Predicting patient response to sodium channel blockers
Disclosed herein is a method for predicting a patient response to a sodium ion channel blocker such as mexiletine when the patient has LQT syndrome or an arrhythmia. The method generally comprises determining a plurality of parameters associated with sodium ion channels; generating a model for patient response by using a partial least squared (PLS) regression analysis on said plurality of parameters; and using the model to predict the patient response if the patient is administered a sodium ion channel blocker such as mexiletine.
1. A method for predicting a patient response to a sodium ion channel blocker, the method comprising:
receiving, at a user interface, a plurality of parameters associated with sodium ion channels of the patient, wherein the plurality of parameters associated with sodium ion channels of the patient comprise DIII-VSD activation and slow recovery τ from inactivation;
applying one or more inputs to a supervised machine learning model, the one or more inputs comprising the plurality of parameters associated with the sodium ion channels of the patient, the model being previously trained using historical data, the historical data comprising ion channel gating parameters associated with sodium ion channels and their corresponding patient response to a sodium ion channel blocker;
receiving one or more outputs from the model, at least one of the one or more outputs including a predicted patient response to the sodium ion channel blocker;
transmitting, for display on the user interface, the one or more outputs from the model;
updating the historical data to include the plurality of parameters associated with the sodium ion channels of the patient and the corresponding one or more outputs; and
re-training the model using the updated historical data.
2. The method according to claim 1 , wherein the plurality of parameters further comprise ion channel gating parameters selected from a group consisting of activation rate, deactivation rate, voltage dependence of activation, voltage dependence of inactivation, inactivation rate, inactivation recovery rate, VSD activation rate, VSD deactivation rate, VSD voltage-dependence, and any combination thereof.
3. The method according to claim 1 , wherein the plurality of parameters further comprise ion channel gating parameters selected from a group consisting of DIII-VSD V1/2, DIII deactivation t, Steady-state Inactivation, inactivation at resting, inactivation t, fast recovery t, slow recovery contribution, late INa, late INa at 150 ms, DIV-VSD V1/2, DIV-VSD activation τ, and any combination thereof.
4. The method according to claim 3 , wherein the plurality of parameters are DIII-VSD V112 and slow recovery τ.
5. The method according to claim 1 , wherein the model exhibits a PLS cross-validated Q2 of at least 0.6.
6. The method according to claim 1 , wherein the model exhibits a PLS cross-validated Q2 of at least 0.9.
7. The method according to claim 1 , wherein the patient response is calculated as a ΔQT as measured by an electrocardiogram.
8. The method according to claim 1 , wherein the sodium ion channel blocker is selected from a group consisting of ranolazine, phenytoin, disopyramide, lidocaine, mexiletine, triamterene, lamotrigine, amiloride, moricizine, oxcarbazepine, quinidine, procainamide, tocainide, amiodarone, propafenone, eleclazine, flecainide, encainide, ajmaline, aprindine, tetrodotoxin, eslicarbazepine acetate, pilsicainide, and eslicarbazepine.
9. The method according to claim 8 , wherein the sodium ion channel blocker is mexiletine.
10. The method of claim 1 , wherein the patient has LQT syndrome or an arrhythmia.
11. The method of claim 10 , wherein the arrhythmia is ventricular tachycardia or ventricular fibrillation.
12. An in vitro method for predicting a patient response to a sodium ion channel blocker, the method comprising:
collecting a biological sample from a patient;
expressing at least one gene from the biological sample;
testing the expressed gene for a plurality of parameters; and
using the plurality of parameters in the model according to claim 1 to predict the patient response to the sodium ion channel blocker.
13. The method according to claim 12 , wherein the patient has LQT syndrome or an arrhythmia.
14. The method according to claim 12 , wherein the at least one gene expresses Na v 1.5.
15. The method according to claim 12 , wherein the plurality of parameters are ion channel gating parameters selected from a group consisting of activation rate, deactivation rate, voltage dependence of activation, voltage dependence of inactivation, inactivation rate, inactivation recovery rate, VSD activation rate, VSD deactivation rate, VSD voltage-dependence, and any combination thereof.
16. The method of claim 12 , wherein the plurality of parameters further comprise ion channel gating parameters selected from a group consisting of fraction of DIII-VSD activated at resting, DIII-VSD V1/2, DIII deactivation τ, Steady-state Inactivation, inactivation at resting, inactivation τ, inactivation fast recovery τ, slow recovery τ, slow recovery contribution, late INa, late INa at 150 ms, DIV-VSD V1/2, DIV-VSD activation τ, and any combination thereof.
17. The method according to claim 12 , wherein the patient response is calculated as a ΔQT as measured by an electrocardiogram.
18. The method according to claim 12 , wherein the sodium ion channel blocker is selected from a group consisting of ranolazine, phenytoin, disopyramide, lidocaine, mexiletine, triamterene, lamotrigine, amiloride, moricizine, oxcarbazepine, quinidine, procainamide, tocainide, amiodarone, propafenone, eleclazine, flecainide, encainide, ajmaline, aprindine, tetrodotoxin, eslicarbazepine acetate, pilsicainide, and eslicarbazepine.
19. The method according to claim 18 , wherein the sodium ion channel blocker is mexiletine.
20. The method according to claim 12 wherein an arrhythmia is ventricular tachycardia or ventricular fibrillation.