Nephritis_Database

Introduction

Glomerulonephritis is a very important field in nephrology, and its diagnosis must be interpreted pathologically through kidney slices, and long-term follow-up treatment is required. According to past studies, glomerulonephritis is one of the important causes of end-stage renal failure. However, in the past, there was a lack of systematic research on glomerulonephritis. In addition, the progress of molecular biology in recent years has led to different understandings of the mechanism of glomerulonephritis.

Patient Cohort

This database contains kidney biopsies at the Chang Gung Memorial Hospital (CGMH) Linkou and Keelung campuses from 2000 to 2019. The nephrologist examines the patients who have been diagnosed with kidney disease and collects basic data including patient’s age, gender, diagnosis, etc., about 4,100 people. The Chang Gung Memorial Research Database (CGRD) combines the electronic health record data from all the districts of CGMH (continuously updated): outpatient, inpatient, emergency, drug prescription and laboratory test results. For privacy consideration, each patient’s data has been de-identified and encrypted IDCODE will be assigned. Besides demographic data and clinical diagnosis collected by physicians, the database also include historical files of CGRD laboratory test results, and biological information such as genomics, proteomics, metabolomics extracted from blood and urine samples as well as pathological slice images. Figure 1 demonstrates that after we excluded patients
(1) who were unable to find corresponding IDCODE;
(2) who received kidney transplantation;
(3) who had failure of their pathological section, etc.,
finally totally 2849 kidney disease patients were remained and collected.

Figure 1. Flow of data cleaning

Figure 2. Examples of one kidney pathological section

Patients’ demographic data Summary Table

Year	F	M	Avg_age	Std
2000	36	44	40.19813	15.92709
2001	37	38	43.01173	16.70481
2002	52	56	38.96833	18.71144
2003	35	44	39.39962	18.67543
2004	50	45	35.55074	18.4875
2005	49	38	39.54172	17.20113
2006	56	56	38.7967	18.27869
2007	75	79	38.25675	19.24349
2008	75	84	38.67931	18.5901
2009	95	87	41.31868	20.13231
2010	52	91	39.82874	19.62673
2011	77	66	39.07448	18.00429
2012	54	71	42.1196	17.78032
2013	78	72	36.76107	19.21058
2014	69	98	41.45366	19.55926
2015	71	84	41.67408	19.27505
2016	94	104	41.71006	18.94485
2017	134	104	41.91387	19.08539
2018	124	97	44.27459	19.59873
2019	75	44	46.18169	19.49708

Requesting Datasets

To request a dataset, please contact the Center of Artificial Intelligence in Medicine at cgmhailab@gmail.com

License agreement

This dataset is made freely available to academic and non-academic entities for non-commercial purposes such as academic research, teaching, scientific publications, or personal experimentation. Permission is granted to use the data given that you agree:

1. That the dataset comes “AS IS”, without express or implied warranty. Although every effort has been made to ensure accuracy, we (Center for Artificial Intelligence in Medicine from Chang Gung Memorial Hospital) do not accept any responsibility for errors or omissions.
2. That you include a reference to the CGBC Dataset in any work that makes use of the dataset. Cite the following sentence: Chang Gung Breast Cancer (CGBC) database from Center for Artificial Intelligence in Medicine of Chang Gung Memorial Hospital.
3. That you do not distribute this dataset or modified versions. It is permissible to distribute derivative works in as far as they are abstract representations of this dataset (such as models trained on it or additional annotations that do not directly include any of our data) and do not allow to recover the dataset or something similar in character.
4. That you may not use the dataset or any derivative work for commercial purposes as, for example, licensing or selling the data, or using the data with a purpose to procure a commercial gain.
5. That all rights not expressly granted to you are reserved by us (Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital).