Please wait a minute...
Quantitative Biology

ISSN 2095-4689

ISSN 2095-4697(Online)

CN 10-1028/TM

邮发代号 80-971

Quantitative Biology  2019, Vol. 7 Issue (3): 210-232   https://doi.org/10.1007/s40484-019-0173-x
  本期目录
Understanding traditional Chinese medicine via statistical learning of expert-specific Electronic Medical Records
Yang Yang1,2, Qi Li1, Zhaoyang Liu1, Fang Ye3, Ke Deng1()
1. Center for Statistical Science & Department of Industry Engineering, Tsinghua University, Beijing 100084, China
2. Department of Mathematical Sciences, Tsinghua University, Beijing 100084, China
3. Zhou Zhongying’s Studio, Nanjing University of Chinese Medicine, Nanjing 210046, China
 全文: PDF(4284 KB)   HTML
Abstract

Background: Traditional Chinese medicine (TCM) has been attracting lots of attentions from various disciplines recently. However, TCM is still mysterious because of its unique philosophy and theoretical thinking. Due to the lack of high quality data, understanding TCM thoroughly faces critical challenges. In this study, we introduce the Zhou Archive, a large-scale database of expert-specific Electronic Medical Records containing information about 73,000+ visits to one TCM doctor for over 35 years. Covering the full spectrum of diagnosis-treatment model behind TCM practice, the archive provides an opportunity to understand TCM from the data-driven perspective.

Methods: Processing the text data in the archive via a series of data processing steps, we transformed the semi-structured EMRs in the archive to a well-structured feature table. Based on the structured feature table obtained, a series of statistical analyses are implemented to learn principles of TCM clinical practice from the archive, including correlation analysis, enrichment analysis, embedding analysis and association pattern discovery.

Results: A structured feature table of 14,000+ features is generated at the end of the proposed data processing procedure, with a feature codebook, a term dictionary and a term-feature map as byproducts. Statistical analysis of the feature table reveals underlying principles about the diagnosis-treatment model of TCM, helping us better understand the TDM practice from a data-driven perspective.

Conclusion: Expert-specific EMRs provide opportunities to understand TCM from the data-driven perspective. Taking advantage of recent progresses on NLP for Chinese, we can process a large number of TCM EMRs efficiently to gain insights via statistical analysis.

Key wordsTCM    EMRs    data-driven perspective    Chinese text mining    statistical analysis
收稿日期: 2018-08-28      出版日期: 2019-10-14
Corresponding Author(s): Ke Deng   
 引用本文:   
. [J]. Quantitative Biology, 2019, 7(3): 210-232.
Yang Yang, Qi Li, Zhaoyang Liu, Fang Ye, Ke Deng. Understanding traditional Chinese medicine via statistical learning of expert-specific Electronic Medical Records. Quant. Biol., 2019, 7(3): 210-232.
 链接本文:  
https://academic.hep.com.cn/qb/CN/10.1007/s40484-019-0173-x
https://academic.hep.com.cn/qb/CN/Y2019/V7/I3/210
Fig.1  
Tongue Picture Pluse Type Lab Tests TCM Patheogenesis TCM Therapy Herbs
503 142 393 1,033 1,699 1,515
Dark Thin pulse B ultrasound Impairment of both Qi and Yin Invigorating Qi and nourishing Yin Rhizoma pinellinae praeparata
Dark red Slippery pulse Biochemical test Weakness of liver and kidney Tonifying liver and kidney Pseudostellariae radix
