To test the hypothesis that accuracy, discrimination, and precision in predicting postoperative complications improve when using both preoperative and intraoperative data input features versus preoperative data alone. Models that predict postoperative complications often ignore important intraoperative physiological changes. Incorporation of intraoperative physiological data may improve model performance. This retrospective cohort analysis included 52,529 inpatient surgeries at a single institution during a 5 year period. Random forest machine learning models in the validated MySurgeryRisk platform made patient-level predictions for three postoperative complications and mortality during hospital admission using electronic health record data and patient neighborhood characteristics. For each outcome, one model trained with preoperative data alone and one model trained with both preoperative and intraoperative data. Models were compared by accuracy, discrimination (expressed as AUROC), precision (expressed as AUPRC), and reclassification indices (NRI). Machine learning models incorporating both preoperative and intraoperative data had greater accuracy, discrimination, and precision than models using preoperative data alone for predicting all three postoperative complications (intensive care unit length of stay >48 hours, mechanical ventilation >48 hours, and neurological complications including delirium) and in-hospital mortality (accuracy: 88% vs. 77%, AUROC: 0.93 vs. 0.87, AUPRC: 0.21 vs. 0.15). Overall reclassification improvement was 2.9-10.0% for complications and 11.2% for in-hospital mortality. Incorporating both preoperative and intraoperative data significantly increased accuracy, discrimination, and precision for machine learning models predicting postoperative complications.
more »
« less
This content will become publicly available on December 1, 2024
Dynamic predictions of postoperative complications from explainable, uncertainty-aware, and multi-task deep neural networks
Abstract Accurate prediction of postoperative complications can inform shared decisions regarding prognosis, preoperative risk-reduction, and postoperative resource use. We hypothesized that multi-task deep learning models would outperform conventional machine learning models in predicting postoperative complications, and that integrating high-resolution intraoperative physiological time series would result in more granular and personalized health representations that would improve prognostication compared to preoperative predictions. In a longitudinal cohort study of 56,242 patients undergoing 67,481 inpatient surgical procedures at a university medical center, we compared deep learning models with random forests and XGBoost for predicting nine common postoperative complications using preoperative, intraoperative, and perioperative patient data. Our study indicated several significant results across experimental settings that suggest the utility of deep learning for capturing more precise representations of patient health for augmented surgical decision support. Multi-task learning improved efficiency by reducing computational resources without compromising predictive performance. Integrated gradients interpretability mechanisms identified potentially modifiable risk factors for each complication. Monte Carlo dropout methods provided a quantitative measure of prediction uncertainty that has the potential to enhance clinical trust. Multi-task learning, interpretability mechanisms, and uncertainty metrics demonstrated potential to facilitate effective clinical implementation.
more »
« less
- Award ID(s):
- 1750192
- NSF-PAR ID:
- 10401749
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 13
- Issue:
- 1
- ISSN:
- 2045-2322
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Advancements in computing and data from the near universal acceptance and implementation of electronic health records has been formative for the growth of personalized, automated, and immediate patient care models that were not previously possible. Artificial intelligence (AI) and its subfields of machine learning, reinforcement learning, and deep learning are well-suited to deal with such data. The authors in this paper review current applications of AI in clinical medicine and discuss the most likely future contributions that AI will provide to the healthcare industry. For instance, in response to the need to risk stratify patients, appropriately cultivated and curated data can assist decision-makers in stratifying preoperative patients into risk categories, as well as categorizing the severity of ailments and health for non-operative patients admitted to hospitals. Previous overt, traditional vital signs and laboratory values that are used to signal alarms for an acutely decompensating patient may be replaced by continuously monitoring and updating AI tools that can pick up early imperceptible patterns predicting subtle health deterioration. Furthermore, AI may help overcome challenges with multiple outcome optimization limitations or sequential decision-making protocols that limit individualized patient care. Despite these tremendously helpful advancements, the data sets that AI models train on and develop have the potential for misapplication and thereby create concerns for application bias. Subsequently, the mechanisms governing this disruptive innovation must be understood by clinical decision-makers to prevent unnecessary harm. This need will force physicians to change their educational infrastructure to facilitate understanding AI platforms, modeling, and limitations to best acclimate practice in the age of AI. By performing a thorough narrative review, this paper examines these specific AI applications, limitations, and requisites while reviewing a few examples of major data sets that are being cultivated and curated in the US.more » « less
