Jove
Visualize
Contact Us

Related Concept Videos

Issues And Trends In Healthcare Delivery System01:29

Issues And Trends In Healthcare Delivery System

5.7K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
5.7K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Knowledge, Attitudes and Practices of Physicians Regarding Antifungal Therapy in Tertiary Care Patients: A Cross-Sectional Survey in Greece.

Pathogens (Basel, Switzerland)·2026
Same author

Clinical, Laboratory, and Therapeutic Characteristics of Visceral Leishmaniasis with Emphasis on Immune Status: A Multicentre Cohort Study in Greece.

Pathogens (Basel, Switzerland)·2026
Same author

Global and regional prevalence of metallo-β-lactamases in carbapenem-resistant Acinetobacter baumannii: a systematic review and meta-analysis.

The Journal of antimicrobial chemotherapy·2026
Same author

The Effect of Mild Exercise in the Chemotherapy Room on the Anxiety Level of Cancer Patients: A Prospective Observational Paired Cohort Study.

Journal of clinical medicine·2025
Same author

Network meta-analysis of cardioplegic methods, in elective isolated coronary artery bypass grafting.

Perfusion·2025
Same author

Multicentre prospective study on the diagnostic and prognostic validity of malnutrition assessment tools in surgery.

The British journal of surgery·2025
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 25, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.1K

Artificial Intelligence in Surgical Risk Prediction.

Stamatios Kokkinakis1, Evangelos I Kritsotakis2, Konstantinos Lasithiotakis1

  • 1Department of General Surgery, School of Medicine, University Hospital of Heraklion, University of Crete, 71500 Heraklion, Greece.

Journal of Clinical Medicine
|June 28, 2023
PubMed
Summary

This review examines how machine learning tools are being integrated into surgical settings to better predict patient recovery and potential complications before and after operations. By analyzing large datasets, these models aim to provide doctors with more accurate assessments of individual patient risks, ultimately helping to personalize care plans and improve surgical safety.

Keywords:
predictive analyticsmachine learningclinical decision supportpostoperative care

Frequently Asked Questions

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:08

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

106

Related Experiment Videos

Last Updated: Jul 25, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.1K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:08

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

106

Area of Science:

  • Surgical outcomes research within Artificial Intelligence in healthcare
  • Clinical informatics and predictive analytics

Background:

Current clinical workflows often lack precise methods for anticipating individual patient complications after invasive procedures. While traditional scoring systems exist, they frequently fail to capture the complex interplay of patient-specific variables. No prior work had resolved the limitations inherent in these static, manual assessment tools. That uncertainty drove interest in automated computational approaches. Prior research has shown that machine learning models can identify patterns within massive health records. This gap motivated the development of advanced predictive algorithms. These systems promise to transform how surgeons evaluate potential threats to patient health. The field now seeks to integrate these digital solutions into routine hospital environments.

Purpose Of The Study:

The aim of this study is to evaluate the current landscape of machine learning applications in surgical risk stratification. This research addresses the challenge of improving patient safety through advanced predictive analytics. The authors seek to clarify how digital tools can assist surgeons in anticipating postoperative complications. This gap motivated a thorough examination of existing algorithmic frameworks. The study investigates the transition from traditional scoring systems to automated computational models. It explores the potential for these technologies to personalize surgical care pathways. The researchers intend to provide a clear summary of the strengths and limitations of current predictive methods. This work serves to guide future efforts in implementing digital solutions within clinical practice.

Main Methods:

This review approach synthesizes findings from recent literature regarding computational modeling in surgery. The authors evaluated studies that utilized various supervised learning architectures. They examined how researchers curated datasets from large-scale hospital databases. The investigation focused on the performance metrics reported across diverse clinical trials. The team assessed the methodologies used to validate these predictive systems. They scrutinized the inclusion criteria for patient cohorts within the selected papers. The review process involved comparing algorithmic predictions against established clinical benchmarks. This systematic strategy ensured a comprehensive overview of current technological capabilities.

Main Results:

Key findings from the literature indicate that machine learning models frequently achieve higher predictive accuracy than conventional risk scores. Several studies reported area under the curve values exceeding 0.80 for specific postoperative complications. The data suggest that these algorithms effectively capture non-linear relationships between patient comorbidities and surgical outcomes. Results show that models incorporating preoperative laboratory values perform better than those using only demographic information. The literature reveals that deep learning approaches often surpass traditional regression techniques in complex scenarios. Findings indicate that model performance remains consistent across various surgical specialties. The evidence highlights that integrating real-time data significantly improves the precision of short-term outcome predictions. The synthesis confirms that these tools successfully identify patients at high risk for readmission or prolonged hospital stays.

Conclusions:

The authors suggest that machine learning models offer improved accuracy over conventional risk stratification methods. These tools demonstrate potential for enhancing clinical decision-making processes. Synthesis and implications indicate that data quality remains a primary factor for model reliability. Researchers propose that future implementation requires rigorous validation across diverse patient populations. The review highlights that algorithmic transparency is necessary for widespread adoption by surgical teams. Evidence suggests that automated systems may reduce subjective bias in preoperative assessments. The authors emphasize that these technologies serve as supportive instruments rather than replacements for clinical judgment. Continued evaluation of long-term patient outcomes will clarify the true utility of these predictive platforms.

The researchers propose that these systems utilize pattern recognition within electronic health records to identify high-risk patients. By processing thousands of variables simultaneously, these models outperform traditional manual scoring systems that rely on limited clinical criteria.

The authors highlight the integration of electronic health records as a primary data source. These digital repositories provide the longitudinal information needed to train algorithms for predicting both immediate and delayed recovery complications.

The authors state that high-quality, structured data is necessary for reliable performance. Without consistent input from diverse patient demographics, the models may exhibit bias or fail to generalize across different hospital settings.

These models function as decision-support tools that process vast amounts of patient data. They act as a bridge between complex medical histories and actionable insights for surgeons during the planning phase.

The researchers measure performance through metrics like area under the receiver operating characteristic curve. This phenomenon quantifies how well the algorithm distinguishes between patients who experience complications and those who recover without issues.

The authors propose that these systems will eventually enable personalized surgical care. By tailoring interventions to individual risk profiles, clinicians may reduce the incidence of adverse events and improve overall recovery trajectories.