Yellow, thin and greasy tongue fur Stringy pulse CT Syndrome of liver and stomach disharmony Regulating liver and spleen Radix glycyrrhizae
Red Small pulse Blood examination Dampness-heat obstruction syndrome Clearing dampness-heat Salvia miltiorrhiza
Thin, yellow and greasy tongue fur Rapid pulse Echogatstroscope Kidney deficiency and sthenic liver-energy Clearing dampness-heat and stasis toxin Red paeonia
Yellow tongue fur Soft pulse Liver function test Dampness-heat in the interior Catharsis and thanhhoa Boiled bombyx batryticatus
Thin and yellow tongue fur Deep pulse BP Deficiency of liver and kidney Dissipating phlegm and removing blood stasis Poria cocos
Yellow and greasy tongue fur Relaxed pulse ALT Impairment of both liver and spleen Strengthening body and anti-cancer Processed rhizoma
Light yellow, thin and greasy tongue fur Weak pulse Fatty liver Phlegm stagnation in collateral Invigorating spleen and stomach Unprocessed rehmannia root
Thin tongue fur Feeble pulse Liver function retest Weakness of both Qi and Yin Nourishing upper warmer Coptidis
Dark violet Left slippery pulse Urinalysis Yin deficiency of liver and kidney Regulating the thoroughfare Fried atractylodes macrocephala koidz
Reddish Right slippery pulse HP Phlegm and blood stasis Diffusing and clearing upper warmer Glehniae radix
Light yellow and greasy tongue fur Right thin pulse AST Spleen deficiency and stomach weakness Treating both cause and symptoms Ophiopogonis radix
Cracked Left stringy pulse CA199 Wind-phlegm stagnation Relieving liver and gallbladder Dried orange peel
Violet Right stringy pulse WBC Combination of dampness-heat and stasis toxin Activating blood and dredging Ligusticum wallichii
Toothed Left thin pulse Routine urine test Lower weakness in liver and kidney Hyperactivity nourishing heart to calm mind Astragali radix
Thin and greasy tongue fur Uneven pulse CEA Endogenous wind rise Treating symptoms first Rhizoma anemarrhenae
Light yellow tongue fur Irregular pulse CA125 Impairment of both body fluids and Qi Nourishing liver and kidney Caulis spatholobi
Dark and light purple Left small pulse HBsAg Occurrence of cancer toxin Nourishing blood and thinning liver Andeophorae radix
Tongue tip red Right small pulse MRI Kidney deficiency and liver depression Strengthening spleen in transportation Barbary wolfberry fruit
Tab.1  
Term Count Term Count Term Count Term Count Term Count
Dry mouth 3,353 Abdominal distension 482 ?Insomnia 259 Edema of lower limbs 168 Hidden pain in liver 139
Deep-colored urine 1,448 Belching 461 Feel agitated 256 Headache 168 Numb hand 137
Fatigue 1,158 Pathology 413 Vomiting 230 Dreaminess in night 168 Feverishness in palms and soles 137
Sensation of chill 983 Cough 378 Gasteremphraxis 223 Stiff neck 168 Short of breath 136
Poor sleep 934 Good appetite 371 Hypertension 220 Unnormal stool 166 Cholecystitis 135
Poor appetite 893 Frequent urinary 357 Dreaminess 213 Not painful 165 Color in yellow 135
Dizziness 769 A little dry mouth 355 Out of breath 213 Not a lot stool 162 Down more than quantity 134
Good defecation 763 Backache 331 Yellow face and poor looking 210 Unobvious dry mouth 158 Stomache 133
Oppression in chest 758 Slightly decayed stool 310 Sore throat 209 Dry throat 156 Eat a little 133
Soreness of waist 757 Slightly regular bowel 308 Feeble leg 207 Frequent passing of flatus 156 Emaciation 131
Normal bowel 746 Borborygmus 300 Feel tired 199 Heating palm 152 Fatty liver 131
