filter and avg qrs, ~90% finished
parent
52a8e8eeca
commit
c973200227
|
|
@ -0,0 +1,359 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# QRS Complex Detection\n",
|
||||
"This notebook holds all the functions to detect a QRS-Complex in an ECG Signal. To be able to differentiate if the signal is from a \"healthy\" person or a person with a \"heartcondition\".\n",
|
||||
"First of all there must be defined some thresholds to what a \"healthy\" QRS-Complex is. To do so we normalize the Data and extract the normal peaks and lengths of the ECG-Signal in the QRS Region."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Import necessary packages\n",
|
||||
"\n",
|
||||
"import neurokit2 as nk\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import json\n",
|
||||
"import sys\n",
|
||||
"import wfdb\n",
|
||||
"\n",
|
||||
"sys.path.append('../scripts')\n",
|
||||
"import data_helper"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Load Data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Reading SB\n",
|
||||
"Reading AFIB\n",
|
||||
"Reading GSVT\n",
|
||||
"Reading SR\n",
|
||||
"Number of patients per category:\n",
|
||||
"SB: 16559\n",
|
||||
"AFIB: 9839\n",
|
||||
"GSVT: 948\n",
|
||||
"SR: 9720\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data_org = data_helper.load_data(only_demographic=False)\n",
|
||||
"\n",
|
||||
"print(\"Number of patients per category:\")\n",
|
||||
"for cat_name in data_org.keys():\n",
|
||||
" print(f\"{cat_name}: {len(data_org[cat_name])}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Cleaning Data from Noice"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# seperating data by diagnose\n",
|
||||
"sb_data = data_org['SB']\n",
|
||||
"afib_data = data_org['AFIB']\n",
|
||||
"gsvt_data = data_org['GSVT']\n",
|
||||
"sr_data = data_org['SR']\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"CPU times: total: 562 ms\n",
|
||||
"Wall time: 1.46 s\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"with open('../filter_params.json','r') as f:\n",
|
||||
" filter_params = json.load(f)\n",
|
||||
"sig_channel = 0\n",
|
||||
"np.random.seed(501)\n",
|
||||
"sampling_rate = 500\n",
|
||||
"### Pick Random Samples from Set\n",
|
||||
"amount_sb_records = len(sb_data)\n",
|
||||
"sample_indizies = np.random.choice(amount_sb_records,1000,replace=False)\n",
|
||||
"sb_data_sample = [sb_data[x].p_signal[:,sig_channel] for x in sample_indizies]\n",
|
||||
"clean_sb = [nk.ecg_clean(elem,sampling_rate=sampling_rate) for elem in sb_data_sample]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"CPU times: total: 375 ms\n",
|
||||
"Wall time: 1.77 s\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"amount_afib_records = len(afib_data)\n",
|
||||
"sample_indizies = np.random.choice(amount_afib_records,1000,replace=False)\n",
|
||||
"afib_data_sample = [afib_data[x].p_signal[:,sig_channel] for x in sample_indizies]\n",
|
||||
"clean_afib = [nk.ecg_clean(elem,sampling_rate=sampling_rate) for elem in afib_data_sample]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"CPU times: total: 547 ms\n",
|
||||
"Wall time: 1.8 s\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"gsvt_data_sample= [gsvt_data[x].p_signal[:,sig_channel] for x in range(len(gsvt_data))]\n",
|
||||
"clean_gsvt = [nk.ecg_clean(elem,sampling_rate=sampling_rate) for elem in gsvt_data_sample]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"CPU times: total: 391 ms\n",
|
||||
"Wall time: 1.72 s\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"amount_sr_records = len(sr_data)\n",
|
||||
"sample_indizies = np.random.choice(amount_sr_records,1000,replace=False)\n",
|
||||
"sr_data_sample = [sr_data[x].p_signal[:,sig_channel] for x in sample_indizies] \n",
|
||||
"clean_sr = [nk.ecg_clean(elem,sampling_rate=sampling_rate) for elem in sr_data_sample]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Lokalisierung der QRS-Komplexe"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"avg_sb = np.mean(clean_sb,axis=1)\n",
|
||||
"\n",
|
||||
"avg_afib = np.mean(clean_afib,axis=1)\n",
|
||||
"\n",
|
||||
"avg_gsvt = np.mean(clean_gsvt,axis=1)\n",
|
||||
"\n",
|
||||
"avg_sr = np.mean(clean_sr,axis=1)\n",
