PMID- 32554376
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20200928
IS  - 2291-9694 (Print)
IS  - 2291-9694 (Electronic)
VI  - 8
IP  - 6
DP  - 2020 Jun 17
TI  - Summarizing Complex Graphical Models of Multiple Chronic Conditions Using the 
      Second Eigenvalue of Graph Laplacian: Algorithm Development and Validation.
PG  - e16372
LID - 10.2196/16372 [doi]
LID - e16372
AB  - BACKGROUND: It is important but challenging to understand the interactions of 
      multiple chronic conditions (MCC) and how they develop over time in patients and 
      populations. Clinical data on MCC can now be represented using graphical models 
      to study their interaction and identify the path toward the development of MCC. 
      However, the current graphical models representing MCC are often complex and 
      difficult to analyze. Therefore, it is necessary to develop improved methods for 
      generating these models. OBJECTIVE: This study aimed to summarize the complex 
      graphical models of MCC interactions to improve comprehension and aid analysis. 
      METHODS: We examined the emergence of 5 chronic medical conditions (ie, traumatic 
      brain injury [TBI], posttraumatic stress disorder [PTSD], depression [Depr], 
      substance abuse [SuAb], and back pain [BaPa]) over 5 years among 257,633 veteran 
      patients. We developed 3 algorithms that utilize the second eigenvalue of the 
      graph Laplacian to summarize the complex graphical models of MCC by removing less 
      significant edges. The first algorithm learns a sparse probabilistic graphical 
      model of MCC interactions directly from the data. The second algorithm summarizes 
      an existing probabilistic graphical model of MCC interactions when a supporting 
      data set is available. The third algorithm, which is a variation of the second 
      algorithm, summarizes the existing graphical model of MCC interactions with no 
      supporting data. Finally, we examined the coappearance of the 100 most common 
      terms in the literature of MCC to validate the performance of the proposed model. 
      RESULTS: The proposed summarization algorithms demonstrate considerable 
      performance in extracting major connections among MCC without reducing the 
      predictive accuracy of the resulting graphical models. For the model learned 
      directly from the data, the area under the curve (AUC) performance for predicting 
      TBI, PTSD, BaPa, SuAb, and Depr, respectively, during the next 4 years is as 
      follows-year 2: 79.91%, 84.04%, 78.83%, 82.50%, and 81.47%; year 3: 76.23%, 
      80.61%, 73.51%, 79.84%, and 77.13%; year 4: 72.38%, 78.22%, 72.96%, 77.92%, and 
      72.65%; and year 5: 69.51%, 76.15%, 73.04%, 76.72%, and 69.99%, respectively. 
      This demonstrates an overall 12.07% increase in the cumulative sum of AUC in 
      comparison with the classic multilevel temporal Bayesian network. CONCLUSIONS: 
      Using graph summarization can improve the interpretability and the predictive 
      power of the complex graphical models of MCC.
CI  - (c)Syed Hasib Akhter Faruqui, Adel Alaeddini, Mike C Chang, Sara Shirinkam, Carlos 
      Jaramillo, Peyman NajafiRad, Jing Wang, Mary Jo Pugh. Originally published in 
      JMIR Medical Informatics (http://medinform.jmir.org), 17.06.2020.
FAU - Faruqui, Syed Hasib Akhter
AU  - Faruqui SHA
AUID- ORCID: 0000-0002-5073-8690
AD  - Department of Mechanical Engineering, The University of Texas at San Antonio, San 
      Antonio, TX, United States.
FAU - Alaeddini, Adel
AU  - Alaeddini A
AUID- ORCID: 0000-0003-4451-3150
AD  - Department of Mechanical Engineering, The University of Texas at San Antonio, San 
      Antonio, TX, United States.
FAU - Chang, Mike C
AU  - Chang MC
AUID- ORCID: 0000-0003-0070-9119
AD  - Department of Mechanical Engineering, The University of Texas at San Antonio, San 
      Antonio, TX, United States.
FAU - Shirinkam, Sara
AU  - Shirinkam S
AUID- ORCID: 0000-0002-8153-4754
AD  - Department of Mathematics and Statistics, University of the Incarnate Word, San 
      Antonio, TX, United States.
FAU - Jaramillo, Carlos
AU  - Jaramillo C
AUID- ORCID: 0000-0002-2424-6326
AD  - South Texas Veterans Health Care System, San Antonio, TX, United States.
FAU - NajafiRad, Peyman
AU  - NajafiRad P
AUID- ORCID: 0000-0001-9671-577X
AD  - Department of Information Systems and Cyber Security, The University of Texas at 
      San Antonio, San Antonio, TX, United States.
FAU - Wang, Jing
AU  - Wang J
AUID- ORCID: 0000-0002-4012-0977
AD  - School of Nursing, UT Health San Antonio, San Antonio, TX, United States.
FAU - Pugh, Mary Jo
AU  - Pugh MJ
AUID- ORCID: 0000-0003-4196-7763
AD  - VA Salt Lake City Health Care System, Salt Lake City, UT, United States.
LA  - eng
GR  - I01 HX000329/HX/HSRD VA/United States
GR  - SC2 GM118266/GM/NIGMS NIH HHS/United States
PT  - Journal Article
DEP - 20200617
PL  - Canada
TA  - JMIR Med Inform
JT  - JMIR medical informatics
JID - 101645109
PMC - PMC7330739
OTO - NOTNLM
OT  - disease network
OT  - graph Laplacian
OT  - graph summarization
OT  - graphical models
OT  - multiple chronic conditions
COIS- Conflicts of Interest: None declared.
EDAT- 2020/06/20 06:00
MHDA- 2020/06/20 06:01
PMCR- 2020/06/17
CRDT- 2020/06/20 06:00
PHST- 2019/09/24 00:00 [received]
PHST- 2020/03/22 00:00 [accepted]
PHST- 2020/01/06 00:00 [revised]
PHST- 2020/06/20 06:00 [entrez]
PHST- 2020/06/20 06:00 [pubmed]
PHST- 2020/06/20 06:01 [medline]
PHST- 2020/06/17 00:00 [pmc-release]
AID - v8i6e16372 [pii]
AID - 10.2196/16372 [doi]
PST - epublish
SO  - JMIR Med Inform. 2020 Jun 17;8(6):e16372. doi: 10.2196/16372.