Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 15 min ago
Peer-reviewedCC BYDiagnostics (Basel, Switzerland)

Diagnostic Accuracy of Machine Learning-Enhanced Methods for Pulmonary Hypertension: A Systematic Review and Meta-Analysis.

  • Faizan Ahmed1
  • Ayesha Zulfiqar2
  • Tushar Kanti Bhadra3
  • Noor Ul Sabah4
  • Taha Alam5
  • Unaiza Iftikhar6
  • Ahmad Zulaid4
  • Hassan Farooq5
  • Qais Bin Abdul Ghaffar7
  • Muhammad Faizan Tahir8
  • Muhammad Haris4
  • Omar Kamel9
6 more authors
  • Haris Bin Tahir10
  • Gabriel Benjamen11
  • Ali Abbas Khaleel12
  • Ali Ghani13
  • Amro Taha14
  • Fawaz Alenezi15
15 affiliations
  1. 1Department of Internal Medicine, Jersey Shore University Medical Center, Neptune, NJ 07753, USA.
  2. 2Dow Medical College, Dow University of Health Sciences, Karachi 74200, Pakistan.
  3. 3National Institute of Cardiovascular Diseases, Dhaka 1207, Bangladesh.
  4. 4Quaid-E-Azam Medical College, University of Health Sciences, Bahawalpur 63100, Pakistan.
  5. 5Ameer-Ud-Din Medical College, University of Health Sciences (UHS), Lahore 54000, Pakistan.
  6. 6Foundation University Medical College, Foundation University Islamabad, Islamabad 44000, Pakistan.
  7. 7Department of Internal Medicine, Camden Clark Medical Center, WVU Medicine, Parkersburg, WV 26101, USA.
  8. 8Shalamar Medical and Dental College, University of Health Sciences, Lahore 54840, Pakistan.
  9. 9Department of Physical Therapy, Qena University, Qena 83523, Egypt.
  10. 10Department of Internal Medicine, Lahore General Hospital, Lahore 54000, Pakistan.
  11. 11School of Medicine, St. George's University, St. George's P.O. Box 7, Grenada.
  12. 12College of Medicine, Al-Mustansiriyah University, Baghdad 14022, Iraq.
  13. 13Department of Cardiology, University of Arizona, Tucson, AZ 85724, USA.
  14. 14Division of Cardiology, West Virginia University, Morgantown, WV 26506, USA.
  15. 15Division of Cardiology, Department of Medicine, Duke University School of Medicine, Durham, NC 27710, USA.
Read full textPDFDOICite

Abstract

Background/Objectives: Right heart catheterization (RHC) is the diagnostic gold standard for pulmonary hypertension (PH), defined as mean pulmonary arterial pressure (mPAP) greater than 20 mmHg at rest. It is invasive and carries procedural risk. Machine learning (ML) and deep learning (DL) applied to non-invasive modalities may provide a non-invasive adjunct for screening, triage, and earlier identification. Methods: Methodological quality was assessed using QUADAS-2. Primary non-comparative pooling was restricted to RHC-confirmed studies using Reitsma hierarchical bivariate random-effects models. Comparative studies were analyzed using a paired hierarchical bivariate model, with between-method differences assessed using paired Wald tests. Sensitivity, specificity, likelihood ratios, and diagnostic odds ratios were estimated; predictive values were evaluated as secondary outcomes. GRADE certainty was assessed separately for non-comparative ML/DL, comparative ML/DL, and traditional methods. Results: Nine studies involving multiple pulmonary hypertension subtypes met the inclusion criteria: five non-comparative (single-arm) studies including approximately 26,530 participants and four comparative (double-arm) studies including 330 paired participants per arm. In the primary synthesis restricted to RHC-confirmed single-arm studies, ML/DL models achieved a pooled sensitivity of 0.720 (95% CI: 0.647-0.783) and specificity of 0.883 (95% CI: 0.796-0.936), with a diagnostic odds ratio of 19.4 (95% CI: 13.6-27.7). Estimates were similar when all five single-arm studies were included (sensitivity 0.716, 95% CI: 0.654-0.771; specificity 0.891, 95% CI: 0.820-0.937). In comparative studies analyzed with a paired hierarchical bivariate model, ML/DL outperformed traditional methods for both sensitivity (0.838, 95% CI: 0.668-0.930 versus 0.707, 95% CI: 0.421-0.889; paired Wald p = 0.019) and specificity (0.849, 95% CI: 0.512-0.968 versus 0.640, 95% CI: 0.376-0.840; paired Wald p = 0.0076). At a 25% pre-test probability, ML/DL was projected to yield 34 additional true positives (95% CI: -30 to 109) and 142 fewer false positives (95% CI: -381 to 129) per 1000 patients tested, although all absolute difference intervals crossed zero. Certainty of evidence was very low across all outcomes. GRADE certainty ranged from low to very low depending on outcome and stratum. Conclusions: ML/DL-based methods showed promising non-invasive diagnostic accuracy for PH, with significantly higher pooled sensitivity and specificity than traditional methods in paired comparisons. However, evidence certainty ranged from low to very low, and projected absolute benefits remained imprecise. These findings are hypothesis-generating; ML/DL tools may serve as adjuncts in the diagnostic pathway but cannot replace RHC at this stage.

