Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2017 Aug 23;8:616. doi: 10.3389/fphys.2017.00616

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2017 Dutta, Chang, Beattie, Sheng, Tran, Wu, Wu, Strauss, Colatsky and Li.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

Classification training error for a range of metrics [resting membrane potential (resting Vm), maximum upstroke velocity (dV/dtmax), peak membrane potential (peak Vm), APD50, APD90, action potential (AP) triangulation (APDtri), diastolic intracellular calcium concentration ([Ca²⁺]_i) (diastolic Ca), peak [Ca²⁺]_i (peak Ca), calcium transient duration at 50 and 90% of the amplitude (CaD50 and CaD90), calcium transient triangulation (Catri), change in amount of charge carried by INaL and ICaL (cqInward) and the charge carried by Inet at the end of the AP beat normalized to control (qNet)] for varying drug doses (0.5–25x Cmax) and varying CLs (1,000, 2,000, and 4,000 ms). Each box represents the mean (across 12 drugs) error (between predicted and known risk levels) for each metric at each concentration (0.5–25X Cmax). A training error of 0 represents perfect separation between the risk categories.