Modeling COVID-19 Vaccine Adverse Effects with a Visualized Knowledge Graph Database
Abstract
:1. Introduction
2. Materials and Methods
2.1. Dataset
2.2. System Overview
2.3. Data Preprocessing
2.4. Knowledge Graph
2.5. Application
3. Results
3.1. Preprocessing of the Data to Generate Knowledge Graph
3.2. Creation of the GraphDB with Dynamic Interface
3.3. Application of the GraphDB for Prediction
3.3.1. Querying
3.3.2. Similarity
3.3.3. Classification
3.4. Evaluation of the Prediction Model
4. Discussion
Supplementary Materials
Author Contributions
Funding
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Vaccine Adverse Event Reporting System (VAERS). Available online: https://vaers.hhs.gov/ (accessed on 21 June 2022).
- Statement for Healthcare Professionals: How COVID-19 Vaccines Are Regulated for Safety and Effectiveness (Revised March 2022). Available online: https://www.who.int/news/item/17-05-2022-statement-for-healthcare-professionals-how-covid-19-vaccines-are-regulated-for-safety-and-effectiveness (accessed on 19 July 2022).
- Safety of COVID-19 Vaccines|European Medicines Agency. Available online: https://www.ema.europa.eu/en/human-regulatory/overview/public-health-threats/coronavirus-disease-covid-19/treatments-vaccines/vaccines-covid-19/safety-covid-19-vaccines (accessed on 20 July 2022).
- EMA. AstraZeneca’s COVID-19 Vaccine: EMA Finds Possible Link to Very Rare Cases of Unusual Blood Clots with Low Platelets. Eur. Med. Agency. 6 April 2021. Available online: https://www.ema.europa.eu/en/news/astrazenecas-covid-19-vaccine-ema-finds-possible-link-very-rare-cases-unusual-blood-clots-low-blood (accessed on 20 July 2022).
- Suspected Adverse Reactions to COVID-19 Vaccination and the Safety of Substances of Human Origin. Eur. Cent. Dis. Prev. Control. 3 June 2021. Available online: https://www.ecdc.europa.eu/en/publications-data/suspected-adverse-reactions-covid-19-vaccination-and-safety-substances-human (accessed on 20 July 2022).
- CDC. CDC Works 24/7. In Centers for Disease Control and Prevention; 21 June 2022. Available online: https://www.cdc.gov/index.htm (accessed on 21 June 2022).
- Beatty, A.L.; Peyser, N.D.; Butcher, X.E.; Cocohoba, J.M.; Lin, F.; Olgin, J.E.; Pletcher, M.J.; Marcus, G.M. Analysis of COVID-19 Vaccine Type and Adverse Effects following Vaccination. JAMA Netw. Open 2021, 4, e2140364. [Google Scholar] [CrossRef] [PubMed]
- Barda, N.; Dagan, N.; Ben-Shlomo, Y.; Kepten, E.; Waxman, J.; Ohana, R.; Hernán, M.A.; Lipsitch, M.; Kohane, I.; Netzer, D.; et al. Safety of the BNT162b2 mRNA Covid-19 Vaccine in a Nationwide Setting. N. Engl. J. Med. 2021, 385, 1078–1090. [Google Scholar] [CrossRef] [PubMed]
- Risma, K.A.; Edwards, K.M.; Hummell, D.S.; Little, F.F.; Norton, A.E.; Stallings, A.; Wood, R.A.; Milner, J.D. Potential mechanisms of anaphylaxis to COVID-19 mRNA vaccines. J. Allergy Clin. Immunol. 2021, 147, 2075–2082.e2. [Google Scholar] [CrossRef]
- Kaur, R.J.; Dutta, S.; Bhardwaj, P.; Charan, J.; Dhingra, S.; Mitra, P.; Singh, K.; Yadav, D.; Sharma, P.; Misra, S. Adverse Events Reported from COVID-19 Vaccine Trials: A Systematic Review. Indian J. Clin. Biochem. IJCB 2021, 36, 427–439. [Google Scholar] [CrossRef] [PubMed]
- Menni, C.; Klaser, K.; May, A.; Polidori, L.; Capdevila, J.; Louca, P.; Sudre, C.H.; Nguyen, L.H.; Drew, D.A.; Merino, J.; et al. Vaccine side-effects and SARS-CoV-2 infection after vaccination in users of the COVID Symptom Study app in the UK: A prospective observational study. Lancet Infect. Dis. 2021, 21, 939–949. [Google Scholar] [CrossRef]
- Gonzalez-Dias, P.; Lee, E.K.; Sorgi, S.; De Lima, D.S.; Urbanski, A.H.; Silveira, E.; Nakaya, H.I. Methods for predicting vaccine immunogenicity and reactogenicity. Hum. Vaccines Immunother. 2019, 16, 269–276. [Google Scholar] [CrossRef] [PubMed]
- Adverse Effects of COVID-19 Vaccination: Machine Learning and Statistical Approach to Identify and Classify Incidences of Morbidity and Post-Vaccination Reactogenicity|medRxiv. Available online: https://www.medrxiv.org/content/10.1101/2021.04.16.21255618v1 (accessed on 21 June 2022).
