How patients fare after anaesthesia for elective surgery: a survey of postoperative nausea and vomiting,pain and confusion

INTRODUCTION

Postoperative nausea and vomiting (PONV), and postoperative pain are common during the early postoperative period. In addition to these problems, elderly patients risk developing postoperative confusion. This study aimed to identify the risk factors associated with these problems, and the extent of these problems, in a Singapore inpatient surgical population.

METHODS

Over a period of six weeks, we surveyed 707 elective surgical inpatients aged ≥ 18 years who received general anaesthesia and/or regional anaesthesia.

RESULTS

The incidence of PONV was 31.8%(95% confidence interval [CI] 34.8–41.9). The incidence increased with increasing Apfel score (p < 0.001) and were higher in female patients (odds ratio [OR] 1.74, 95% CI 1.28–2.36), non-smokers (OR 1.72, 95% CI 1.04–2.88), patients with a history of PONV and/or motion sickness (OR 3.45, 95% CI 2.38–5.24), patients who received opioids (OR 1.39, 95% CI 1.03–1.88), and patients who received general anaesthesia (OR 1.76, 95% CI 1.11–2.79). Moderate to severe pain at rest and with movement were reported in 19.9% and 52.5% of patients, respectively. Among the patients who were predicted to experience mild pain, 29.5% reported moderate pain and 8.1% reported severe pain. The prevalence of postoperative confusion was 3.9% in the geriatric population.

CONCLUSION

Higher Apfel scores were associated with a higher risk of PONV and multimodal treatment for postoperative pain management was found to be insufficient. The incidence of postoperative confusion was low in this study.     

Grid Binary LOgistic REgression (GLORE): building shared models without sharing data

Objective

The classification of complex or rare patterns in clinical and genomic data requires the availability of a large, labeled patient set. While methods that operate on large, centralized data sources have been extensively used, little attention has been paid to understanding whether models such as binary logistic regression (LR) can be developed in a distributed manner, allowing researchers to share models without necessarily sharing patient data.

Material and methods

Instead of bringing data to a central repository for computation, we bring computation to the data. The Grid Binary LOgistic REgression (GLORE) model integrates decomposable partial elements or non-privacy sensitive prediction values to obtain model coefficients, the variance-covariance matrix, the goodness-of-fit test statistic, and the area under the receiver operating characteristic (ROC) curve.

Results

We conducted experiments on both simulated and clinically relevant data, and compared the computational costs of GLORE with those of a traditional LR model estimated using the combined data. We showed that our results are the same as those of LR to a 10⁻¹⁵ precision. In addition, GLORE is computationally efficient.

Limitation

In GLORE, the calculation of coefficient gradients must be synchronized at different sites, which involves some effort to ensure the integrity of communication. Ensuring that the predictors have the same format and meaning across the data sets is necessary.

Conclusion

The results suggest that GLORE performs as well as LR and allows data to remain protected at their original sites.     

Finding falls in ambulatory care clinical documents using statistical text mining

Objective

To determine how well statistical text mining (STM) models can identify falls within clinical text associated with an ambulatory encounter.

Materials and Methods

2241 patients were selected with a fall-related ICD-9-CM E-code or matched injury diagnosis code while being treated as an outpatient at one of four sites within the Veterans Health Administration. All clinical documents within a 48-h window of the recorded E-code or injury diagnosis code for each patient were obtained (n=26 010; 611 distinct document titles) and annotated for falls. Logistic regression, support vector machine, and cost-sensitive support vector machine (SVM-cost) models were trained on a stratified sample of 70% of documents from one location (dataset A_train) and then applied to the remaining unseen documents (datasets A_test–D).

Results

All three STM models obtained area under the receiver operating characteristic curve (AUC) scores above 0.950 on the four test datasets (A_test–D). The SVM-cost model obtained the highest AUC scores, ranging from 0.953 to 0.978. The SVM-cost model also achieved F-measure values ranging from 0.745 to 0.853, sensitivity from 0.890 to 0.931, and specificity from 0.877 to 0.944.

Discussion

The STM models performed well across a large heterogeneous collection of document titles. In addition, the models also generalized across other sites, including a traditionally bilingual site that had distinctly different grammatical patterns.

Conclusions

The results of this study suggest STM-based models have the potential to improve surveillance of falls. Furthermore, the encouraging evidence shown here that STM is a robust technique for mining clinical documents bodes well for other surveillance-related topics.     

