Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index; 31 of the 35 sources its claims cite were checked for support.
Abstract
Background: Accurate prediction of postoperative care requirements is critical for patient safety and resource allocation. Although numerous approaches involving artificial intelligence (AI) and machine learning (ML) have been proposed to support such predictions, their implementation in practice has so far been insufficiently successful. One reason for this is that the performance of the algorithms is difficult to assess in practical use, as the accuracy of clinical decisions has not yet been systematically quantified. As a result, models are often assessed purely from a technical perspective, neglecting the socio-technical context. Methods: We conducted a retrospective, single-center observational study at the University Hospital Augsburg, including 35,488 elective surgical cases documented between August 2023 and January 2025. For each case, preoperative care-level predictions by surgical and anesthesiology teams were compared with the actual postoperative care provided. Predictive performance was evaluated using accuracy and sensitivity. Since this is a highly imbalanced dataset, in addition to sensitivity and specificity, the balanced accuracy and the Fβ-score were also calculated. The results were contrasted with published Machine-Learning (ML)-based approaches. Results: Overall prediction accuracy was high (surgery: 91.2%; anesthesiology: 87.1%). However, sensitivity for identifying patients requiring postoperative intensive care was markedly lower than reported for ML models in the literature, with the largest discrepancies observed in patients ultimately admitted to the ICU (surgery: 38.05%; anesthesiology: 56.84%; ML: 70%). Nevertheless, clinical judgment demonstrated a superior F1-score, indicating a more balanced performance between sensitivity and precision (surgery: 0.527; anesthesiology: 0.551; ML: 0.28). Conclusions: This study provides the first real-world benchmark of clinical expertise in postoperative care prediction and shows a way in which modern ML approaches must be evaluated in a specific sociotechnical context. By quantifying the predictive performance of surgeons and anesthesiologists, it enables an evaluation of existing ML approaches. Thus the strength of our work is the provision of a real-world benchmark against which all ML methods for preoperative prediction of ICU demand can be systematically evaluated. This enables, for the first time, a comparison of different approaches on a common, practice-oriented basis and thus significantly facilitates translation into clinical practice, thereby closing the translational gap. Furthermore it offers a data-driven framework to support the integration of ML into preoperative decision-making.
Overview
CoChat Summary
TL;DR
This retrospective single-center study benchmarks preoperative clinician predictions of postoperative care level against actual care in 35,488 elective surgical cases, finding high overall accuracy but low sensitivity for ICU-level needs. It proposes this clinical performance as a reference benchmark for future AI/ML models.
Key findings
- Overall prediction accuracy was 91.17% for surgery and 87.12% for anesthesiology; approximately 9% and 13% of cases, respectively, did not match the actual postoperative level of care.
- For patients ultimately requiring Level 3 ICU care, sensitivity was 38.05% for surgery and 56.84% for anesthesiology, compared with 70% reported for ML models in the literature; F1-scores were 0.527 for surgery, 0.551 for anesthesiology, and 0.28 for the cited ML model.
- Level 0 dominated the dataset (90.3% prevalence): sensitivity for Level 0 was 98.21% for surgery and 91.14% for anesthesiology, while specificity differed (41.78% vs. 69.46%). Level 1 sensitivity was very low (9.88% surgery, 26.59% anesthesiology), and interrater agreement was low (Kappa = 0.0263 surgery, 0.0408 anesthesiology).
- Among 28,976 cases where both specialties predicted Level 0 and this was confirmed, some patients still required higher care (Level 1: n = 485; Level 2: n = 114; Level 3: n = 161).
Methods
- Retrospective, single-center observational study at University Hospital Augsburg. From 46,830 recorded cases, 11,342 emergency cases were excluded, leaving 35,488 elective procedures from 1 August 2023 to 31 January 2025. For each case, surgical and anesthesiologic preoperative predictions were compared with the actual postoperative level of care.
- Four care levels were defined: Level 0 = standard recovery room/PACU followed by timely transfer to general ward; Level 1 = prolonged PACU stay of at least 4 h; Level 2 = postoperative IMC monitoring; Level 3 = postoperative ICU care.
- Performance metrics included accuracy, sensitivity, specificity, balanced accuracy, precision, Fβ-score (β = 0.5, 1, 2), Cohen’s Kappa, and Chi-square tests; analyses used R and Python. No ML model was trained; published ML results were used only for contextual comparison.
