Skip to content
DraconiticResearch
Search Sources API
201,818 studies31 sourcesUpdated 24 min ago
Peer-reviewedCC BY-NC-ND 4.0BMC Medical Informatics and Decision Making

Comparative machine learning approaches to prognosticate clinical outcomes in oral and maxillofacial space infections: a retrospective analysis

  • Shiyuan Liu1,2
  • Heli Shen3
  • Ruipu Zhang4
  • Songpo He5
  • Huaqiang Wang6
  • Bingxin Xu7
  • Xiaoge Zhang8
  • Xianjun Zhang1,2
  • Wei Li1,2
8 affiliations
  1. 1Department of Oral and Maxillofacial Surgery, Xuchang Central Hospital, Henan, China
  2. 2Oral Medicine Center, Xuchang Central Hospital, Henan, China
  3. 3Publicity Department, Xuchang University, Henan, China
  4. 4Department of Oral and Maxillofacial Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan China
  5. 5Department of Otorhinolaryngology, Xuchang Central Hospital, Henan, China
  6. 6Department of Intensivecare Unit, Xuchang Central Hospital, Henan, China
  7. 7Research Center for Clinical Medical Sciences, Xuchang Central Hospital, Henan, China
  8. 8Nursing Department, Xuchang Central Hospital, Henan, China
Read full textDOICite

Abstract

Background: The objective of this study was to evaluate the performance of multiple machine learning algorithms to provide evidence supporting early intervention for high-risk patients with oral and maxillofacial space infections (OMSI), thereby reducing complication rates and improving overall clinical outcomes.

Methods: A retrospective cohort study was performed to analyse clinical data from 432 medical records, with a focus on key variables related to disease severity and treatment outcomes. The data included age, gender, height, weight, BMI, blood test results, such as the CRP, white blood cell count, neutrophil count, lymphocyte count, monocyte count, albumin, potassium, sodium, chlorine, calcium, uric acid, blood urea nitrogen, PCT, fibrinogen, blood glucose, vital signs, such as body temperature, heart rate, systolic blood pressure, diastolic blood pressure, respiration, days before hospitalization, the extent of mouth opening, the space of infected spaces, and the source of infection.

Results: We summarized the predictive performance of three models—Logistic regression, Random Forest, and XGBoost—across three key clinical outcomes. For predicting hospital stay duration, Logistic regression performed best. For predicting ICU admission, XGBoost exhibited the strongest performance. For predicting surgical intervention, Logistic regression achieved the optimal overall performance, while XGBoost and Random Forest demonstrated the highest specificity.

Conclusions: In summary, we have successfully developed, validated, and compared predictive models for key clinical outcomes in patients with OMSI. They further hold promise for ultimately optimizing the diagnostic and therapeutic workflow and improving outcomes for patients with this common yet potentially life-threatening condition.

Clinical trial number: Not applicable.

Trial registration: Not applicable.

Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12911-026-03668-x.

Related

  1. Comparative Effectiveness and Hematological Safety of Linezolid and Tedizolid in Bone and Joint Infections: A Retrospective Cohort Study
    Charlène Aïn, Paul Laffont-Lozes, Albert Sotto +6
    Infectious Diseases and TherapyPeer-reviewedCC BY-NC 4.0Full textSurgery & anaesthesiaHAL
  2. Comparative evaluation of metagenomic and targeted next-generation sequencing for pathogen detection in bronchoalveolar lavage fluid from patients with lower respiratory tract infections: a retrospective cohort study.
    Rui Zhao, Heya Na, Wei Miao +5
    Frontiers in cellular and infection microbiologyPeer-reviewedCC BYFull textGeneral medicineEurope PMCPMC
  3. Comparative Analysis of Manual and Deep LIIF Extended Global Scoring Method for Ki-67 Across a Spectrum of Oral and Maxillofacial Pathologies: An Exploratory Study
    P. C. Rasla, Dhinakaran Paranchodi, Akshay Trimukhe +12
    Head and Neck PathologyPeer-reviewedLicence not statedFull textGeneral medicinePMC
  4. Clinical Factors Influencing Cosmetic Lip Reduction Recommendations: A Comparative Study of Orthodontists and Oral and Maxillofacial Surgeons
    Varun Nambiar, Dhanalakshmi Varun, Rahul VC Tiwari
    CureusPeer-reviewedCC BY 4.0Full textGeneral medicinePMC
  5. Efficacy and safety of portable ultrasound-guided pingyangmycin sclerotherapy for deep-seated oral and maxillofacial venous malformations: a retrospective observational study.
    Qizhang Wang, Xiye Sun, Chengzhi Zhao +3
    Frontiers in neurologyPeer-reviewedCC BYFull textSurgery & anaesthesiaEurope PMCCrossref

Cite

BibTeXRIS
BibTeX
@article{liu2026comparative,
  title = {{Comparative machine learning approaches to prognosticate clinical outcomes in oral and maxillofacial space infections: a retrospective analysis}},
  author = {Shiyuan Liu and Heli Shen and Ruipu Zhang and Songpo He and Huaqiang Wang and Bingxin Xu and Xiaoge Zhang and Xianjun Zhang and Wei Li},
  journal = {BMC Medical Informatics and Decision Making},
  year = {2026},
  month = jun,
  doi = {10.1186/s12911-026-03668-x},
  url = {https://doi.org/10.1186/s12911-026-03668-x},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - Comparative machine learning approaches to prognosticate clinical outcomes in oral and maxillofacial space infections: a retrospective analysis
AU  - Shiyuan Liu
AU  - Heli Shen
AU  - Ruipu Zhang
AU  - Songpo He
AU  - Huaqiang Wang
AU  - Bingxin Xu
AU  - Xiaoge Zhang
AU  - Xianjun Zhang
AU  - Wei Li
PY  - 2026
DA  - 2026/06/30
JO  - BMC Medical Informatics and Decision Making
DO  - 10.1186/s12911-026-03668-x
UR  - https://doi.org/10.1186/s12911-026-03668-x
AB  - Background: The objective of this study was to evaluate the performance of multiple machine learning algorithms to provide evidence supporting early intervention for high-risk patients with oral and maxillofacial space infections (OMSI), thereby reducing complication rates and improving overall clinical outcomes.  Methods: A retrospective cohort study was performed to analyse clinical data from 432 medical records, with a focus on key variables related to disease severity and treatment outcomes. The data included age, gender, height, weight, BMI, blood test results, such as the CRP, white blood cell count, neutrophil count, lymphocyte count, monocyte count, albumin, potassium, sodium, chlorine, calcium, uric acid, blood urea nitrogen, PCT, fibrinogen, blood glucose, vital signs, such as body temperature, heart rate, systolic blood pressure, diastolic blood pressure, respiration, days before hospitalization, the extent of mouth opening, the space of infected spaces, and the source of infection.  Results: We summarized the predictive performance of three models—Logistic regression, Random Forest, and XGBoost—across three key clinical outcomes. For predicting hospital stay duration, Logistic regression performed best. For predicting ICU admission, XGBoost exhibited the strongest performance. For predicting surgical intervention, Logistic regression achieved the optimal overall performance, while XGBoost and Random Forest demonstrated the highest specificity.  Conclusions: In summary, we have successfully developed, validated, and compared predictive models for key clinical outcomes in patients with OMSI. They further hold promise for ultimately optimizing the diagnostic and therapeutic workflow and improving outcomes for patients with this common yet potentially life-threatening condition.  Clinical trial number: Not applicable.  Trial registration: Not applicable.  Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12911-026-03668-x.
SN  - 1472-6947
ER  -