Utilizing Machine Learning Methods for Preoperative Prediction of Postsurgical Mortality and Intensive Care Unit Admission

Chiew, Calvin J; Liu, Nan; Wong, Ting Hway; Sim, Yilin Eileen; Abdullah, Hairil Rizal

doi:10.1097/sla.0000000000003297

Cited by 95 publications

(93 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML models usually have distinctive black box and uninterpretable characteristics, which means that the function between the features and the response is invisible to the researcher ( 23 , 31 – 33 ).…”

Section: Methodsmentioning

confidence: 99%

Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

Dai

Fan

et al. 2020

Front. Endocrinol.

View full text Add to dashboard Cite

Background: Some patients with acromegaly do not reach the remission standard in the short term after surgery but achieve remission without additional postoperative treatment during long-term follow-up; this phenomenon is defined as postoperative delayed remission (DR). DR may complicate the interpretation of surgical outcomes in patients with acromegaly and interfere with decision-making regarding postoperative adjuvant therapy. Objective: We aimed to develop and validate machine learning (ML) models for predicting DR in acromegaly patients who have not achieved remission within 6 months of surgery. Methods: We enrolled 306 acromegaly patients and randomly divided them into training and test datasets. We used the recursive feature elimination (RFE) algorithm to select features and applied six ML algorithms to construct DR prediction models. The performance of these ML models was validated using receiver operating characteristics analysis. We used permutation importance, SHapley Additive exPlanations (SHAP), and local interpretable model-agnostic explanation (LIME) algorithms to determine the importance of the selected features and interpret the ML models. Results: Fifty-five (17.97%) acromegaly patients met the criteria for DR, and five features (post-1w rGH, post-1w nGH, post-6m rGH, post-6m IGF-1, and post-6m nGH) were significantly associated with DR in both the training and the test datasets. After the RFE feature selection, the XGboost model, which comprised the 15 important features, had the greatest discriminatory ability (area under the curve = 0.8349, sensitivity = 0.8889, Youden's index = 0.6842). The XGboost model showed good discrimination ability and provided significantly better estimates of DR of patients with acromegaly compared with using only the Knosp grade. The results obtained from permutation importance, SHAP, and LIME algorithms showed that post-6m IGF-1 is the most important feature in XGboost algorithm prediction and showed the reliability and the clinical practicability of the XGboost model in DR prediction. Dai et al. ML Models Predict Acromegaly DR Conclusions: ML-based models can serve as an effective non-invasive approach to predicting DR and could aid in determining individual treatment and follow-up strategies for acromegaly patients who have not achieved remission within 6 months of surgery.

show abstract

Section: Methodsmentioning

confidence: 99%

Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

Dai

Fan

et al. 2020

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…Specifically, machine learning methods have been gaining momentum over the years due to their capabilities of modelling complex patterns within data, encouraged by the advancement of computational hardware. They have demonstrated success in various areas of emergency medicine [8], such as predicting in-patient admission [9], postsurgical mortality, and intensive care unit admission [10], and in-hospital mortality of emergency department patients [11][12][13][14], all of which are complex non-linear dynamical systems. In the domain of ambulance-related research, machine learning has been considered for ambulance travel time estimation [15,16], location selection for ambulance stations [17], and demand prediction [17,18].…”

Section: Introductionmentioning

confidence: 99%

Leveraging Machine Learning Techniques and Engineering of Multi-Nature Features for National Daily Regional Ambulance Demand Prediction