|
||||
"\n",
|
||||
"def get_r_peaks(clean_ecg_data,sampling_rate)->list:\n",
|
||||
" return [nk.ecg_peaks(record,sampling_rate=sampling_rate)[1] for record in clean_ecg_data]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sb_r_peaks = get_r_peaks(clean_sb,sampling_rate)\n",
|
||||
"afib_r_peaks = get_r_peaks(clean_afib,sampling_rate)\n",
|
||||
"# gsvt_r_peaks = get_r_peaks(clean_gsvt,sampling_rate)\n",
|
||||
"sr_r_peaks = get_r_peaks(clean_sr,sampling_rate)\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# sb_r_peaks = [x for x in sb_r_peaks if len(x['ECG_R_Peaks'])>3]\n",
|
||||
"def remove_with_to_few(signals,clean):\n",
|
||||
" index_for_removal = []\n",
|
||||
" for index, element in enumerate(signals):\n",
|
||||
" if len(element['ECG_R_Peaks']) < 3:\n",
|
||||
" index_for_removal.append(index)\n",
|
||||
" for i in index_for_removal:\n",
|
||||
" del clean[i]\n",
|
||||
" del signals[i]\n",
|
||||
" return signals,clean\n",
|
||||
"\n",
|
||||
"sb_r_peaks,clean_sb = remove_with_to_few(sb_r_peaks,clean_sb)\n",
|
||||
"afib_r_peaks,clean_afib = remove_with_to_few(afib_r_peaks,clean_afib)\n",
|
||||
"sr_r_peaks,clean_sr = remove_with_to_few(sr_r_peaks,clean_sr)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"sb done\n",
|
||||
"afib done\n",
|
||||
"sr done\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"def get_infos(ecg_data,r_peaks,sampling_rate:int)->list:\n",
|
||||
" return [nk.ecg_delineate(ecg_data[x],r_peaks[x]['ECG_R_Peaks'],sampling_rate=sampling_rate,method=\"dwt\")[1]for x in range(len(ecg_data))]\n",
|
||||
"\n",
|
||||
"sb_info = get_infos(clean_sb,sb_r_peaks,sampling_rate=sampling_rate)\n",
|
||||
"print('sb done')\n",
|
||||
"afib_info = get_infos(clean_afib,afib_r_peaks,sampling_rate=sampling_rate)\n",
|
||||
"print('afib done')\n",
|
||||
"sr_info = get_infos(clean_sr,sr_r_peaks,sampling_rate=sampling_rate)\n",
|
||||
"print('sr done')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import math\n",
|
||||
"# Removes nan values from P and T peaks and removed corosponding 'base' signals\n",
|
||||
"def remove_nan(signal,clean_signal):\n",
|
||||
" nan_indizies = []\n",
|
||||
" for i in range(len(signal)):\n",
|
||||
" if math.isnan(signal[i]['ECG_P_Peaks'][0]):\n",
|
||||
" nan_indizies.append(i)\n",
|
||||
" for i in range(len(signal)):\n",
|
||||
" if math.isnan(signal[i]['ECG_T_Peaks'][0]):\n",
|
||||
" nan_indizies.append(i)\n",
|
||||
" nth_removed_index = 0\n",
|
||||
" for i in nan_indizies:\n",
|
||||
" del signal[i-nth_removed_index]\n",
|
||||
" del clean_signal[i-nth_removed_index]\n",
|
||||
" nth_removed_index+=1\n",
|
||||
" return signal,clean_signal\n",
|
||||
"\n",
|
||||
"sb_info,clean_sb = remove_nan(sb_info,clean_sb)\n",
|
||||
"afib_info,clean_afib = remove_nan(afib_info,clean_afib)\n",
|
||||
"sr_info,clean_sr = remove_nan(sr_info,clean_sr)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"sb_p 854 sb_t 854 sb_clean 854\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# get first P Peaks in Signals\n",
|
||||
"first_sb_p_peak = [elem['ECG_P_Peaks'][0] for elem in sb_info]\n",
|
||||
"first_afib_p_peak = [elem['ECG_P_Peaks'][0] for elem in afib_info]\n",
|
||||
"first_sr_p_peak = [elem['ECG_P_Peaks'][0] for elem in sr_info]\n",
|
||||
"\n",
|
||||
"# get first T Peaks in Signals\n",
|
||||
"first_sb_t_peak = [elem['ECG_T_Peaks'][0] for elem in sb_info]\n",
|
||||
"first_afib_t_peak = [elem['ECG_T_Peaks'][0] for elem in afib_info]\n",
|
||||
"first_sr_t_peak = [elem['ECG_T_Peaks'][0] for elem in sr_info]\n",
|
||||
"\n",
|
||||
"print(\"sb_p\",len(first_sb_p_peak),'sb_t',len(first_sb_t_peak),'sb_clean',len(clean_sb))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def cut_signals(signals,first_p,first_t):\n",
|
||||
" return [signals[i][first_p[i]:first_t[i]] for i in range(len(signals))]\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"sliced_sb = cut_signals(clean_sb,first_sb_p_peak,first_sb_t_peak)\n",
|
||||
"sliced_afib = cut_signals(clean_afib,first_afib_p_peak,first_afib_t_peak)\n",
|
||||
"sliced_sr = cut_signals(clean_sr,first_sr_p_peak,first_sr_t_peak)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
Loading…
Reference in New Issue