The application of naive Bayes model averaging to predict Alzheimer's disease from genome-wide data

Objective

Predicting patient outcomes from genome-wide measurements holds significant promise for improving clinical care. The large number of measurements (eg, single nucleotide polymorphisms (SNPs)), however, makes this task computationally challenging. This paper evaluates the performance of an algorithm that predicts patient outcomes from genome-wide data by efficiently model averaging over an exponential number of naive Bayes (NB) models.

Design

This model-averaged naive Bayes (MANB) method was applied to predict late onset Alzheimer''s disease in 1411 individuals who each had 312 318 SNP measurements available as genome-wide predictive features. Its performance was compared to that of a naive Bayes algorithm without feature selection (NB) and with feature selection (FSNB).

Measurement

Performance of each algorithm was measured in terms of area under the ROC curve (AUC), calibration, and run time.

Results

The training time of MANB (16.1 s) was fast like NB (15.6 s), while FSNB (1684.2 s) was considerably slower. Each of the three algorithms required less than 0.1 s to predict the outcome of a test case. MANB had an AUC of 0.72, which is significantly better than the AUC of 0.59 by NB (p<0.00001), but not significantly different from the AUC of 0.71 by FSNB. MANB was better calibrated than NB, and FSNB was even better in calibration. A limitation was that only one dataset and two comparison algorithms were included in this study.

Conclusion

MANB performed comparatively well in predicting a clinical outcome from a high-dimensional genome-wide dataset. These results provide support for including MANB in the methods used to predict outcomes from large, genome-wide datasets.     

Use of a support vector machine for categorizing free-text notes: assessment of accuracy across two institutions

Background

Electronic health record (EHR) users must regularly review large amounts of data in order to make informed clinical decisions, and such review is time-consuming and often overwhelming. Technologies like automated summarization tools, EHR search engines and natural language processing have been shown to help clinicians manage this information.

Objective

To develop a support vector machine (SVM)-based system for identifying EHR progress notes pertaining to diabetes, and to validate it at two institutions.

Materials and methods

We retrieved 2000 EHR progress notes from patients with diabetes at the Brigham and Women''s Hospital (1000 for training and 1000 for testing) and another 1000 notes from the University of Texas Physicians (for validation). We manually annotated all notes and trained a SVM using a bag of words approach. We then used the SVM on the testing and validation sets and evaluated its performance with the area under the curve (AUC) and F statistics.

Results

The model accurately identified diabetes-related notes in both the Brigham and Women''s Hospital testing set (AUC=0.956, F=0.934) and the external University of Texas Faculty Physicians validation set (AUC=0.947, F=0.935).

Discussion

Overall, the model we developed was quite accurate. Furthermore, it generalized, without loss of accuracy, to another institution with a different EHR and a distinct patient and provider population.

Conclusions

It is possible to use a SVM-based classifier to identify EHR progress notes pertaining to diabetes, and the model generalizes well.     

Improving personal health records for patient-centered care

Objective

To assess the patient-centeredness of personal health records (PHR) and offer recommendations for best practice guidelines.

Design

Semi-structured interviews were conducted in seven large early PHR adopter organizations in 2007. Organizations were purposively selected to represent a variety of US settings, including medium and large hospitals, ambulatory care facilities, insurers and health plans, government departments, and commercial sectors.

Measurements

Patient-centeredness was assessed against a framework of care that includes: (1) respect for patient values, preferences, and expressed needs; (2) information and education; (3) access to care; (4) emotional support to relieve fear and anxiety; (5) involvement of family and friends; (6) continuity and secure transition between healthcare providers; (7) physical comfort; (8) coordination of care. Within this framework we used evidence for patient preferences (where it exists) to compare existing PHR policies, and propose a best practice model.

Results

Most organizations enable many patient-centered functions such as data access for proxies and minors. No organization allows patient views of clinical progress notes, and turnaround times for PHR reporting of normal laboratory results can be up to 7 days.

Conclusion

Findings suggest patient-centeredness for personal health records can be improved, and recommendations are made for best practice guidelines.     

Use of population health data to refine diagnostic decision-making for pertussis

Objective

To improve identification of pertussis cases by developing a decision model that incorporates recent, local, population-level disease incidence.

Design

Retrospective cohort analysis of 443 infants tested for pertussis (2003–7).

Measurements

Three models (based on clinical data only, local disease incidence only, and a combination of clinical data and local disease incidence) to predict pertussis positivity were created with demographic, historical, physical exam, and state-wide pertussis data. Models were compared using sensitivity, specificity, area under the receiver-operating characteristics (ROC) curve (AUC), and related metrics.