Lin

Cheong

et al. 2020

IJERPH

View full text Add to dashboard Cite

The accurate prediction of ambulance demand provides great value to emergency service providers and people living within a city. It supports the rational and dynamic allocation of ambulances and hospital staffing, and ensures patients have timely access to such resources. However, this task has been challenging due to complex multi-nature dependencies and nonlinear dynamics within ambulance demand, such as spatial characteristics involving the region of the city at which the demand is estimated, short and long-term historical demands, as well as the demographics of a region. Machine learning techniques are thus useful to quantify these characteristics of ambulance demand. However, there is generally a lack of studies that use machine learning tools for a comprehensive modeling of the important demand dependencies to predict ambulance demands. In this paper, an original and novel approach that leverages machine learning tools and extraction of features based on the multi-nature insights of ambulance demands is proposed. We experimentally evaluate the performance of next-day demand prediction across several state-of-the-art machine learning techniques and ambulance demand prediction methods, using real-world ambulatory and demographical datasets obtained from Singapore. We also provide an analysis of this ambulatory dataset and demonstrate the accuracy in modeling dependencies of different natures using various machine learning techniques.

show abstract

“…Based on these criteria, we included 94 cases. Data from each patient were retrospectively collected by medical case record review and include: age, gender, American Society of Anaesthesiologist (ASA) status, presence of comorbidities such as ischemic heart disease (IHD) and congestive heart failure (CHF); preoperative drugs such as antiplatelet or anticoagulation use; preoperative haemoglobin, surgical discipline, surgical severity (39,40), units of red blood cell (RBC) transfused perioperatively, days between IV iron therapy and surgery for the IV FCM group, and hospital length of stay. 5 patients were excluded from analysis as their surgeries were postponed after they had received IV iron therapy.…”

Section: Conduct Of Retrospective Chart Reviewmentioning

confidence: 99%

Real-world results of the implementation of preoperative anaemia clinic with intravenous iron therapy for treating iron-deficiency anaemia: a propensity-matched case-control study

Abdullah¹,

Thamnachit²,

Hao³

et al. 2021

Ann Transl Med

Self Cite

View full text Add to dashboard Cite

Background: Preoperative anaemia is associated with blood transfusion and longer hospital length of stay.Preoperative iron deficiency anaemia (IDA) can be treated with oral or intravenous (IV) iron. IV iron can raise haemoglobin faster compared with oral iron. However, its ability to reduce blood transfusion and length of stay in clinical trials is inconclusive. This study aims to compare blood transfusion and hospital length of stay between anemic patients who received preoperative IV iron versus standard care, after implementation of a protocol in 2017 to screen patients for preoperative IDA, and its treatment with IV iron.Methods: Retrospective before-after cohort study comparing 89 patients who received IV iron preoperatively in 2017, with historic patients who received oral iron therapy (selected by propensity score matching (PSM) from historic cohort of 7,542 patients who underwent surgery in 2016). Propensity score was calculated using ASA status, age, gender, surgical discipline, surgical risk and preoperative haemoglobin concentration. Both 1:1 and 1:2 matching were performed as sensitivity analysis.Results: After PSM, there was no statistically significant difference in distribution of preoperative clinical variables. There was no significant difference in proportion of cases requiring transfusion nor a difference in average units transfused per patient. IV iron cohort stayed in hospital on average 8.0 days compared to non-IV iron cohort 14.1-15.1 days (P=0.006, P=0.013 respectively). Average time from IV iron therapy to surgery was 10.5 days.Conclusions: Preoperative IV iron therapy for patients with IDA undergoing elective surgery may not reduce perioperative blood transfusion, but this could be due to the short time between therapy and surgery.Implementation of IV iron therapy may reduce hospital length of stay compared to standard care for anemic patients, although this may be enhanced by concomitant improvement in perioperative care.

show abstract

Utilizing Machine Learning Methods for Preoperative Prediction of Postsurgical Mortality and Intensive Care Unit Admission

Cited by 95 publications

References 25 publications

Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

Leveraging Machine Learning Techniques and Engineering of Multi-Nature Features for National Daily Regional Ambulance Demand Prediction

Real-world results of the implementation of preoperative anaemia clinic with intravenous iron therapy for treating iron-deficiency anaemia: a propensity-matched case-control study

Contact Info

Product

Resources

About