The DOI matches its Crossref record; 50 of the 54 references it cites were found in a registry or an index.
Validation of a Machine Learning Model That Outperforms Clinical Risk Scoring Systems for Upper Gastrointestinal Bleeding
Open accessAbstract
Background & Aims: Scoring systems are suboptimal for determining risk in patients with gastrointestinal bleeding (UGIB); these might be improved by a machine learning model. We used machine learning to develop a model to calculate risk of hospital-based intervention or death in patients with UGIB and compared its performance with other scoring systems. Methods: We analyzed data collected from consecutive unselected patients with UGIB from medical centers in 4 countries (United States, Scotland, England, Denmark; n=1958) from March 2014 through March 2015. We used the data to derive and internally validate a gradient-boosting machine learning model to identify patients who met a composite endpoint of hospital-based intervention (transfusion or hemostatic intervention) or death within 30 days. We compared the performance of the machine learning prediction model with validated pre-endoscopic clinical risk scoring systems (the Glasgow-Blatchford score [GBS], admission-Rockall score, and AIMS65). We externally validated the machine learning model using data from 2 Asia-Pacific sites (Singapore and New Zealand; n=399). Performance was measured by area under receiver operating characteristic curve (AUC) analysis. Results: The machine learning model identified patients who met the composite endpoint with an AUC of 0.91 in the in the internal validation set; the clinical scoring systems identified patients who met the composite endpoint with AUC values of 0.88 for GBS (P=.001), 0.73 for Rockall score (P<.001), and 0.78 for AIMS65 score (P<.001). In the external validation cohort, the machine learning model identified patients who met the composite endpoint with an AUC of 0.90, the GBS with an AUC of 0.87 (P=.004), the Rockall score with an AUC of 0.66 (P<.001), and the AIMS65 with an AUC of 0.64 (P<.001). At cutoff scores at which the machine learning model and GBS identified patients who met the composite endpoint with 100% sensitivity, the specificity values were 26% with the machine learning model vs 12% with GBS (P<.001). Conclusions: We developed a machine learning model that identifies patients with UGIB who met a composite endpoint of hospital-based intervention or death within 30 days with a greater AUC and higher levels of specificity, at 100% sensitivity, than validated clinical risk scoring systems. This model could increase identification of low-risk patients who can be safely discharged from the emergency department for outpatient management.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“AI-assisted tools have been successfully applied in various clinical settings to assist diagnosis [5], improve therapy [6], and predict risk of mortality [7].”
From Randomized Controlled Trials of Artificial Intelligence in Clinical Practice: Systematic Review (2022) · cites this paper as [7]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“there have been well-designed studies where more “complex” ML approaches have outperformed regression-derived clinical risk scores on external validation [7,59,60].”
From Randomized Controlled Trials of Artificial Intelligence in Clinical Practice: Systematic Review (2022) · cites this paper as [7]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 1×
“Currently the models deployed on electronic health records include support vector machines, regression models, and decision trees (classification and regression trees (CART), random forest, and gradient boosting decision trees).(21-28)”
MethodDeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988) · Biometrics · doi:10.2307/2531595 · Cited by 22,649 · cited 1×
“For external validation, the AUC was calculated and then compared using a 2-tailed nonparametric method.(35) McNemar’s matched pairs test was used to compare specificities.”
MethodMultilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728 · cited 1×
“21-28 Currently, the one use of clinical risk assessment tools for patients with UGIB generally agreed upon by guidelines and experts is to identify very low-risk patients who may be safely discharged from emergency departments with outpatient management 15, 18, 29 .”