- iOntoBioethics: A Framework for the Agile Development of Bioethics Ontologies in Pandemics, Applied to COVID-19-PMC. Available online: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8175792/ (accessed on 20 July 2022).
- ElDahshan, K.A.; AlHabshy, A.A.; Abutaleb, G.E. Data in the time of COVID-19: A general methodology to select and secure a NoSQL DBMS for medical data. PeerJ Comput. Sci. 2020, 6, e297. [Google Scholar] [CrossRef] [PubMed]
- Neo4j Graph Data Platform–The Leader in Graph Databases. Neo4j Graph Data Platform. Available online: https://neo4j.com/ (accessed on 21 June 2022).
- Saad, E.; Sadiq, S.; Jamil, R.; Rustam, F.; Mehmood, A.; Choi, G.S.; Ashraf, I. Novel extreme regression-voting classifier to predict death risk in vaccinated people using VAERS data. PLoS ONE 2022, 17, e0270327. [Google Scholar] [CrossRef] [PubMed]
- Grover, A.; Leskovec, J. node2vec: Scalable Feature Learning for Networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13 August 2016; pp. 855–864. [Google Scholar] [CrossRef] [Green Version]
- Neumann, M.; King, D.; Beltagy, I.; Ammar, W. ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing. arXiv 2019, arXiv:1902.07669. [Google Scholar]
- Singer, U.; Guy, I.; Radinsky, K. Node Embedding over Temporal Graphs. arXiv 2019, arXiv:1903.08889. [Google Scholar]
- Wang, Y.; Dong, L.; Jiang, X.; Ma, X.; Li, Y.; Zhang, H. KG2Vec: A node2vec-based vectorization model for knowledge graph. PLoS ONE 2021, 16, e0248552. [Google Scholar] [CrossRef] [PubMed]
- Lee, J.Y.; Ang, A.S.Y.; Ali, N.M.; Ang, L.M.; Omar, A. Incidence of adverse reaction of drugs used in COVID-19 management: A retrospective, observational study. J. Pharm. Policy Pract. 2021, 14, 84. [Google Scholar] [CrossRef] [PubMed]
- El-Elimat, T.; AbuAlSamen, M.M.; Almomani, B.A.; Al-Sawalha, N.A.; Alali, F.Q. Acceptance and attitudes toward COVID-19 vaccines: A cross-sectional study from Jordan. PLoS ONE 2021, 16, e0250555. [Google Scholar] [CrossRef] [PubMed]
- Shen, S.C.; Dubey, V. Addressing vaccine hesitancy: Clinical guidance for primary care physicians working with parents. Can. Fam. Physician Med. Fam. Can. 2019, 65, 175–181. [Google Scholar]
Model ID | Model Type | Additional Features |
---|---|---|
1 | Logistic Regression | Symptoms |
2 | XGBoost | Symptoms |
3 | Logistic Regression | Embedding |
4 | XGBoost | Embedding |
5 | XGBoost | Symptoms + Embedding |
VAX_TYPE | Counts |
---|---|
COVID-19 | 12,834 |
VARZOS | 223 |
UNK | 141 |
FLU4 | 84 |
HEPA | 30 |
HEP | 26 |
PPV | 26 |
FLUX | 24 |
DTAPIPV | 24 |
TDAP | 23 |
VAX_NAME | Counts |
---|---|
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | 5855 |
COVID-19 (COVID-19 (MODERNA)) | 5795 |
COVID-19 (COVID-19 (JANSSEN)) | 1164 |
ZOSTER (SHINGRIX) | 165 |
VACCINE NOT SPECIFIED (NO BRAND NAME) | 132 |
ZOSTER (NO BRAND NAME) | 46 |
INFLUENZA (SEASONAL) (NO BRAND NAME) | 24 |
INFLUENZA (SEASONAL) (FLUZONE HIGH-DOSE QUADRIVALENT) | 24 |
INFLUENZA (SEASONAL) (FLUARIX QUADRIVALENT) | 22 |
COVID-19 (COVID-19 (UNKNOWN)) | 20 |
VAX_MANUE | Counts |
---|---|
PFIZER\BIONTECH | 5855 |
MODERNA | 5795 |
JANSSEN | 1164 |
GLAXOSMITHKLINE BIOLOGICALS | 281 |
UNKNOWN MANUFACTURER | 247 |
MERCK & CO. INC. | 146 |
SANOFI PASTEUR | 93 |
SEQIRUS, INC. | 30 |
