Systematic Review on ML Hypotension Detection
Budget: $30 – $250 USD
I need a detailed systematic review on "machine-learning early detection warning system for intraoperative hypotension." This review is for academic submission and should be 23-25 pages in length (double spaced) with no intention to publish. I will provide the reference list (see below towards the bottom). Please expect that I will need revisions of the draft as my school will requires changes as they per their suggestions.
PLEASE NOTE: my school is VERY strict with using AI to write the actual paper. It's fine to use AI for support, but not in the actual writing out of the paper. This is why I'm outsourcing this.
Key Focus Areas:
- Clinical outcomes with an emphasis on accuracy of predictions and reduction in adverse events
- Comprehensive analysis of clinical trials.
- Research question: In patients undergoing surgery, does the utility of a machine-learning early detection warning system for intraoperative hypotension compared to standard care monitoring reduce the likelihood of developing postoperative organ injury?
Ideal Skills and Experience:
- Experience in putting together systematic review for a topic using existing clinical trials.
- The articles referenced must be no more than 5 years old
The below are the required subsections of this paper:
ABSTRACT: should be structured into four paragraphs not exceeding 250 words total. It must be written in complete sentences. Abbreviations should be avoided. No literature
should be cited in this section. The abstract must include your testable hypothesis and how you tested it.
Sections:
● Hypothesis: State the hypothesis of the study (see How to Write a Hypothesis in
Moodle/LMS)
● Methods: Identify the study design and statistical methods used
● Results: Describe the outcome of the study and the statistical significance, if
appropriate
● Conclusions: State the significance of the results
● Word Count: Provide a word count for the abstract
● Keywords: Following the abstract, provide 3 to 10 keywords for indexing purposes
INTRODUCTION:
The introduction should provide a clear statement of the problem, the relevant literature on the subject, and the proposed approach or solution. The introduction must:
● Be well referenced
● Begin with an impactful statement
● Begin broadly to educate readers about the general topic, then narrow down to the focus of the paper
● Use references that are NOT used in the results section
4. METHODS:
The methods should contain enough information to allow the study to be replicated, including:
● Databases used
● Search strategy
● Search terms
● Inclusion / exclusion criteria (state the parameters for including references in your
paper and the parameters used to exclude references, i.e. year published or
population type)
● Methods of data analysis (how the evidence table was constructed
● Statistical methods used
● Written in past tense
RESULTS:
The results should be presented with clarity and precision, and should:
● Summarize the data and key findings of the selected primary literature (i.e.
populations, outcomes, etc.)
● Synthesize the data contained in multiple studies, providing any relationship between those studies (i.e. similarities in data)
● Include an Evidence Table as an Appendix to the paper
● Reference all citations in the evidence table
● Written in past tense
DISCUSSION:
Authors should explain what the results mean and how the results relate to the hypothesis presented. The discussion should interpret the findings and should include:
● Explanation of the findings (not a reiteration of the results)
● Interpretation of the results
● Assessment of the primary literature's impact on the hypothesis (answer the question - does the data support the hypothesis?)
● Limitations and future directions
● All citations in the evidence table referenced
● Conclusion: A concluding paragraph should be added at the end of the paper that clearly states how the hypothesis was proven or disproven
FIGURES AND TABLES:
An Evidence Table:
● Must be included as an Appendix to the paper
● Cited in the results and discussion sections
● Limited use of review articles
Other Figures and Tables:
● A maximum of two (2) properly cited figures/tables reproduced directly from the primary literature is permitted. An unlimited number of original figures/tables is permitted.
● All figures should have a title and figure legend that properly describes the dataset
(i.e. the lines, boxes, colors, symbols, error bars, abbreviations).
● All figures/tables should be numbered in the order they are cited in the text.
References
Lai C.J., Cheng Y.J., Han Y.Y., et al. (2024) Hypotension prediction index for prevention of intraoperative hypotension in patients undergoing general anesthesia: a randomized controlled trial. Perioper. Med. 13(1), 57.
Šribar A., Jurinjak I.S., Almahariq H., et al. (2023) Hypotension prediction index guided versus conventional goal directed therapy to reduce intraoperative hypotension during thoracic surgery: a randomized trial. BMC Anesthesiol. 23(1), 101.
Rellum S.R., Schuurmans J., Schenk J., et al. (2023) Effect of the machine learning-derived Hypotension Prediction Index (HPI) combined with diagnostic guidance versus standard care on depth and duration of intraoperative and postoperative hypotension in elective cardiac surgery patients: HYPE-2 – study protocol of a randomised clinical trial. BMJ Open 13(5), e061832.