Regularization and Variable Selection Via the Elastic Net
Zou, H., & Hastie, T. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00503.x · Cited by 20,957
Regularization Paths for Generalized Linear Models via Coordinate Descent
Friedman, J., Hastie, T., & Tibshirani, R. (2010) · Journal of Statistical Software · doi:10.18637/jss.v033.i01 · Cited by 19,927
ggplot2: Elegant Graphics for Data Analysis
Ginestet, C. E. (2011) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.1111/j.1467-985x.2010.00676_9.x · Cited by 14,511
ggplot2: Elegant Graphics for Data Analysis
Wickham, H. (2009) · doi:10.1007/978-0-387-98141-3 · Cited by 14,447
Ridge regression: Biased estimation for nonorthogonal problems
Hoerl, A. E., & Kennard, R. W. (1970) · Technometrics · doi:10.1080/00401706.1970.10488634 · Cited by 9,648
Least Squares Support Vector Machine Classifiers
Suykens, J., & Vandewalle, J. (1999) · Neural Processing Letters · doi:10.1023/a:1018628609742 · Cited by 9,481
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,266
Building Predictive Models in R Using the caret Package
Kuhn, M. (2008) · Journal of Statistical Software · doi:10.18637/jss.v028.i05 · Cited by 8,863
Ridge Regression: Biased Estimation for Nonorthogonal Problems
Hoerl, A. E., & Kennard, R. W. (2000) · Technometrics · doi:10.2307/1271436 · Cited by 7,001
ROCR: visualizing classifier performance in R
Sing, T., Sander, O., Beerenwinkel, N., & Lengauer, T. (2005) · Computer applications in the biosciences · doi:10.1093/bioinformatics/bti623 · Cited by 3,172
Barkun, A. N., Bardou, M., Kuipers, E. J., Sung, J., Hunt, R. H., Martel, M., Sinclair, P., & for the International Consensus Upper Gastrointestinal Bleeding Conference Group* (2010) · Annals of Internal Medicine · doi:10.7326/0003-4819-152-2-201001190-00009 · Cited by 1,152 · cited 2×
“Multiple guidelines recommend stratification of patients into low- and high-risk groups, and some recommend using risk assessment scores.(15,17,18) Pre-endoscopic risk scores such as the GlasgowBlatchford score (GBS), admission Rockall score, and AIMS65 synthesize clinical, hemodynamic, and initial laboratory variable…”
BackgroundMethodHecht-Nielsen, R. (1992) · Elsevier eBooks · doi:10.1016/b978-0-12-741252-8.50010-8 · Cited by 1,052
Burden of Gastrointestinal, Liver, and Pancreatic Diseases in the United States
Peery, A. F., Crockett, S. D., Barritt, A. S., Dellon, E. S., Eluri, S., Gangarosa, L. M., Jensen, E. T., Lund, J. L., Pasricha, S., Runge, T. M., et al. (2015) · Gastroenterology · doi:10.1053/j.gastro.2015.08.045 · Cited by 993 · cited 1×
“BACKGROUND Acute upper gastrointestinal bleeding (UGIB) is a common gastrointestinal diagnosis requiring hospital admission, with reported annual incidences in the range of 48 to 172 per 100,000 1-8 and mortality of ~2-10%.(9-16) Multiple guidelines recommend stratification of patients into low and high risk groups, a…”
BackgroundIncidence of and mortality from acute upper gastrointestinal haemorrhage in the United Kingdom
Rockall, T. A., Logan, R. F., Devlin, H. B., & Northfield, T. C. (1995) · BMJ · doi:10.1136/bmj.311.6999.222 · Cited by 910
Upper Digestive Bleeding in Cirrhosis. Post–Therapeutic Outcome and Prognostic Indicators
D’Amico, G., & de Franchis, R. (2003) · Hepatology · doi:10.1053/jhep.2003.50385 · Cited by 910 · cited 1×
“Two studies examined the prediction of mortality on external validation with ML models compared to liver-specific Child-Pugh and Model for End-Stage Liver Disease scores (designed to predict mortality in all patients with cirrhosis rather than in those presenting with gastrointestinal bleeding), and only 1 study found…”
Gralnek, I. M., Dumonceau, J., Kuipers, E. J., Lanas, Á., Sanders, D. S., Kurien, M., Rotondano, G., Hucl, T., Dinis-Ribeiro, M. J., Marmo, R., et al. (2015) · Endoscopy · doi:10.1055/s-0034-1393172 · Cited by 827
Management of Patients With Ulcer Bleeding
Laine, L., & Jensen, D. M. (2012) · The American Journal of Gastroenterology · doi:10.1038/ajg.2011.480 · Cited by 801 · cited 3×