NOVARTIS VACCINES AND DIAGNOSTICS | 23 |
PFIZER\WYETH | 19 |
Symptom | Counts |
---|---|
Headache | 1596 |
Pyrexia | 1410 |
Fatigue | 1332 |
Pain | 1229 |
Chills | 1128 |
Pain in extremity | 913 |
Nausea | 895 |
Dizziness | 867 |
Arthralgia | 605 |
COVID-19 | 604 |
Drug | Counts |
---|---|
(C0014695, Ergocalciferol) | 374 |
(C0040165, Levothyroxine) | 302 |
(C0004057, Aspirin) | 290 |
(C0286651, atorvastatin) | 282 |
(C0065374, Lisinopril) | 269 |
(C0008318, Cholecalciferol) | 268 |
(C0003968, Ascorbic Acid) | 227 |
(C0025598, metFORMIN) | 203 |
(C0025859, Metoprolol) | 197 |
(C0028978, Omeprazole) | 192 |
Condition | Counts |
---|---|
(C0020538, Hypertensive disease) | 910 |
(C5203670, COVID-19) | 638 |
(C0004096, Asthma) | 417 |
(C0041834, Erythema) | 281 |
(C0020676, Hypothyroidism) | 249 |
(C0042109, Urticaria) | 233 |
(C0149931, Migraine Disorders) | 226 |
(C0017168, Gastroesophageal reflux disease) | 200 |
(C0011847, Diabetes) | 194 |
(C0242350, Erectile dysfunction) | 191 |
Allergy | Counts |
---|---|
(C0030842, penicillin) | 442 |
(C0749139, sulfa) | 324 |
(C1705924, TAC1 wt Allele) | 155 |
(C0009214, codeine) | 148 |
(C0023115, latex) | 131 |
(C0002645, amoxicillin) | 114 |
(C0013227, Pharmaceutical Preparations) | 112 |
(C0020517, Hypersensitivity) | 111 |
(C0014806, erythromycin) | 74 |
(C0026549, morphine) | 66 |
Allergy | Symptom | Count |
---|---|---|
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Headache | 706 |
COVID-19 (COVID-19 (MODERNA)) | Pyrexia | 663 |
COVID-19 (COVID-19 (MODERNA)) | Headache | 660 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Fatigue | 626 |
COVID-19 (COVID-19 (MODERNA)) | Fatigue | 586 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Pyrexia | 566 |
COVID-19 (COVID-19 (MODERNA)) | Chills | 565 |
COVID-19 (COVID-19 (MODERNA)) | Pain | 554 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Pain | 531 |
COVID-19 (COVID-19 (MODERNA)) | Pain in extremity | 459 |
Allergy | Use_Drug | Count |
---|---|---|
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Ergocalciferol | 169 |
COVID-19 (COVID-19 (MODERNA)) | Ergocalciferol | 165 |
COVID-19 (COVID-19 (MODERNA)) | levothyroxine | 145 |
COVID-19 (COVID-19 (MODERNA)) | atorvastatin | 139 |
COVID-19 (COVID-19 (MODERNA)) | Cholecalciferol | 132 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | levothyroxine | 127 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Cholecalciferol | 114 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | atorvastatin | 109 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Ascorbic Acid | 106 |
COVID-19 (COVID-19 (MODERNA)) | Omeprazole | 106 |
Allergy | Had_Condition | Count |
---|---|---|
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Hypertensive disease | 408 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | COVID-19 | 407 |
COVID-19 (COVID-19 (MODERNA)) | Hypertensive disease | 394 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Asthma | 219 |
COVID-19 (COVID-19 (MODERNA)) | COVID-19 | 189 |
COVID-19 (COVID-19 (MODERNA)) | Erythema | 176 |
COVID-19 (COVID-19 (MODERNA)) | Asthma | 158 |
COVID-19 (COVID-19 (MODERNA)) | Urticaria | 122 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Hypothyroidism | 115 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Erectile dysfunction | 110 |