Regular bowel 658 Sweating 299 Feel fatigue 193 Noisy heart 151 Much poor sleep 131
Bitter taste in mouth 612 Acid regurgitation 290 Inhibited defecation 189 Poor breathing 150 Limb leg 131
Dry mouth and want to drink 568 Tinnitus 288 Normal hepatic region 185 Constious fatigue 149 CT 130
Dry and hard stool 564 Dry stool 286 Sick to vomiting 176 A lot of menstruation 148 Dry mouth at night 128
Sweat easily 562 Undry mouth 286 Not too many self-conscious Symptoms 176 Deep sore throat 145 Drink a little 127
Slightly dry stool 533 Taste food well 274 Blurred eye 173 Not much expectoration 145 Normal stool with shape 126
Dry and bitter taste in mouth 528 Nauseating 271 Loose stool 172 Dry and bitter mouth 141 Little in menstruation 125
Palpitation 504 Dizziness 269 Poor looking 172 Odor in mouth 140 Sweatly a lot 125
Normal appetite 492 Not dry stool 264 Quite good appetite 172 Get cold easily 140 Poor appetite 122
Tab.2  
Symptoms Body parts Disease names Lab tests Medical treatments Background terms
14,346 3,665 2,050 956 437 60,623
Dry mouth Dry stool Hand Gastral cavity High blood pressure Gastrosis Blood pressure Hemameba Chemotherapy Take TCM Stool Past days
Cough Loose stool Abdomen Lower limb Hepatitis B Myoma of uterus CT Protein Radiotherapy Gallbladder removal Pain Examination
Fatigue Bitter taste in mouth Stomach Brain Adenocarcinoma HLP liver function test MRI After chemotherapy Take prednisone Surgery Treatment
Debility Nausea Heart Liver Gastritis Cervical spondylosis health examination Liver function test Chemotherapy after surgery Gallbladder surgery Normal Hospital
Vertigo Poor appetite Head Nose Diabetes Gastric cancer Gastroscope Liver function Chemotherapy and radiotherapy 4 cycles of chemotherapy Now Test
Sensation of chill Dyspepsodynia Eye Lymph Capsulitis Enteritis B ultrasound Urine test 6 cycles of chemotherapy After radiotherapy Obviously Unwell
Oppression in chest Headache Chest ?Joint Cholecystitis Squamous cancer Glucose Stool volume Take insulin Gamma knife treatment Sometimes Discover
Deep-colored urine Belching Waist Bone Liver cirrhosis Rhinitis Ascites Enteroscope Colon cancer surgery 1 time of chemotherapy Less Usually
Fatigue and debility Dizziness Foot Ear Hypertensive disease Hepatitis B disease Fatness in liver CT scan Do chemotherapy 2 times of chemotherapy Self constious Transfer
Abdominal distension Insomnia Lung Upper body Gallstones Coronary heart disease Menstrual blood volume Heart rate Induced abortion Western medicine control Last year Currently
Palpitation Gasteremphraxis Back Hepatic region Hepatopathy Nephritis Blood volume Electrocardiogram Rectal cancer surgery 2 cycles of chemotherapy This year Worse
Soreness of waist Swelling pain Gallbladder Hand and foot Lung cancer Lipemia Body weight Occult blood test Take antihypertensive drug Hormone treatment Disease history Long time
Dull pain Numbness Intestine Lymph gland Intestinal cancer Hyperlipemia Three positive ALT Take western medicine Take chemotherapy medicine Recently Urine and stool
Poor sleep Catching cold Gland Shoulder Hepatitis Liver cancer test blood pressure Renal function TCM treatment 6 times of chemotherapy Appetite Left side
Stomachache Well gas Neck Face Cerebral infarction Breast cancer urine volume Blood type 4 cycles of chemotherapy Successive chemotherapy Discomfort After treatment
Tab.3  
Fig.2  