“Multiple guidelines recommend stratification of patients into low- and high-risk groups, and some recommend using risk assessment scores.(15,17,18) Pre-endoscopic risk scores such as the GlasgowBlatchford score (GBS), admission Rockall score, and AIMS65 synthesize clinical, hemodynamic, and initial laboratory variable…”
BackgroundMethodSelf-citationMotwani, M., Dey, D., Berman, D. S., Germano, G., Achenbach, S., Al-Mallah, M. H., Andreini, D., Budoff, M. J., Cademartiri, F., Callister, T. Q., et al. (2016) · European Heart Journal · doi:10.1093/eurheartj/ehw188 · Cited by 692 · cited 1×
“Use of crossvalidation and hyperparameter tuning for internal validation is considered a robust method for model evaluation prior to external validation on a separate dataset and maximizes the potential performance of the ML model.(30-34) External validation was”
MethodHearnshaw, S., Logan, R. F. A., Lowe, D., Travis, S. P. L., Murphy, M. F., & Palmer, K. R. (2011) · Gut · doi:10.1136/gut.2010.228437 · Cited by 671 · cited 1×
“BACKGROUND Acute upper gastrointestinal bleeding (UGIB) is a common gastrointestinal diagnosis requiring hospital admission, with reported annual incidences in the range of 48 to 172 per 100,000 1-8 and mortality of ~2-10%.(9-16) Multiple guidelines recommend stratification of patients into low and high risk groups, a…”
BackgroundLongstreth, G. F. (1995) · PubMed · Cited by 587
Lanas, Á., García‐Rodríguez, L. A., Polo-Tomás, M., Ponce, M., Alonso-Abreu, I., Pérez-Aisa, M. A., Gisbert, J. P., Bujanda, L., Castro, M., Muñoz, M., et al. (2009) · The American Journal of Gastroenterology · doi:10.1038/ajg.2009.164 · Cited by 579 · cited 1×
“BACKGROUND Acute upper gastrointestinal bleeding (UGIB) is a common gastrointestinal diagnosis requiring hospital admission, with reported annual incidences in the range of 48 to 172 per 100,000 1-8 and mortality of ~2-10%.(9-16) Multiple guidelines recommend stratification of patients into low and high risk groups, a…”
BackgroundSaltzman, J. R., Tabak, Y. P., Hyett, B. H., Sun, X., Travis, A. C., & Johannes, R. S. (2011) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2011.06.024 · Cited by 543 · cited 1×
“BACKGROUND Acute upper gastrointestinal bleeding (UGIB) is a common gastrointestinal diagnosis requiring hospital admission, with reported annual incidences in the range of 48 to 172 per 100,000 1-8 and mortality of ~2-10%.(9-16) Multiple guidelines recommend stratification of patients into low and high risk groups, a…”
BackgroundEpidemiology of acute upper gastrointestinal bleeding
van Leerdam, M. E. (2008) · Best Practice & Research Clinical Gastroenterology · doi:10.1016/j.bpg.2007.10.011 · Cited by 457
Stanley, A. J., Laine, L., Dalton, H. R., Ngu, J. H., Schultz, M., Abazi, R., Zakko, L., Thornton, S., Wilkinson, K., Khor, C. J. L., et al. (2017) · BMJ · doi:10.1136/bmj.i6432 · Cited by 436 · cited 4×
“A composite endpoint is typically used in assessments to identify very-low-risk patients, most commonly a combination of hospital-based intervention (transfusion or hemostatic intervention [endoscopic, surgical, or interventional radiologic]) and mortality.(19) The aim of this study was to develop and validate a pre-e…”
MethodResultInfluentialSelf-citationShimabukuro, D. W., Barton, C. W., Feldman, M. D., Mataraso, S. J., & Das, R. (2017) · BMJ Open Respiratory Research · doi:10.1136/bmjresp-2017-000234 · Cited by 382 · cited 1×
“Electronic health records are becoming platforms for deploying prognostic ML models, which have already been used in clinical care for sepsis, acute kidney injury, and delirium.(47-49) The next steps would be an electronic health record based study that would reliably identify patients presenting with acute UGIB, use…”
MethodWilson, F. P., Shashaty, M. G. S., Testani, J. M., Aqeel, I., Borovskiy, Y., Ellenberg, S. S., Feldman, H. I., Fernández, H., Gitelman, Y., Lin, J. J., et al. (2015) · The Lancet · doi:10.1016/s0140-6736(15)60266-5 · Cited by 362 · cited 1×