-
null (Ed.)Objective: To elucidate the mechanics of scalp rotation flaps through 3D imaging and computational modeling. Excessive tension near a wound or sutured region can delay wound healing or trigger complications. Measuring tension in the operating room is challenging, instead, noninvasive methods to improve surgical planning are needed. Design: Multi-view stereo allows creation of 3D patient-specific geometries based on a set of photographs. The patient-specific 3D geometry is imported into a finite element (FE) platform to perform a virtual procedure. The simulation is compared with the clinical outcome. Additional simulations quantify the effect of individual flap parameters on the resulting tension distribution. Participants: Rotation flaps for reconstruction of scalp defects following melanoma resection in 2 cases are presented. Rotation flaps were designed without preoperative FE preparation. Main Outcome Measure: Tension distribution over the operated region. Results: The tension from FE shows peaks at the base and distal ends of the scalp rotation flap. The predicted geometry from the simulation aligns with postoperative photographs. Simulations exploring the flap design parameters show variation in the tension. Lower tensions were achieved when rotation was oriented with respect to skin tension lines (horizontal tissue fibers) and smaller rotation angles. Conclusions: Tension distribution following rotation of scalp flaps can be predicted through personalized FE simulations. Flaps can be designed to reduce tension using FE, which may greatly improve the reliability of scalp reconstruction in craniofacial surgery, critical in complex cases when scalp reconstruction is essential for coverage of hardware, implants, and/or bone graft.more » « less
-
more » « less
ABSTRACT BACKGROUND AND PURPOSE Functional magnetic resonance imaging (fMRI) is becoming widely recognized as a key component of preoperative neurosurgical planning, although intraoperative electrocortical stimulation (ECS) is considered the gold standard surgical brain mapping method. However, acquiring and interpreting ECS results can sometimes be challenging. This retrospective study assesses whether intraoperative availability of fMRI impacted surgical decision‐making when ECS was problematic or unobtainable.
METHODS Records were reviewed for 191 patients who underwent presurgical fMRI with fMRI loaded into the neuronavigation system. Four patients were excluded as a bur‐hole biopsy was performed. Imaging was acquired at 3 Tesla and analyzed using the general linear model with significantly activated pixels determined via individually determined thresholds. fMRI maps were displayed intraoperatively via commercial neuronavigation systems.
RESULTS Seventy‐one cases were planned ECS; however, 18 (25.35%) of these procedures were either not attempted or aborted/limited due to: seizure (10), patient difficulty cooperating with the ECS mapping (4), scarring/limited dural opening (3), or dural bleeding (1). In all aborted/limited ECS cases, the surgeon continued surgery using fMRI to guide surgical decision‐making. There was no significant difference in the incidence of postoperative deficits between cases with completed ECS and those with limited/aborted ECS.
CONCLUSIONS Preoperative fMRI allowed for continuation of surgery in over one‐fourth of patients in which planned ECS was incomplete or impossible, without a significantly different incidence of postoperative deficits compared to the patients with completed ECS. This demonstrates additional value of fMRI beyond presurgical planning, as fMRI data served as a backup method to ECS.
-
Gait speed assessment increases the predictive value of mortality and morbidity following older adults’ cardiac surgery. The purpose of this study was to improve clinical assessment and prediction of mortality and morbidity among older patients undergoing cardiac surgery through the identification of the relationships between preoperative gait and postural stability characteristics utilizing a noninvasive-wearable mobile phone device and postoperative cardiac surgical outcomes. This research was a prospective study of ambulatory patients aged over 70 years undergoing non-emergent cardiac surgery. Sixteen older adults with cardiovascular disease (Age 76.1 ± 3.6 years) scheduled for cardiac surgery within the next 24 h were recruited for this study. As per the Society of Thoracic Surgeons (STS) recommendation guidelines, eight of the cardiovascular disease (CVD) patients were classified as frail (prone to adverse outcomes with gait speed ≤0.833 m/s) and the remaining eight patients as non-frail (gait speed >0.833 m/s). Treating physicians and patients were blinded to gait and posture assessment results not to influence the decision to proceed with surgery or postoperative management. Follow-ups regarding patient outcomes were continued until patients were discharged or transferred from the hospital, at which time data regarding outcomes were extracted from the records. In the preoperative setting, patients performed the 5-m walk and stand still for 30 s in the clinic while wearing a mobile phone with a customized app “Lockhart Monitor” available at iOS App Store. Systematic evaluations of different gait and posture measures identified a subset of smartphone measures most sensitive to differences in two groups (frail versus non-frail) with adverse postoperative outcomes (morbidity/mortality). A regression model based on these smartphone measures tested positive on five CVD patients. Thus, clinical settings can readily utilize mobile technology, and the proposed regression model can predict adverse postoperative outcomes such as morbidity or mortality events.more » « less