Results

The model using only clinical data included cyanosis, cough for 1 week, and absence of fever, and was 89% sensitive (95% CI 79 to 99), 27% specific (95% CI 22 to 32) with an area under the ROC curve of 0.80. The model using only local incidence data performed best when the proportion positive of pertussis cultures in the region exceeded 10% in the 8–14 days prior to the infant''s associated visit, achieving 13% sensitivity, 53% specificity, and AUC 0.65. The combined model, built with patient-derived variables and local incidence data, included cyanosis, cough for 1 week, and the variable indicating that the proportion positive of pertussis cultures in the region exceeded 10% 8–14 days prior to the infant''s associated visit. This model was 100% sensitive (p<0.04, 95% CI 92 to 100), 38% specific (p<0.001, 95% CI 33 to 43), with AUC 0.82.

Conclusions

Incorporating recent, local population-level disease incidence improved the ability of a decision model to correctly identify infants with pertussis. Our findings support fostering bidirectional exchange between public health and clinical practice, and validate a method for integrating large-scale public health datasets with rich clinical data to improve decision-making and public health.     

A study in transfer learning: leveraging data from multiple hospitals to enhance hospital-specific predictions

Background

Data-driven risk stratification models built using data from a single hospital often have a paucity of training data. However, leveraging data from other hospitals can be challenging owing to institutional differences with patients and with data coding and capture.

Objective

To investigate three approaches to learning hospital-specific predictions about the risk of hospital-associated infection with Clostridium difficile, and perform a comparative analysis of the value of different ways of using external data to enhance hospital-specific predictions.

Materials and methods

We evaluated each approach on 132 853 admissions from three hospitals, varying in size and location. The first approach was a single-task approach, in which only training data from the target hospital (ie, the hospital for which the model was intended) were used. The second used only data from the other two hospitals. The third approach jointly incorporated data from all hospitals while seeking a solution in the target space.

Results

The relative performance of the three different approaches was found to be sensitive to the hospital selected as the target. However, incorporating data from all hospitals consistently had the highest performance.

Discussion

The results characterize the challenges and opportunities that come with (1) using data or models from collections of hospitals without adapting them to the site at which the model will be used, and (2) using only local data to build models for small institutions or rare events.

Conclusions

We show how external data from other hospitals can be successfully and efficiently incorporated into hospital-specific models.     

Research and applications: Supervised machine learning and active learning in classification of radiology reports

Objective

This paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology reports for use in the Victorian Cancer Registry.

Materials and methods

In addition to traditional supervised learning methods such as conditional random fields and support vector machines, active learning (AL) approaches were investigated to optimize training production and further improve classification performance. The project involved two pilot sites in Victoria, Australia (Lake Imaging (Ballarat) and Peter MacCallum Cancer Centre (Melbourne)) and, in collaboration with the NSW Central Registry, one pilot site at Westmead Hospital (Sydney).

Results

The reportability classifier performance achieved 98.25% sensitivity and 96.14% specificity on the cancer registry''s held-out test set. Up to 92% of training data needed for supervised machine learning can be saved by AL.

Discussion

AL is a promising method for optimizing the supervised training production used in classification of radiology reports. When an AL strategy is applied during the data selection process, the cost of manual classification can be reduced significantly.

Conclusions

The most important practical application of the reportability classifier is that it can dramatically reduce human effort in identifying relevant reports from the large imaging pool for further investigation of cancer. The classifier is built on a large real-world dataset and can achieve high performance in filtering relevant reports to support cancer registries.     

The use of chicken legs for teaching wound closure skills

Objective

Training models are required to impart surgical skills, like wound closure techniques, prior to practice in patients. In an ideal case, the tissue characteristics of the model are close to those of humans, easy to create and of low cost.

Methods

Here, we describe a model to train students in wound closure technique using conventional chicken legs obtained from the supermarket.

Results

The described model has good tissue characteristics, does not require any lavish preparation and is of minimal cost (0.62 Euro or 0.78 USD).

Conclusions

Chicken legs appear to be an appropriate tool for teaching wound closure techniques.     

Research and applications: Machine learning for predicting the response of breast cancer to neoadjuvant chemotherapy

Objective

To employ machine learning methods to predict the eventual therapeutic response of breast cancer patients after a single cycle of neoadjuvant chemotherapy (NAC).

Materials and methods

Quantitative dynamic contrast-enhanced MRI and diffusion-weighted MRI data were acquired on 28 patients before and after one cycle of NAC. A total of 118 semiquantitative and quantitative parameters were derived from these data and combined with 11 clinical variables. We used Bayesian logistic regression in combination with feature selection using a machine learning framework for predictive model building.

Results

The best predictive models using feature selection obtained an area under the curve of 0.86 and an accuracy of 0.86, with a sensitivity of 0.88 and a specificity of 0.82.

