the two problems, we have underlying assumptions about the probabilistic models of the studied network. In this paper we present two new methods for addressing these problems. For solving the forward problem we propose a method that does not employ Monte Carlo simulations, whereas for solving the inverse problem we use particle filtering.

  PublisherDOI

Frequent coauthors

• Petar M. Djurić

  Stony Brook University

  6 shared

• David Garry

  Stony Brook Medicine

  4 shared

• Mónica F. Bugallo

  Stony Brook University

  4 shared

• Cassandra Heiselman

  4 shared

• Marci Lobel

  Stony Brook School

  3 shared

• Kimberly Herrera

  2 shared

• Marzieh Ajirak

  Stony Brook University

  2 shared

• Joseph Chappelle

  Stony Brook School

  2 shared

Labs

• Electrical and Computer Engineering, Stony Brook UniversityPI

Education

• PhD, Electrical and Computer Engineering

  Stony Brook University

  2011