  Discovered Words Overlap with Jieba Overlap with SP Overlap with LTP Overlap with THULAC Overlap with TopWORDS Overlap with Segment List
Jieba 23,989 23,989 (100%) 13,906 (68%) 13,688 (57%) 13,270 (55%) 9,864 (41%) 2,765 (12%)
SP 26,358 13,906 (53%) 26,358 (100%) 14,815 (56%) 14,217 (54%) 10,722 (41%) 4,899 (19%)
LTP 28,619 13,688 (48%) 14,818 (52%) 28,619 (100%) 20,137 (70%) 10,923 (38%) 4,142 (14%)
THULAC 30,254 13,270 (44%) 14,217 (47%) 20,137 (67%) 30,254 (100%) 12,088 (40%) 4,096 (14%)
TopWORDS 47,248 9,864 (21%) 10,722 (23%) 10,923 (23%) 12,088 (26%) 47,248 (100%) 17,365 (37%)
Tab.4  
  Discovered Words Overlap with Jieba Overlap with SP Overlap with LTP Overlap with THULAC Overlap with TopWORDS Overlap with Segment List
Jieba 11,412 11,412 (100%) 7,419 (65%) 7,025 (62%) 6,907 (61%) 8,062 (71%) 2,061 (18%)
SP 11,225 7,419 (66%) 11,225 (100%) 7,442 (66%) 7,261 (65%) 8,275 (74%) 2,699 (24%)
LTP 11,590 7,025 (61%) 7,442 (64%) 11,590 (100%) 9,184 (79%) 8,050 (69%) 2,456 (21%)
THULAC 12,298 6,907 (56%) 7,261 (59%) 9,184 (75%) 12,298 (100%) 8,343 (68%) 2,484 (20%)
TopWORDS 43,300 8,062 (19%) 8,275 (19%) 8,050 (19%) 8,343 (19%) 43,300 (100%) 16,593 (38%)
Tab.5  
    Contribution by different methods
  Total number Jieba SP LTP THULAC TopWORDS
Technical terms 21,454 3,500 (16%) 5,419 (25%) 5,340 (25%) 6,018 (28%) 18,844 (88%)
Background terms 60,623 21,037 (35%) 19,858 (33%) 23,485 (39%) 24,720 (41%) 27,929 (46%)
Suspicious terms 5,755 968 (17%) 2,510 (44%) 1,420 (25%) 1,121 (19%) 2,564 (45%)
Frequent Technical terms 15,513 2,291 (15%) 2,767 (18%) 2,833 (18%) 3,069 (20%) 15,209 (98%)
Frequent Background terms 35,004 9,871 (28%) 8,963 (26%) 9,642 (28%) 10,069 (29%) 27,623 (79%)
Frequent Suspicious terms 2,940 379 (13%) 622 (21%) 407 (14%) 406 (14%) 2,554 (87%)
Tab.6  
  Segmentation Sites Overlap with Jieba Overlap with SP Overlap with LTP Overlap with THULAC Overlap with TopWORDS
Jieba 469,381 469,381 (100%) 382,513 (81%) 396,660 (85%) 393,300 (84%) 162,473 (35%)
SP 476,058 382,513 (80%) 476,058 (100%) 418,836 (88%) 408,289 (86%) 160,548 (34%)
LTP 525,648 396,660 (75%) 418,836 (80%) 525,648 (100%) 476,232 (91%) 158,298 (30%)
THULAC 525,308 393,300 (75%) 408,289 (78%) 476,232 (91%) 525,308 (100%) 160,094 (30%)
TopWORDS 185,869 162,473 (87%) 160,548 (86%) 158,298 (85%) 160,094 (86%) 185,869 (100%)
Tab.7  
  Segmented Words Overlap with Jieba Overlap with SP Overlap with LTP Overlap with THULAC Overlap with TopWORDS
Jieba 709,385 709,385 (100%) 484,564 (68%) 479,641 (68%) 475,637 (67%) 201,698 (28%)
SP 716,062 484,564 (68%) 716,062 (100%) 533,394 (74%) 512,552 (72%) 201,159 (28%)
LTP 765,652 479,641 (63%) 533,394 (70%) 765,652 (100%) 645,135 (84%) 184,021 (24%)
THULAC 765,312 475,637 (62%) 512,552 (67%) 645,135 (84%) 765,312 (100%) 185,705 (24%)
TopWORDS 425,873 201,698 (47%) 201,159 (47%) 184,021 (43%) 185,705 (44%) 425,873 (100%)
Tab.8  
Fig.3  
Fig.4  
Fig.5  
Fig.6  
Fig.7  
Symptoms Herbs
Dry mouth Glehniae radix, andeophorae radix
Dried rhizome of rehmanni, salivia chinensis
Dendrobium
Radix trichosanthis, asparagus cochinchinensis, ophiopogonis radix
Radix trichosanthis, rhizoma anemarrhenae
Calcined oyster, calcined fossil fragment
Asparagus cochinchinensis, ophiopogonis radix
Figwort root, flos chrysanthemi indici
Hiraute shiny bugleweed herb, alismatis
Poor sleep Tuber fleeceflower stem
Cooked date seed
Asparagus cochinchinensis, lilium davidii, cooked date seed