Limitations
- Stated in the paper: overall accuracy is influenced by the high proportion of Level 0 cases and the system default to Level 0; physician training level was not systematically recorded; physicians’ reasons for predictions were not recorded; the single-center design limits generalizability; center-specific protocols may influence postoperative care levels; reasons for the actual care level realized were unavailable; no ML model was developed or trained; and the comparison with published ML results is illustrative rather than a direct evaluation.
- Evident from the text: the retrospective design and severe class imbalance limit inference, Level 1 was almost indistinguishable in practice, and no judgment could be made about the medical appropriateness of the observed care allocation.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
17 Valid · 5 Not valid · 4 Not checked · 86 Own results and interpretations
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“The absence of widespread adoption of promising data-driven and ML-based approaches can also be attributed to the lack of direct performance comparisons with subjective clinical decision-making [4,[31][32][33][34][35].”
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > 1. Introduction
What the sources say
- Partly supportedcites [4] Chiew, 2020, Utilizing Machine Learning Methods for Preoperative Prediction of Postsurgical Mortality and Intensive Care Unit Admission, Ann. Surg. sourceExperimental — accuracy not yet measured
The Discussion says further studies are needed to compare the authors’ approach with provider judgment, supporting the point that a direct comparison was lacking for this approach. It does not say that a lack of such comparisons explains the absence of widespread adoption of data-driven or ML approaches; it instead mentions interpretability and logistical challenges for implementation. No page number is available in our copy. (LLM, conf=0.83)
- Disputedcites [31] Sokol, 2025, Artificial intelligence should genuinely support clinical reasoning and decision making to bridge the translational gap, npj Digit. Med. sourceExperimental — accuracy not yet measured
The Systems ecology and artificial intelligence section (page unavailable) says predictive models are designed for evaluation and benchmarking against human experts, contrary to the claimed lack of direct comparisons. It attributes poor adoption instead to impractical tools and a lack of real-world usability. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
- Partly supportedcites [32] Arina, 2024, Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools, Anesthesiology sourceExperimental — accuracy not yet measured
The Benchmarks section reports that only three reviewed studies used clinical assessment as a comparator, and the discussion says widespread adoption requires stronger validation. The paper does not attribute limited adoption to a lack of direct comparisons with subjective clinical decision-making; it emphasizes bias, external validation, and generalizability instead. Page numbers were not available in our copy. (LLM, conf=0.82)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Furthermore, current ML models only predict the need for ICU admission-corresponding to Level 3 in our methodology [4].”
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > 4.2. Limitations
What the sources say
- Disputedcites [4] Chiew, 2020, Utilizing Machine Learning Methods for Preoperative Prediction of Postsurgical Mortality and Intensive Care Unit Admission, Ann. Surg. sourceExperimental — accuracy not yet measured
The Abstract (Objective) and Methods state that the models predict both 30-day postsurgical mortality and ICU stay longer than 24 hours. That contradicts the claim that they only predict ICU admission. “Level 3” is the citing paper’s own classification, not one established by this source. (LLM, conf=0.91)
Checked by a reasoning model — may be wrong.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“This observation is consistent with the findings of the meta-analysis by Arina et al. and underscores the importance of establishing a benchmark against clinical expertise [32].”
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > 4.1. Summary of the Results and Their Significance for the Establishment of Future AI Models
What the sources say
- Disputedcites [32] Arina, 2024, Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools, Anesthesiology sourceExperimental — accuracy not yet measured
The Benchmarks section reports the opposite of similar performance: across studies with technical or clinical comparators, ML models generally outperformed them, with an average increase in AUC and accuracy of 0.2–0.3. It notes one exception involving an ASA score, but does not present comparable performance between clinical judgment and ML as its finding. No page number is available in our copy. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In their systematic review and meta-analysis, Arina et al. summarized relevant AI models, highlighting three major limitations: the overall modest performance of existing approaches, the challenges of imbalanced datasets, and the lack of a pragmatic clinical benchmark [32].”
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > 4.1. Summary of the Results and Their Significance for the Establishment of Future AI Models
What the sources say
- Partly supportedcites [32] Arina, 2024, Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools, Anesthesiology sourceExperimental — accuracy not yet measured
The Benchmarks section (page unavailable) reports that studies used different comparators, which supports a concern about inconsistent benchmarking. It also lists clinical assessment as a comparator and does not establish that a pragmatic clinical benchmark is lacking specifically for postoperative ICU-demand models. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“For preoperative ICU prediction, the authors identified the study by Chiew et al. as particularly impactful, as it demonstrated a procedure-independent approach relying solely on preoperatively available information [4].”