Discussion

With the numerous options for NAC available, development of a method to predict response early in the course of therapy is needed. Unfortunately, by the time most patients are found not to be responding, their disease may no longer be surgically resectable, and this situation could be avoided by the development of techniques to assess response earlier in the treatment regimen. The method outlined here is one possible solution to this important clinical problem.

Conclusions

Predictive modeling approaches based on machine learning using readily available clinical and quantitative MRI data show promise in distinguishing breast cancer responders from non-responders after the first cycle of NAC.     

Governance for clinical decision support: case studies and recommended practices from leading institutions

Objective

Clinical decision support (CDS) is a powerful tool for improving healthcare quality and ensuring patient safety; however, effective implementation of CDS requires effective clinical and technical governance structures. The authors sought to determine the range and variety of these governance structures and identify a set of recommended practices through observational study.

Design

Three site visits were conducted at institutions across the USA to learn about CDS capabilities and processes from clinical, technical, and organizational perspectives. Based on the results of these visits, written questionnaires were sent to the three institutions visited and two additional sites. Together, these five organizations encompass a variety of academic and community hospitals as well as small and large ambulatory practices. These organizations use both commercially available and internally developed clinical information systems.

Measurements

Characteristics of clinical information systems and CDS systems used at each site as well as governance structures and content management approaches were identified through extensive field interviews and follow-up surveys.

Results

Six recommended practices were identified in the area of governance, and four were identified in the area of content management. Key similarities and differences between the organizations studied were also highlighted.

Conclusion

Each of the five sites studied contributed to the recommended practices presented in this paper for CDS governance. Since these strategies appear to be useful at a diverse range of institutions, they should be considered by any future implementers of decision support.     

Neurocognitive sequelae of cerebral malaria in adults: A pilot study in Benguela Central Hospital,Angola

Objective

To characterize the neurocognitive sequelae of cerebral malaria (CM) in an adult sample of the city of Benguela, Angola.

Methods

A neuropsychological assessment was carried out in 22 subjects with prior history of CM ranging from 6 to 12 months after the infection. The obtained results were compared to a control group with no previous history of cerebral malaria. The study was conducted in Benguela Central Hospital, Angola in 2011.

Results

CM group obtained lower results on the two last trials of a verbal learning task and on an abstract reasoning test.

Conclusions

CM is associated to a slower verbal learning rate and to difficulties in the ability to discriminate and perceive relations between new elements.     

Intrahepatic type II gall bladder perforation by a gall stone in a CAPD patient

Introduction

Perforation of the gall bladder represents a rare, but life-threatening complication of cholecystitis. Clinical presentation may vary between severe peritonism in acute perforation and absence of symptoms in subacute or chronic progression of perforation. Abdominal imaging like ultrasound or CT-scan are important tools for immediate diagnose of gall bladder perforation.

Case presentation

We report a case of a 30-year old female patient with end-stage kidney disease treated by continuous ambulatory peritoneal dialysis (CAPD) who was admitted to the emergency room with fever and mild abdominal pain. A type II gall bladder perforation by a solitary gall stone with development of a liver abscess was detected by abdominal ultrasound.

Conclusion

Gall bladder perforations are rare but have to be considered in patients with abdominal pain and fever. Abdominal ultrasound is a reliable tool to establish diagnosis.     

Automated concept-level information extraction to reduce the need for custom software and rules development

Objective

Despite at least 40 years of promising empirical performance, very few clinical natural language processing (NLP) or information extraction systems currently contribute to medical science or care. The authors address this gap by reducing the need for custom software and rules development with a graphical user interface-driven, highly generalizable approach to concept-level retrieval.

Materials and methods

A ‘learn by example’ approach combines features derived from open-source NLP pipelines with open-source machine learning classifiers to automatically and iteratively evaluate top-performing configurations. The Fourth i2b2/VA Shared Task Challenge''s concept extraction task provided the data sets and metrics used to evaluate performance.

Results

Top F-measure scores for each of the tasks were medical problems (0.83), treatments (0.82), and tests (0.83). Recall lagged precision in all experiments. Precision was near or above 0.90 in all tasks.

Discussion

With no customization for the tasks and less than 5 min of end-user time to configure and launch each experiment, the average F-measure was 0.83, one point behind the mean F-measure of the 22 entrants in the competition. Strong precision scores indicate the potential of applying the approach for more specific clinical information extraction tasks. There was not one best configuration, supporting an iterative approach to model creation.

Conclusion

Acceptable levels of performance can be achieved using fully automated and generalizable approaches to concept-level information extraction. The described implementation and related documentation is available for download.