“Electronic health records are becoming platforms for deploying prognostic ML models, which have already been used in clinical care for sepsis, acute kidney injury, and delirium.(47-49) The next steps would be an electronic health record based study that would reliably identify patients presenting with acute UGIB, use…”
MethodStanley, A. J., Ashley, D., Dalton, H. R., Mowat, C., Gaya, D., Thompson, E., Warshow, U. M., Groome, M., Cahill, A., Benson, G. S., et al. (2008) · The Lancet · doi:10.1016/s0140-6736(08)61769-9 · Cited by 358 · cited 1×
“Sensitivity of 100% means that no patients who will die or require transfusion or hemostatic intervention have a score above the cutoff and suggests that these patients generally can be sent home with outpatient management.(41) The significant increase in specificity from 12% with GBS to 26% with the ML model, with th…”
ResultSelf-citationAcute upper gastrointestinal haemorrhage in west of Scotland: case ascertainment study
Blatchford, O., Davidson, L., Murray, W. R., Blatchford, M., & Pell, J. P. (1997) · BMJ · doi:10.1136/bmj.315.7107.510 · Cited by 325
Changing Epidemiology of Upper Gastrointestinal Hemorrhage in the Last Decade: A Nationwide Analysis
Wuerth, B. A., & Rockey, D. C. (2017) · Digestive Diseases and Sciences · doi:10.1007/s10620-017-4882-6 · Cited by 312
Asia-Pacific working group consensus on non-variceal upper gastrointestinal bleeding: an update 2018
Sung, J. J. �., Chiu, P. W. Y., Chan, F. K. L., Lau, J., Goh, K., Ho, L. K. Y., Jung, H.-Y., Sollano, J. D., Gotoda, T., Reddy, D. N., et al. (2018) · Gut · doi:10.1136/gutjnl-2018-316276 · Cited by 282 · cited 2×
“Currently, the one use of clinical risk assessment tools for patients with UGIB generally agreed on by guidelines and experts is to identify very-low-risk patients who may be safely discharged from emergency departments with outpatient management.(15,18,29) A composite endpoint is typically used in assessments to iden…”
Abougergi, M. S., Travis, A. C., & Saltzman, J. R. (2014) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2014.09.027 · Cited by 280
Neural Networks for Perception
(1992) · Elsevier eBooks · doi:10.1016/c2013-0-11675-3 · Cited by 247
Vreeburg, E. M., Snel, P., de Bruijne, J. W., Bartelsman, J. F. W. M., Rauws, E. A., & Tytgat, G. N. J. (1997) · PubMed · Cited by 239
Analysis of 3,294 cases of upper gastrointestinal bleeding in military medical facilities.
Yavorski, R. T., Wong, R. K., Maydonovitch, C. L., Battin, L. S., Furnia, A., & Amundson, D. E. (1995) · PubMed · Cited by 211
Czernichow, P., Hochain, P., Nousbaum, J., Raymond, J.-M., Rudelli, A., Dupas, J., Amouretti, M., Gouérou, H., Capron, M.-H., Herman, H., et al. (2000) · European Journal of Gastroenterology & Hepatology · doi:10.1097/00042737-200012020-00007 · Cited by 187
Predicting Survival From Large Echocardiography and Electronic Health Record Datasets
Samad, M. D., Ulloa, A., Wehner, G. J., Jing, L., Hartzel, D. N., Good, C. W., Williams, B. A., Haggerty, C. M., & Fornwalt, B. K. (2018) · JACC. Cardiovascular imaging · doi:10.1016/j.jcmg.2018.04.026 · Cited by 173
Validation in prediction research: the waste by data splitting
Steyerberg, E. W. (2018) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2018.07.010 · Cited by 157 · cited 1×
“Use of crossvalidation and hyperparameter tuning for internal validation is considered a robust method for model evaluation prior to external validation on a separate dataset and maximizes the potential performance of the ML model.(30-34) External validation was”
MethodWong, A. H., Young, A. T., Liang, A. S., Gonzales, R., Douglas, V. C., & Hadley, D. (2018) · JAMA Network Open · doi:10.1001/jamanetworkopen.2018.1018 · Cited by 154 · cited 1×
“47-49 The next steps would be an electronic health record based study that would reliably identify patients presenting with acute UGIB, use structured datafields as predictive variables to develop models based on local patterns of disease and outcomes, and then prospectively validate the models in…”