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > 4.1. Summary of the Results and Their Significance for the Establishment of Future AI Models
What the sources say
- Partly supportedcites [4] Chiew, 2020, Utilizing Machine Learning Methods for Preoperative Prediction of Postsurgical Mortality and Intensive Care Unit Admission, Ann. Surg. sourceExperimental — accuracy not yet measured
The Discussion says the risk calculator uses variables available from routine preoperative evaluation, supporting the preoperative-information part of the claim. But the Methods list surgical risk, specialty, and a description of the planned surgery among the collected details, and say the model processed surgical descriptions as predictors. The approach was therefore not procedure-independent in the sense of excluding procedure information. No page numbers are available in our copy. (LLM, conf=0.89)
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
49 more claims · 5 with their cited sources checked
Create a free account to see all 112 claims and every source verdict.
- Probably not a substantial claim. 37
- It may state two separate claims as one. 28
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > 3.1. Surgery-Based Predictions
“Overall, the surgeons show an accuracy of 91.17%”
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > This study offers real-world insights into the preoperative prediction of postoperative care requirements following elective surgical interventions.
“| Level 0 | 31,480 (98.21%) | 296 (0.92%) | 125 (0.39%) | 152 (0.47%) | 32,053 | | Level 1 | 736 (86.59%) | 84 (9.88%) | 21 (2.47%) | 9 (1.06%) | 850 | | Level 2 | 492 (57.14%) | 41 (4.76%) | 324 (37.63%) | 4 (0.46%) | 861 | | Level 3 | 772 (44.78%) | 28 (1.62%) | 268 (15.55%) | 656 (38.05%) | 1724 | | total | 33,480 | 449 | 738 | 821 | 35,488 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > 4.1. Summary of the Results and Their Significance for the Establishment of Future AI Models
“Over the approximately one-year observation period, this concept could lead to a maximum increase of 1309 correctly predicted ICU admissions.”
§ Prediction of Postoperative ICU Requirements: Closing the Translational Gap with a Real-World Clinical Benchmark for Artificial Intelligence Approaches > 2.1. Clinical Practice at the University Hospital Augsburg
“between 1 August 2023, and 31 January 2025.”
Citations
Cites
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation
Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006) · Lecture Notes in Computer Science · doi:10.1007/11941439_114 · Cited by 1,974
Rajpurkar, P., Irvin, J., Ball, R. L., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C. P., et al. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002686 · Cited by 1,449
On evaluation metrics for medical applications of artificial intelligence
Hicks, S. A., Strümke, I., Thambawita, V., Hammou, M., Riegler, M. A., Halvorsen, P., & Parasa, S. (2022) · Scientific Reports · doi:10.1038/s41598-022-09954-8 · Cited by 934
Artificial Intelligence and Surgical Decision-making.
Loftus, T. J., Tighe, P. J., Filiberto, A. C., Efron, P. A., Brakenridge, S. C., Mohr, A. M., Rashidi, P., Upchurch, G. R., & Bihorac, A. (2020) · JAMA Surgery · doi:10.1001/jamasurg.2019.4917 · Cited by 650
Kheterpal, S., Tremper, K. K., Heung, M., Rosenberg, A. L., Englesbe, M., Shanks, A. M., & Campbell, D. A. (2009) · Anesthesiology · doi:10.1097/aln.0b013e3181979440 · Cited by 590
Wijnberge, M., Geerts, B. F., Hol, L., Lemmers, N., Mulder, M. P., Berge, P., Schenk, J., Terwindt, L. E., Hollmann, M. W., Vlaar, A. P., et al. (2020) · JAMA · doi:10.1001/jama.2020.0592 · Cited by 586
Steiner, D. F., MacDonald, R., Liu, Y., Truszkowski, P., Hipp, J. D., Gammage, C., Thng, F., Peng, L., & Stumpe, M. C. (2018) · American Journal of Surgical Pathology · doi:10.1097/pas.0000000000001151 · Cited by 489
Deep neural networks are superior to dermatologists in melanoma image classification
Brinker, T. J., Hekler, A., Enk, A. H., Berking, C., Haferkamp, S., Hauschild, A., Weichenthal, M., Klode, J., Schadendorf, D., Holland-Letz, T., et al. (2019) · European Journal of Cancer · doi:10.1016/j.ejca.2019.05.023 · Cited by 415
Bihorac, A., Ozrazgat-Baslanti, T., Ebadi, A., Motaei, A., Madkour, M., Pardalos, P. M., Lipori, G., Hogan, W. R., Efron, P. A., Moore, F., et al. (2019) · Annals of Surgery · doi:10.1097/sla.0000000000002706 · Cited by 377