Related

  1. Diagnostic accuracy of deep learning for microsatellite instability prediction in gastric cancer: A systematic review and meta-analysis
    Y. Du, H. Liao, J. Li +2
    medRxivPreprintCC BYFull textOncologymedRxiv
  2. Natriuretic Peptide Receptor-C (NPR3) in Pulmonary Hypertension Associated with Chronic Lung Disease: A PRISMA-ScR Scoping Review of Diagnostic, Prognostic, Mechanistic, and Therapeutic Evidence
    Emmanuel Eroume A Egom, Adamou Mfopa, Njimona Ibrahim +4
    Journal of clinical medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  3. Treatment Strategies for Achieving and Maintaining Low-Risk Status in Pulmonary Arterial Hypertension: A Systematic Review
    Shahbaz Younas Chaoddhary, Sai Ram Kumar Yatiraju, Aishwarya Chellamani +6
    CureusPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  4. Prevalence and factors associated with pulmonary hypertension in patients undergoing maintenance hemodialysis: a systematic review and meta-analysis
    Hong-wei Yang, Juan Wang, Hui Ji +6
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  5. Diagnostic accuracy of the appendicitis inflammatory response (AIR) score for acute appendicitis during pregnancy: A systematic review and diagnostic meta-analysis
    Yasaman Tavakoli, Behdad Ghanami, Azad Alimohammadi +1
    Surgery in practice and sciencePeer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{ahmed2026diagnostic,
  title = {{Diagnostic Accuracy of Machine Learning-Enhanced Methods for Pulmonary Hypertension: A Systematic Review and Meta-Analysis.}},
  author = {Faizan Ahmed and Ayesha Zulfiqar and Tushar Kanti Bhadra and Noor Ul Sabah and Taha Alam and Unaiza Iftikhar and Ahmad Zulaid and Hassan Farooq and Qais Bin Abdul Ghaffar and Muhammad Faizan Tahir and Muhammad Haris and Omar Kamel and Haris Bin Tahir and Gabriel Benjamen and Ali Abbas Khaleel and Ali Ghani and Amro Taha and Fawaz Alenezi},
  journal = {Diagnostics (Basel, Switzerland)},
  year = {2026},
  month = sep,
  doi = {10.3390/diagnostics16193106},
  url = {https://europepmc.org/article/MED/42882261},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Diagnostic Accuracy of Machine Learning-Enhanced Methods for Pulmonary Hypertension: A Systematic Review and Meta-Analysis.
AU  - Faizan Ahmed
AU  - Ayesha Zulfiqar
AU  - Tushar Kanti Bhadra
AU  - Noor Ul Sabah
AU  - Taha Alam
AU  - Unaiza Iftikhar
AU  - Ahmad Zulaid
AU  - Hassan Farooq
AU  - Qais Bin Abdul Ghaffar
AU  - Muhammad Faizan Tahir
AU  - Muhammad Haris
AU  - Omar Kamel
AU  - Haris Bin Tahir
AU  - Gabriel Benjamen
AU  - Ali Abbas Khaleel
AU  - Ali Ghani
AU  - Amro Taha
AU  - Fawaz Alenezi
PY  - 2026
DA  - 2026/09/24
JO  - Diagnostics (Basel, Switzerland)
DO  - 10.3390/diagnostics16193106
UR  - https://europepmc.org/article/MED/42882261
AB  - Background/Objectives: Right heart catheterization (RHC) is the diagnostic gold standard for pulmonary hypertension (PH), defined as mean pulmonary arterial pressure (mPAP) greater than 20 mmHg at rest. It is invasive and carries procedural risk. Machine learning (ML) and deep learning (DL) applied to non-invasive modalities may provide a non-invasive adjunct for screening, triage, and earlier identification. Methods: Methodological quality was assessed using QUADAS-2. Primary non-comparative pooling was restricted to RHC-confirmed studies using Reitsma hierarchical bivariate random-effects models. Comparative studies were analyzed using a paired hierarchical bivariate model, with between-method differences assessed using paired Wald tests. Sensitivity, specificity, likelihood ratios, and diagnostic odds ratios were estimated; predictive values were evaluated as secondary outcomes. GRADE certainty was assessed separately for non-comparative ML/DL, comparative ML/DL, and traditional methods. Results: Nine studies involving multiple pulmonary hypertension subtypes met the inclusion criteria: five non-comparative (single-arm) studies including approximately 26,530 participants and four comparative (double-arm) studies including 330 paired participants per arm. In the primary synthesis restricted to RHC-confirmed single-arm studies, ML/DL models achieved a pooled sensitivity of 0.720 (95% CI: 0.647-0.783) and specificity of 0.883 (95% CI: 0.796-0.936), with a diagnostic odds ratio of 19.4 (95% CI: 13.6-27.7). Estimates were similar when all five single-arm studies were included (sensitivity 0.716, 95% CI: 0.654-0.771; specificity 0.891, 95% CI: 0.820-0.937). In comparative studies analyzed with a paired hierarchical bivariate model, ML/DL outperformed traditional methods for both sensitivity (0.838, 95% CI: 0.668-0.930 versus 0.707, 95% CI: 0.421-0.889; paired Wald p = 0.019) and specificity (0.849, 95% CI: 0.512-0.968 versus 0.640, 95% CI: 0.376-0.840; paired Wald p = 0.0076). At a 25% pre-test probability, ML/DL was projected to yield 34 additional true positives (95% CI: -30 to 109) and 142 fewer false positives (95% CI: -381 to 129) per 1000 patients tested, although all absolute difference intervals crossed zero. Certainty of evidence was very low across all outcomes. GRADE certainty ranged from low to very low depending on outcome and stratum. Conclusions: ML/DL-based methods showed promising non-invasive diagnostic accuracy for PH, with significantly higher pooled sensitivity and specificity than traditional methods in paired comparisons. However, evidence certainty ranged from low to very low, and projected absolute benefits remained imprecise. These findings are hypothesis-generating; ML/DL tools may serve as adjuncts in the diagnostic pathway but cannot replace RHC at this stage.
SN  - 2075-4418
ER  -