Nahon, S., Hagège, H., Latrive, J., Rosa, I., Nalet, B., Bour, B., Faroux, R., Gower, P., Arpurt, J., Denis, J., et al. (2012) · Endoscopy · doi:10.1055/s-0032-1310006 · Cited by 109
An epidemiological study of acute upper gastrointestinal bleeding in Crete, Greece
Paspatis, G. A., Matrella, E., Kapsoritakis, A. N., Leontithis, C., Papanikolaou, N. K., Chlouverakis, G. J., & Kouroumalis, E. (2000) · European Journal of Gastroenterology & Hepatology · doi:10.1097/00042737-200012110-00008 · Cited by 80
Shung, D. L., Simonov, M., Gentry, M., Au, B., & Laine, L. (2019) · Digestive Diseases and Sciences · doi:10.1007/s10620-019-05645-z · Cited by 79 · cited 1×
“Most prior studies of ML models in UGIB, including the largest ML study published to date, did not have an external validation group.(46)”
ResultSelf-citationRamaekers, R., Mukarram, M. A., Smith, C. A. M., & Thiruganasambandamoorthy, V. (2016) · Academic Emergency Medicine · doi:10.1111/acem.13101 · Cited by 75 · cited 1×
“A meta-analysis reported similar results for GBS of 0, with sensitivity of 99% and specificity of 8% for a composite outcome of recurrent UGIB, intervention, or death.(40) At the matched sensitivity of 100%, our ML model had specificity of 26%.”
ResultRotondano, G., Cipolletta, L., Grossi, E., Koch, M., Intraligi, M., Buscema, M., & Marmo, R. (2011) · Gastrointestinal Endoscopy · doi:10.1016/j.gie.2010.10.006 · Cited by 70 · cited 1×
“For example, the largest study of ML in UGIB used 2380 patients and found that a neural network model had improved performance over the full Rockall score (which included endoscopic findings) for 30-day mortality on internal validation only, but this study had no external validation of the model and no assessment of m…”
ResultKennedy, E. H., Wiitala, W. L., Hayward, R. A., & Sussman, J. B. (2012) · Medical Care · doi:10.1097/mlr.0b013e31827da594 · Cited by 67 · cited 1×
“Use of crossvalidation and hyperparameter tuning for internal validation is considered a robust method for model evaluation prior to external validation on a separate dataset and maximizes the potential performance of the ML model.(30-34) External validation was”
MethodLyles, T. E., Elliott, A. C., & Rockey, D. C. (2013) · Journal of Clinical Gastroenterology · doi:10.1097/mcg.0000000000000014 · Cited by 61 · cited 1×
“For mortality, other ML models have a trend towards better performance than clinical risk scores, although only 3 studies compared ML models to clinical risk scores designed to assess risk in gastrointestinal bleeding and only 1 of them compared to a pre-endoscopic clinical risk score which is the appropriate comparat…”
ResultA simplified prognostic model to predict mortality in patients with acute variceal bleeding
Lee, H. H., Park, J. M., Han, S., Park, S., Kim, H. Y., Oh, J. H., Kim, C. W., Yoon, S. K., & Choi, M. (2017) · Digestive and Liver Disease · doi:10.1016/j.dld.2017.11.006 · Cited by 21 · cited 1×
“For mortality, other ML models have a trend towards better performance than clinical risk scores, although only 3 studies compared ML models to clinical risk scores designed to assess risk in gastrointestinal bleeding and only 1 of them compared to a pre-endoscopic clinical risk score which is the appropriate comparat…”
Result
Research works printed but not linked: 2
- Rotondano, 2011, Artificial neural networks accurately predict mortality in patients with nonvariceal upper GI bleeding, Gastrointest Endosc, 73, 218, 10.1016/j.gie.2010.10.006 · DOI
- Shung, 2019, Machine Learning to Predict Outcomes in Patients with Acute Gastrointestinal Bleeding: A Systematic Review, Dig Dis Sci, 64, 2078, 10.1007/s10620-019-05645-z · DOI
Cited by
Sorted by citations
ACG Clinical Guideline: Upper Gastrointestinal and Ulcer Bleeding
Laine, L., Barkun, A. N., Saltzman, J. R., Martel, M., & Leontiadis, G. I. (2021) · The American Journal of Gastroenterology · doi:10.14309/ajg.0000000000001245 · Cited by 661
“(8) can be set to provide sensitivities of 99% (comparable with GBS 5 0–1) or 100% (comparable with GBS 5 0) with specificities that are higher than GBS.”