Ripollés-Melchor J., Espinosa Á.V., Fernández-Valdes-Bango P., et al. (2024) Hypotension Prediction Index-guided intraoperative hemodynamic therapy did not reduce the incidence of postoperative AKI or overall complications compared to standard care. Rev. Esp. Anestesiol. Reanim. 71(10), 719–731.
Lorente J.V., Ripollés-Melchor J., Jimenez I.F., et al. (2023) Intraoperative hemodynamic optimization using the hypotension prediction index vs. goal-directed hemodynamic therapy during elective major abdominal surgery: the Predict-H multicenter randomized controlled trial. Front. Anesthesiol. 2, 1193886.
Mulder M.P., et al. (2026) Comparison of a mean arterial pressure alarm to the hypotension prediction index in preventing intraoperative hypotension in elective moderate- to high-risk non-cardiac surgical patients: a study protocol for a blinded, parallel, randomized controlled trial with a non-inferiority framework. Trials 27(1), 104.
Barker A., et al. (2024) Machine learning predicts unplanned care escalations for post-anesthesia care unit patients during the perioperative period: a single-center retrospective study in surgical patients. J. Med. Syst. 48(1), 91.
Wijnberge M., Geerts B.F., Hol L., et al. (2020) Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial. JAMA 323(11), 1052–1060.
Murabito P., Astuto M., Sanfilippo F., et al. (2022) Proactive management of intraoperative hypotension reduces biomarkers of organ injury and oxidative stress during elective non-cardiac surgery: a pilot randomized controlled trial. J. Clin. Med. 11(2), 392.
Strömblad C.T., Wilson R.S., Kanter G., et al. (2021) Effect of a predictive model on planned surgical duration accuracy, patient wait time, and use of presurgical resources: a randomized clinical trial. JAMA Surg. 156(4), 322–330.
Schneck E., Schulte D., Habig L., et al. (2020) Hypotension Prediction Index based protocolized haemodynamic management reduces the incidence and duration of intraoperative hypotension in primary total hip arthroplasty: a single centre feasibility randomised blinded prospective interventional trial. J. Clin. Monit. Comput. 34(6), 1149–1158.
Habicher M., Denn S.M., Schneck E., et al. (2025) Perioperative goal-directed therapy with artificial intelligence to reduce the incidence of intraoperative hypotension and renal failure in patients undergoing lung surgery: a pilot study. J. Clin. Anesth. 102, 111777.
PLEASE NOTE: my school is VERY strict with using AI to write the actual paper. It's fine to use AI for support, but not in the actual writing out of the paper. This is why I'm outsourcing this.
Key Focus Areas:
- Clinical outcomes with an emphasis on accuracy of predictions and reduction in adverse events
- Comprehensive analysis of clinical trials.
- Research question: In patients undergoing surgery, does the utility of a machine-learning early detection warning system for intraoperative hypotension compared to standard care monitoring reduce the likelihood of developing postoperative organ injury?
Ideal Skills and Experience:
- Experience in putting together systematic review for a topic using existing clinical trials.
- The articles referenced must be no more than 5 years old
The below are the required subsections of this paper:
ABSTRACT: should be structured into four paragraphs not exceeding 250 words total. It must be written in complete sentences. Abbreviations should be avoided. No literature
should be cited in this section. The abstract must include your testable hypothesis and how you tested it.
Sections:
● Hypothesis: State the hypothesis of the study (see How to Write a Hypothesis in
Moodle/LMS)
● Methods: Identify the study design and statistical methods used
● Results: Describe the outcome of the study and the statistical significance, if
appropriate
● Conclusions: State the significance of the results
● Word Count: Provide a word count for the abstract
● Keywords: Following the abstract, provide 3 to 10 keywords for indexing purposes
INTRODUCTION:
The introduction should provide a clear statement of the problem, the relevant literature on the subject, and the proposed approach or solution. The introduction must:
● Be well referenced
● Begin with an impactful statement
● Begin broadly to educate readers about the general topic, then narrow down to the focus of the paper
● Use references that are NOT used in the results section
4. METHODS:
The methods should contain enough information to allow the study to be replicated, including:
● Databases used
● Search strategy
● Search terms
● Inclusion / exclusion criteria (state the parameters for including references in your
paper and the parameters used to exclude references, i.e. year published or
population type)
● Methods of data analysis (how the evidence table was constructed
● Statistical methods used
● Written in past tense
RESULTS:
The results should be presented with clarity and precision, and should:
● Summarize the data and key findings of the selected primary literature (i.e.
populations, outcomes, etc.)