Allergy | Allergic_to | Count |
---|---|---|
COVID-19 (COVID-19 (MODERNA)) | penicillins | 706 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | penicillins | 663 |
COVID-19 (COVID-19 (MODERNA)) | sulfa | 660 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | sulfa | 626 |
COVID-19 (COVID-19 (MODERNA)) | codeine | 586 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | TAC1 wt Allele | 566 |
COVID-19 (COVID-19 (MODERNA)) | latex | 565 |
COVID-19 (COVID-19 (MODERNA)) | TAC1 wt Allele | 554 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Pharmaceutical Preparations | 531 |
COVID-19 (COVID-19 (MODERNA)) | amoxicillin | 459 |
Allergy | Symptom | Similarity |
---|---|---|
COVID-19 (COVID-19 (JANSSEN)) | Tinnitus | 0.267765 |
COVID-19 (COVID-19 (JANSSEN)) | Skin lesion | 0.258912 |
COVID-19 (COVID-19 (JANSSEN)) | Thrombosis | 0.253751 |
COVID-19 (COVID-19 (MODERNA)) | Aspartate aminotransferase normal | 0.243350 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Diarrhea hemorrhagic | 0.263173 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Interchange of vaccine products | 0.246813 |
COVID-19 (COVID-19 (UNKNOWN)) | Thrombophlebitis septic | 0.275156 |
COVID-19 (COVID-19 (UNKNOWN)) | Imaging procedure | 0.259467 |
Vaccine | Allergic_to | Similarity |
---|---|---|
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Pinus <genus> | 0.230201 |
COVID-19 (COVID-19 (MODERNA)) | Vibramycin | 0.235300 |
vaccine | had_condition | similarity |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Pressure Ulcer | 0.236387 |
vaccine | use_drug | similarity |
COVID-19 (COVID-19 (JANSSEN)) | cefalexin | 0.254526 |
COVID-19 (COVID-19 (JANSSEN)) | feverfew extract | 0.267852 |
COVID-19 (COVID-19 (PFIZER-BIONTECH)) | Diclofenac | 0.252584 |
COVID-19 (COVID-19 (MODERNA)) | Vibramycin | 0.235300 |
COVID-19 (COVID-19 (MODERNA)) | Propranolol Hydrochloride | 0.253414 |
COVID-19 (COVID-19 (MODERNA)) | Combigan | 0.311181 |
COVID-19 (COVID-19 (UNKNOWN)) | Oral Tablet | 0.253658 |
COVID-19 (COVID-19 (UNKNOWN)) | Claritin-D | 0.253505 |
Model ID | Model Type | Additional Features | Positive F1-Score | Precision-Recall AUC |
---|---|---|---|---|
1 | Logistic regression | Symptoms | train: 0.88 test: 0.63 | train: 0.96 test: 0.65 |
2 | XGBoost | Symptoms | train: 0.90 test: 0.67 | train: 0.97 test: 0.69 |
3 | Logistic regression | Embedding | train: 0.36 test: 0.25 | train: 0.33 test: 0.23 |
4 | XGBoost | Embedding | train: 0.58 test: 0.31 | train: 0.91 test: 0.24 |
5 | XGBoost | Symptoms + Embedding | train: 0.90 test: 0.67 | train: 0.97 test: 0.69 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, Z.; Gao, X.; Li, C. Modeling COVID-19 Vaccine Adverse Effects with a Visualized Knowledge Graph Database. Healthcare 2022, 10, 1419. https://doi.org/10.3390/healthcare10081419
Liu Z, Gao X, Li C. Modeling COVID-19 Vaccine Adverse Effects with a Visualized Knowledge Graph Database. Healthcare. 2022; 10(8):1419. https://doi.org/10.3390/healthcare10081419
Chicago/Turabian StyleLiu, Zhiyuan, Ximing Gao, and Chenyu Li. 2022. "Modeling COVID-19 Vaccine Adverse Effects with a Visualized Knowledge Graph Database" Healthcare 10, no. 8: 1419. https://doi.org/10.3390/healthcare10081419