BackgroundSelf-citationLaursen, S. B., Oakland, K., Laine, L., Bieber, V., Marmo, R., Redondo‐Cerezo, E., Dalton, H. R., Ngu, J., Schultz, M., Soncini, M., et al. (2020) · Gut · doi:10.1136/gutjnl-2019-320002 · Cited by 185
“35 Although several risk scores have been developed for assessment of patients with gastrointestinal bleeding, no risk score has been widely accepted in clinical practice.”
Self-citationArtificial intelligence in gastroenterology: A state-of-the-art review
Kröner, P. T., Engels, M. M. L., Glicksberg, B. S., Johnson, K. W., Mzaik, O., van Hooft, J. E., Wallace, M. B., El‐Serag, H. B., & Krittanawong, C. (2021) · World Journal of Gastroenterology · doi:10.3748/wjg.v27.i40.6794 · Cited by 175
Zhou, Q., Chen, Z.-H., Cao, Y.-H., & Peng, S. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00524-2 · Cited by 126
Randomized Controlled Trials of Artificial Intelligence in Clinical Practice: Systematic Review
Lam, T. Y. T., Cheung, M. F. K., Munro, Y. L., Lim, K. M., Shung, D., & Sung, J. J. Y. (2022) · Journal of Medical Internet Research · doi:10.2196/37188 · Cited by 120
“AI-assisted tools have been successfully applied in various clinical settings to assist diagnosis [5], improve therapy [6], and predict risk of mortality [7].”
Self-citation
Metadata
- Authors
- Shung, D. L., Au, B., Taylor, R. A., Tay, J. K., Laursen, S. B., Stanley, A. J., Dalton, H. R., Ngu, J., Schultz, M., & Laine, L.
- Affiliations
- Yale University (US)
- Stanford University (US)
- Odense University Hospital (DK)
- Glasgow Royal Infirmary (GB)
- Royal Cornwall Hospital (GB)
- Christchurch Hospital (NZ)
- Dunedin Public Hospital (NZ)
- Corresponding author
- Shung, Dennis L.
- Laine, Loren
- ORCID
- Venue
- Gastroenterology
- Publisher
- Elsevier BV
- Published
- 2020-01
- Volume
- 158
- Issue
- 1
- Pages
- 160-167
- ISSN
- 0016-5085 (ISSN-L)
- PMC
- PMC7004228
- OpenAlex
- W2976369463
- Semantic Scholar
- 49e263c97948d8177c777a1106e0ab0795effa58
- Cited by
- 227
- References
- 54
- Citations by year
- 2026: 22 · 2025: 30 · 2024: 49 · 2023: 29 · 2022: 31 · 2021: 37 · 2020: 25
- FWCI
- 21.87
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Gastroenterology (publishedVersion)
- PubMed (publishedVersion)
- University of Southern Denmark Research Portal (University of Southern Denmark) (publishedVersion, cc-by-nc-nd)
- Europe PMC (PubMed Central) (acceptedVersion)
- PubMed Central (acceptedVersion)
- Funders
- National Institutes of Health (T32 DK007017)
- Topics
- Health Sciences › Medicine › Gastroenterology › Gastrointestinal Bleeding Diagnosis and Treatment
- Health Sciences › Medicine › Gastroenterology › Helicobacter pylori-related gastroenterology studies
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- upper gastrointestinal bleeding, machine learning prediction models, Glasgow-Blatchford score, Rockall score, AIMS65, gradient boosting, hospital-based intervention, 30-day mortality, external validation, risk stratification, endoscopic hemostasis, blood transfusion, internal validation, sensitivity and specificity
- MeSH terms
- Machine Learning, Adult, Aged, Aged, 80 and over, Blood Transfusion, Emergency Service, Hospital, Female, Gastrointestinal Hemorrhage, Hemostatic Techniques, Humans, Male, Middle Aged, Models, Biological, Prognosis, ROC Curve, Risk Assessment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