Cortex albiziae
Asparagus cochinchinensis, cooked date seed
Asparagus cochinchinensis, lilium davidii, cooked date seed, cortex albiziae
Stomach distension Processed rhizoma, caulis perllae
Coptidis
Fried Fructus aurantii immaturus, rhizoma pinellinae praeparata
Dried orange peel, rhizoma pinellinae praeparata
Dried orange peel, immature tangerine peel
Debility Eclipta alba, processed glossy privet fruit
Fried atractylodes macrocephala koidz, poria cocos, codonopsis, radix glycyrrhizae
Red paeonia, processed rhizoma, vinegar-baked bupleurum root
Fried atractylodes macrocephala koidz, poria cocos, radix glycyrrhizae, pseudostellariae radix
Asparagus cochinchinensis, ophiopogonis radix
Belching Rhizoma pinellinae praeparata
Coptidis
Fructus amomi
Gastralgia Processed rhizoma, caulis perllae
Rhizoma pinellinae praeparata
Fructus amomi, costus root
Dizziness Tribulus terrestris, gastrodiae, ligusticum wallichii
Tribulusterrestris, chrysanthemum, gastrodiae
Gastrodiae, ligusticum wallichii
Sensation of chill Radix glycyrrhizae, processed cassia twig
Parched white peony root, processed cassia twig
Cinnamon
Palpitation Salvia miltiorrhiza, ligusticum wallichii
Salvia miltiorrhiza
Headache Tribulusterrestris, gastrodiae, ligusticum wallichii
Ligusticum wallichii
Poor appetite Fried atractylodes macrocephala koidz, poria cocos, radix glycyrrhizae
Pseudostellariae radix, coloured malt, fried millet sprout
Yellowish complexion Astragali radix
Chinese angelica
Cough Glehniae radix, ophiopogonis radix
Glehniae radix
Dry stool Fructus trichosanthis
Roasted Fructus aurantii immaturus, fructus trichosanthis
Vertigo Barbary wolfberry fruit, gastrodiae
Deep-colored urine Radix sophorae flavescentis
Bitter in mouth Fructus evodiae, coptidis
Abdominal distension Dried orange peel, immature tangerine peel
Feel agitated Asparagus cochinchinensis, lilium davidii
Borborygmus Fructus evodiae, coptidis
Loose stool Fried atractylodes macrocephala koidz, codonopsis
Cough, oppression in chest Rhizoma pinellinae praeparata
Oppression in chest Red paeonia, processed rhizoma, vinegar-baked bupleurum root
oppression in chest, palpitation Salvia miltiorrhiza
Nausea, vomiting Rhizoma pinellinae praeparata
Tab.9  
1 W. H. Liu, (2017) TCM acupuncture-moxibustion: contributing to human health. World J. Acupunct. Moxibustion, 27, 1
https://doi.org/10.1016/S1003-5257(17)30089-2.
2 A. C. Ahn, , T. Bennani, , R. Freeman, , O. Hamdy, and T. J. Kaptchuk, (2007) Two styles of acupuncture for treating painful diabetic neuropathy–a pilot randomised control trial. Acupunct. Med., 25, 11–17
https://doi.org/10.1136/aim.25.1-2.11. pmid: 17641562
3 Z. Liu, , F. Sun, , M. Zhu, and X. Wang, (2004) Effect of acupuncture on insulin resistance in non-insulin dependent diabetes mellitus. J. Acupunt.Tuina Sci., 2, 8–11
https://doi.org/10.1007/BF02848387.
4 S. Li, and B. Zhang, (2013) Traditional Chinese medicine network pharmacology: theory, methodology and application. Chin. J. Nat. Med., 11, 110–120
https://doi.org/10.1016/S1875-5364(13)60037-0. pmid: 23787177
5 B. Zhang, , X. Wang, and S. Li, (2013) An integrative platform of TCM network pharmacology and its application on a herbal formula, Qing-Luo-Yin. Evid. Based Complement. Alternat. Med., 2013, 456747
https://doi.org/10.1155/2013/456747. pmid: 23653662
6 S. Li, , B. Zhang, and N. Zhang, (2011) Network target for screening synergistic drug combinations with application to traditional Chinese medicine. BMC Syst. Biol., 5, S10