● Synthesize the data contained in multiple studies, providing any relationship between those studies (i.e. similarities in data)
● Include an Evidence Table as an Appendix to the paper
● Reference all citations in the evidence table
● Written in past tense
DISCUSSION:
Authors should explain what the results mean and how the results relate to the hypothesis presented. The discussion should interpret the findings and should include:
● Explanation of the findings (not a reiteration of the results)
● Interpretation of the results
● Assessment of the primary literature's impact on the hypothesis (answer the question - does the data support the hypothesis?)
● Limitations and future directions
● All citations in the evidence table referenced
● Conclusion: A concluding paragraph should be added at the end of the paper that clearly states how the hypothesis was proven or disproven
FIGURES AND TABLES:
An Evidence Table:
● Must be included as an Appendix to the paper
● Cited in the results and discussion sections
● Limited use of review articles
Other Figures and Tables:
● A maximum of two (2) properly cited figures/tables reproduced directly from the primary literature is permitted. An unlimited number of original figures/tables is permitted.
● All figures should have a title and figure legend that properly describes the dataset
(i.e. the lines, boxes, colors, symbols, error bars, abbreviations).
● All figures/tables should be numbered in the order they are cited in the text.
References
Lai C.J., Cheng Y.J., Han Y.Y., et al. (2024) Hypotension prediction index for prevention of intraoperative hypotension in patients undergoing general anesthesia: a randomized controlled trial. Perioper. Med. 13(1), 57.
Šribar A., Jurinjak I.S., Almahariq H., et al. (2023) Hypotension prediction index guided versus conventional goal directed therapy to reduce intraoperative hypotension during thoracic surgery: a randomized trial. BMC Anesthesiol. 23(1), 101.
Rellum S.R., Schuurmans J., Schenk J., et al. (2023) Effect of the machine learning-derived Hypotension Prediction Index (HPI) combined with diagnostic guidance versus standard care on depth and duration of intraoperative and postoperative hypotension in elective cardiac surgery patients: HYPE-2 – study protocol of a randomised clinical trial. BMJ Open 13(5), e061832.
Ripollés-Melchor J., Espinosa Á.V., Fernández-Valdes-Bango P., et al. (2024) Hypotension Prediction Index-guided intraoperative hemodynamic therapy did not reduce the incidence of postoperative AKI or overall complications compared to standard care. Rev. Esp. Anestesiol. Reanim. 71(10), 719–731.
Lorente J.V., Ripollés-Melchor J., Jimenez I.F., et al. (2023) Intraoperative hemodynamic optimization using the hypotension prediction index vs. goal-directed hemodynamic therapy during elective major abdominal surgery: the Predict-H multicenter randomized controlled trial. Front. Anesthesiol. 2, 1193886.
Mulder M.P., et al. (2026) Comparison of a mean arterial pressure alarm to the hypotension prediction index in preventing intraoperative hypotension in elective moderate- to high-risk non-cardiac surgical patients: a study protocol for a blinded, parallel, randomized controlled trial with a non-inferiority framework. Trials 27(1), 104.
Barker A., et al. (2024) Machine learning predicts unplanned care escalations for post-anesthesia care unit patients during the perioperative period: a single-center retrospective study in surgical patients. J. Med. Syst. 48(1), 91.
Wijnberge M., Geerts B.F., Hol L., et al. (2020) Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial. JAMA 323(11), 1052–1060.
Murabito P., Astuto M., Sanfilippo F., et al. (2022) Proactive management of intraoperative hypotension reduces biomarkers of organ injury and oxidative stress during elective non-cardiac surgery: a pilot randomized controlled trial. J. Clin. Med. 11(2), 392.
Strömblad C.T., Wilson R.S., Kanter G., et al. (2021) Effect of a predictive model on planned surgical duration accuracy, patient wait time, and use of presurgical resources: a randomized clinical trial. JAMA Surg. 156(4), 322–330.
Schneck E., Schulte D., Habig L., et al. (2020) Hypotension Prediction Index based protocolized haemodynamic management reduces the incidence and duration of intraoperative hypotension in primary total hip arthroplasty: a single centre feasibility randomised blinded prospective interventional trial. J. Clin. Monit. Comput. 34(6), 1149–1158.
Habicher M., Denn S.M., Schneck E., et al. (2025) Perioperative goal-directed therapy with artificial intelligence to reduce the incidence of intraoperative hypotension and renal failure in patients undergoing lung surgery: a pilot study. J. Clin. Anesth. 102, 111777.