Moonesinghe, S. R., Mythen, M. G., Das, P., Rowan, K. M., & Grocott, M. P. W. (2013) · Anesthesiology · doi:10.1097/aln.0b013e3182a4e94d · Cited by 334
Development and Validation of a Score for Prediction of Postoperative Respiratory Complications
Brueckmann, B., Villa-Uribe, J. L., Bateman, B. T., Grosse-Sundrup, M., Hess, D. R., Schlett, C. L., & Eikermann, M. (2013) · Anesthesiology · doi:10.1097/aln.0b013e318293065c · Cited by 274
A. van Klei, W., G.M. Moons, K., L.G. Rutten, C., Schuurhuis, A., T.A. Knape, J., J. Kalkman, C., & E. Grobbee, D. (2002) · Anesthesia & Analgesia · doi:10.1097/00000539-200203000-00030 · Cited by 233
Erratum: Corrigendum: Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature22985 · Cited by 213
Chiew, C. J., Liu, N., Wong, T. H., Sim, Y. E., & Abdullah, H. R. (2020) · Annals of Surgery · doi:10.1097/sla.0000000000003297 · Cited by 151
Impact of delay to surgery on survival in stage I-III colon cancer
Grass, F., Behm, K. T., Duchalais, É., Crippa, J., Spears, G. M., Harmsen, W. S., Hübner, M., Mathis, K. L., Kelley, S. R., Pembérton, J. H., et al. (2019) · European Journal of Surgical Oncology · doi:10.1016/j.ejso.2019.11.513 · Cited by 127
Sokol, K., Fackler, J., & Vogt, J. E. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01725-9 · Cited by 105
Arina, P., Kaczorek, M. R., Hofmaenner, D. A., Pisciotta, W., Refinetti, P., Singer, M., Mazomenos, E. B., & Whittle, J. (2024) · Anesthesiology · doi:10.1097/aln.0000000000004764 · Cited by 81
On evaluation metrics for medical applications of artificial intelligencePreprint
Hicks, S. A., Strümke, I., Thambawita, V. L., et al. (2021) · medRxiv · doi:10.1101/2021.04.07.21254975 · Cited by 60
Intermediate care units: Recommendations on facilities and structure
Waydhas, C., Herting, E., Kluge, S., Markewitz, A., Marx, G., Muhl, E., Nicolai, T., Notz, K., Parvu, V., Quintel, M., et al. (2017) · Medizinische Klinik - Intensivmedizin und Notfallmedizin · doi:10.1007/s00063-017-0369-7 · Cited by 51
Risk Scoring in Perioperative and Surgical Intensive Care Patients: A Review
Hariharan, S., & Zbar, A. P. (2006) · Current Surgery · doi:10.1016/j.cursur.2006.02.005 · Cited by 41
Thevathasan, T., Copeland, C. C., Long, D. R., Patrocínio, M. D., Friedrich, S., Grabitz, S. D., Kasotakis, G., Benjamin, J., Ladha, K. S., Sarge, T., et al. (2018) · Anesthesia & Analgesia · doi:10.1213/ane.0000000000003946 · Cited by 40
Cabrera, A., Bouterse, A., Nelson, M., Razzouk, J. A., Ramos, O., Chung, D., Cheng, W. K., & Danisa, O. (2022) · Journal of Clinical Neuroscience · doi:10.1016/j.jocn.2022.10.029 · Cited by 37
Impact of Delay in Treatment Initiation on Overall Survival in Laryngeal Cancers
Kompelli, A. R., Li, H., & Neskey, D. M. (2018) · Otolaryngology · doi:10.1177/0194599818803330 · Cited by 32
Financial cost of elective day of surgery cancellations
Turunen, E., Miettinen, M., Setälä, L. P., & Vehviläinen-Julkunen, K. (2018) · Journal of Hospital Administration · doi:10.5430/jha.v7n6p30 · Cited by 24
Cao, Y., Wang, Y. J., Liu, H., & Wu, L. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1571725 · Cited by 24
Artificial intelligence in intensive care: moving towards clinical decision support systems
Montomoli, J., Hilty, M. P., & İnce, C. (2022) · Minerva Anestesiologica · doi:10.23736/s0375-9393.22.16739-8 · Cited by 21
Rozeboom, P. D., Henderson, W. G., Dyas, A. R., Bronsert, M. R., Colborn, K. L., Lambert-Kerzner, A., Hammermeister, K. E., McIntyre, R. C., & Meguid, R. A. (2022) · JAMA Surgery · doi:10.1001/jamasurg.2021.7580 · Cited by 19
SAPS 3 score as a predictive factor for postoperative referral to intensive care unit
Silva, J. M., Rocha, H. M. C., Katayama, H. T., Dias, L. F., de Paula, M. B., Andraus, L. M. R., Silva, J. M. C., & Malbouisson, L. M. S. (2016) · Annals of Intensive Care · doi:10.1186/s13613-016-0129-5 · Cited by 17
van de Sande, D., van Genderen, M. E., Verhoef, C., van Bommel, J., Gommers, D., van Unen, E., Huiskens, J., & Grünhagen, D. J. (2021) · Surgery · doi:10.1016/j.surg.2021.05.005 · Cited by 15
Stieger, A., Schober, P. R., Venetz, P., Andereggen, L., Bello, C., Filipovic, M. G., Luedi, M. M., & Huber, M. (2025) · Journal of Clinical Anesthesia · doi:10.1016/j.jclinane.2025.111810 · Cited by 14
TURAN, E. İ., BAYDEMIR, A. E., ŞAHIN, A. S., & ÖZCAN, F. G. (2025) · Minerva Anestesiologica · doi:10.23736/s0375-9393.24.18587-2 · Cited by 10
Post-operative intensive care: Is it really necessary?
Cashmore, R. M. J., Fowler, A. J., & Pearse, R. M. (2019) · Intensive Care Medicine · doi:10.1007/s00134-019-05775-y · Cited by 9
Ive, J., Olukoya, O., Funnell, J. P., Booker, J., Lam, S. H. M., Reddy, U., Noor, K., Dobson, R., Luoma, A. M. V., & Marcus, H. J. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01952-0 · Cited by 9
Who benefits from postoperative ICU admissions?-more research is needed
Park, C.-M., & Suh, G. Y. (2018) · Journal of Thoracic Disease · doi:10.21037/jtd.2018.05.156 · Cited by 7
Xu, Z., Yao, S., Jiang, Z., Hu, L., Huang, Z., Zeng, Q., & Liu, X. (2023) · Heart & Lung · doi:10.1016/j.hrtlng.2023.08.001 · Cited by 7
Işık, G. Ö., Kılıç, B., Erşen, E., Kaynak, M., Turna, A., Özçıbık, O. S., Yıldırım, T., & Kara, H. V. (2025) · European journal of medical research · doi:10.1186/s40001-025-02553-z · Cited by 4
Nothofer, S., Geipel, J., Aehling, K., Sommer, B., Heller, A. R., Shiban, E., & Simon, P. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14082632 · Cited by 3
Self-citationA warning model for predicting patient admissions to the intensive care unit (ICU) following surgery
Li, L., He, H., Xiang, L., & Wang, Y. (2025) · Perioperative Medicine · doi:10.1186/s13741-025-00544-6 · Cited by 3
Erratum to: SAPS 3 score as a predictive factor for postoperative referral to intensive care unit
Silva, J. M., Rocha, H. M. C., Katayama, H. T., et al. (2016) · Annals of Intensive Care · doi:10.1186/s13613-016-0180-2
Development and Validation of a Score for Prediction of Postoperative Respiratory Complications
Brueckmann, B., Villa-Uribe, J. L., Bateman, B. T., et al. (2013) · Survey of Anesthesiology · doi:10.1097/01.sa.0000435460.76037.da
Research works printed but not linked: 1
- Devereaux, 2011, An international prospective cohort study evaluating major vascular complications among patients undergoing noncardiac surgery: The VISION Pilot Study, Open Med., 5, e193
Metadata
- Authors
- Althammer, A., Berger, F., Spring, O., Simon, P., Girrbach, F., Dieing, M., Brunner, J. O., Shmygalev, S., Bartenschlager, C. C., & Heller, A. R.
- Affiliations
- University of Augsburg (DE)
- Corresponding author
- Althammer, Alexander
- ORCID
- Venue
- Information
- Publisher
- MDPI AG
- Published
- 2025-10-13
- Volume
- 16
- Issue
- 10
- Pages
- 888
- ISSN
- 2078-2489 (ISSN-L)
- OpenAlex
- W4415280985
- Semantic Scholar
- e01392e04d52a348f6c6bdbfdd9ab5ae98d433ed
- Cited by
- 0
- References
- 37
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Information (publishedVersion, cc-by)
- Preprints.org (acceptedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- German Federal Ministry of Education and Research (16SV9030)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- ICU admission prediction, elective surgery, clinical decision-making, machine learning model evaluation, translational gap, predictive performance, sensitivity and specificity, resource allocation
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.