https://doi.org/10.1186/1752-0509-5-S1-S10. pmid: 21689469
7 W. Lam, , S. Bussom, , F. Guan, , Z. Jiang, , W. Zhang, , E. A. Gullen, , S. H. Liu, and Y. C. Cheng, (2010) The four-herb Chinese medicine PHY906 reduces chemotherapy-induced gastrointestinal toxicity. Sci. Transl. Med., 2, 45ra59
https://doi.org/10.1126/scitranslmed.3001270. pmid: 20720216
8 Y. Z. Xiang, , H. C. Shang, , X. M. Gao, and B. L. Zhang, (2008) A comparison of the ancient use of ginseng in traditional Chinese medicine with modern pharmacological experiments and clinical trials. Phytother. Res., 22, 851–858
https://doi.org/10.1002/ptr.2384. pmid: 18567057
9 J. Jian, and Z. Wu, (2004) Influences of traditional Chinese medicine on non-specific immunity of Jian Carp (Cyprinus carpio var. Jian). Fish Shellfish Immunol., 16, 185–191
https://doi.org/10.1016/S1050-4648(03)00062-7. pmid: 15123322
10 R. J. Bick, , B. J. Poindexter, , R. R. Sweney, and A. Dasgupta, (2002) Effects of Chan Su, a traditional Chinese medicine, on the calcium transients of isolated cardiomyocytes: cardiotoxicity due to more than Na, K-ATPase blocking. Life Sci., 72, 699–709
https://doi.org/10.1016/S0024-3205(02)02302-0. pmid: 12467910
11 K. Iwasaki, , T. Satoh-Nakagawa, , M. Maruyama, , Y. Monma, , M. Nemoto, , N. Tomita, , H. Tanji, , H. Fujiwara, , T. Seki, , M. Fujii, , et al. (2005) A randomized, observer-blind, controlled trial of the traditional Chinese medicine Yi-Gan San for improvement of behavioral and psychological symptoms and activities of daily living in dementia patients. J. Clin. Psychiatry, 66, 248–252
https://doi.org/10.4088/JCP.v66n0214. pmid: 15705012
12 K. Deng, , D. Liu, , S. Gao, and Z. Geng, (2005) Structural learning of graphical models and its applications to traditional Chinese medicine. Lect. Notes Comput. Sci., 3614, 362–367
https://doi.org/10.1007/11540007_45.
13 Y. Feng, , Z. Wu, , X. Zhou, , Z. Zhou, and W. Fan, (2006) Knowledge discovery in traditional Chinese medicine: state of the art and perspectives. Artif. Intell. Med., 38, 219–236
https://doi.org/10.1016/j.artmed.2006.07.005. pmid: 16930966
14 H. Yang, , J. Chen, , S. Tang, , Z. Li, , Y. Zhen, , L. Huang, and J. Yi, (2009) New drug R&D of traditional Chinese medicine: role of data mining approaches. J. Biol. Syst., 17, 329–347
https://doi.org/10.1142/S0218339009002971.
15 Q. Wang, and Y. Zhu, (2009) Epidemiological investigation of constitutional types of Chinese medicine in general population: based on 21,948 epidemiological investigation data of nine provinces in China. Zhonghua Zhongyiyao Zazhi (in Chinese), 24, 7–12
16 R. Xue, , Z. Fang, , M. Zhang, , Z. Yi, , C. Wen, and T. Shi, (2013) TCMID: traditional Chinese Medicine integrative database for herb molecular mechanism analysis. Nucleic Acids Res., 41, D1089–D1095
https://doi.org/10.1093/nar/gks1100. pmid: 23203875
17 B. Liu, , X. Zhou, , Y. Wang, , J. Hu, , L. He, , R. Zhang, , S. Chen, and Y. Guo, (2012) Data processing and analysis in real-world traditional Chinese medicine clinical data: challenges and approaches. Stat. Med., 31, 653–660
https://doi.org/10.1002/sim.4417. pmid: 22161304
18 X. Wang, , H. Qu, , P. Liu, and Y. Cheng, (2004) A self-learning expert system for diagnosis in traditional Chinese medicine. Expert Syst. Appl., 26, 557–566
https://doi.org/10.1016/j.eswa.2003.10.004.
19 S. Yu, , Y. Ma, , J. Gronsbell, , T. Cai, , A. N. Ananthakrishnan, , V. S. Gainer, , S. E. Churchill, , P. Szolovits, , S. N. Murphy, , I. S. Kohane, , et al. (2018) Enabling phenotypic big data with PheNorm. J. Am. Med. Inform. Assoc., 25, 54–60
https://doi.org/10.1093/jamia/ocx111. pmid: 29126253
20 D. M. Roden, , J. M. Pulley, , M. A. Basford, , G. R. Bernard, , E. W. Clayton, , J. R. Balser, and D. R. Masys, (2008) Development of a large-scale de-identified DNA biobank to enable personalized medicine. Clin. Pharmacol. Ther., 84, 362–369
https://doi.org/10.1038/clpt.2008.89. pmid: 18500243
21 D. R. Blair, , C. S. Lyttle, , J. M. Mortensen, , C. F. Bearden, , A. B. Jensen, , H. Khiabanian, , R. Melamed, , R. Rabadan, , E. V. Bernstam, , S. Brunak, , et al. (2013) A nondegenerate code of deleterious variants in Mendelian loci contributes to complex disease risk. Cell, 155, 70–80
https://doi.org/10.1016/j.cell.2013.08.030. pmid: 24074861
22 M. Rotmensch, , Y. Halpern, , A. Tlimat, , S. Horng, and D. Sontag, (2017) Learning a health knowledge graph from electronic medical records. Sci. Rep., 7, 5994
https://doi.org/10.1038/s41598-017-05778-z. pmid: 28729710
23 S. Blecker, , S. D. Katz, , L. I. Horwitz, , G. Kuperman, , H. Park, , A. Gold, and D. Sontag, (2016) Comparison of approaches for heart failure case identification from electronic health record data. JAMA Cardiol., 1, 1014–1020
https://doi.org/10.1001/jamacardio.2016.3236. pmid: 27706470
24 J. C. Denny, , L. Bastarache, , M. D. Ritchie, , R. J. Carroll, , R. Zink, , J. D. Mosley, , J. R. Field, , J. M. Pulley, , A. H. Ramirez, , E. Bowton, , et al. (2013) Systematic comparison of phenome-wide association study of electronic medical record data and genome-wide association study data. Nat. Biotechnol., 31, 1102–1110
https://doi.org/10.1038/nbt.2749. pmid: 24270849
25 F. Doshi-Velez, , Y. Ge, and I. Kohane, (2014) Comorbidity clusters in autism spectrum disorders: an electronic health record time-series analysis. Pediatrics, 133, e54–e63
https://doi.org/10.1542/peds.2013-0819. pmid: 24323995
26 P. C. Chang, , H. Tseng, , J. Dan, and C. D. Manning, (2009) Discriminative reordering with Chinese grammatical relations features. In: SSST’ 09 Proceedings of the 3rd Workshop on Syntax and Structure in Statistical Translation. pp. 51–59
27 R. Levy, and C. D. Manning, (2003) Is it harder to parse Chinese, or the Chinese Treebank? In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, 1, 439–446
28 W. Che, , Z. Li, and T. Liu, (2010) LTP: A Chinese language technology platform. In: COLING’10 Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations, pp. 13–16
29 M. Sun, , X. Chen, , K. Zhang, , Z. Guo, , J. Ma, and Z. Liu, (2016) THULAC: An efficient lexical analyzer for Chinese
30 Z. Li, and M. Sun, (2009) Punctuation as implicit annotations for Chinese word segmentation. Comput. Linguist., 35, 505–512
https://doi.org/10.1162/coli.2009.35.4.35403.
31 K. Deng, , P. K. Bol, , K. J. Li, and J. S. Liu, (2016) On the unsupervised analysis of domain-specific Chinese texts. Proc. Natl. Acad. Sci. USA, 113, 6154–6159
https://doi.org/10.1073/pnas.1516510113. pmid: 27185919
32 O. Levy, and Y. Goldberg, (2014) Neural word embedding as implicit matrix factorization. In: Adv. Neural Inf. Process. Syst. Conference
33 L. Maaten, and G. E. Hinton, (2008) Visualizing high-dimensional data using t-SNE. J. Mach. Learn. Res., 9, 2579–2605
34 I. Borg, and P. Groenen, (1987) Modern multidimensional scaling: theory and applications. J. Educ. Meas., 40, 277–280
35 R. Agrawal, , T. Imielinski, and A. Swami, (1993) Mining association rules between sets of items in large databases. In: SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data, pp. 207–216
36 R. Agrawal, and R. Srikant, (1994) Fast algorithms for mining association rules. In: Readings in database systems (3rd ed.), pp. 580–592. San Francisco: Morgan Kaufmann Publishers Inc.
37 P. He, , K. Deng, , Z. Liu, , D. Liu, , J. S. Liu, and Z. Geng, (2012) Discovering herbal functional groups of traditional Chinese medicine. Stat. Med., 31, 636–642
https://doi.org/10.1002/sim.4146. pmid: 21413055
38 K. Deng, , Z. Geng, and J. S. Liu, (2014) Association pattern discovery via theme dictionary models. J. R. Stat. Soc. B, 76, 319–347
https://doi.org/10.1111/rssb.12032.
[1] QB-19173-OF-DK_suppl_1 Download
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed