Operating Room Usage Time Estimation with Machine Learning Models.

Effectively handling the limited number of surgery operating rooms equipped with expensive equipment is a challenging task for hospital management such as reducing the case-time duration and reducing idle time. Improving the efficiency of operating room usage via reducing the idle time with better scheduling would rely on accurate estimation of surgery duration. Our model can achieve a good prediction result on surgery duration with a dozen of features. We have found the result of our best performing department-specific XGBoost model with the values 31.6 min, 18.71 min, 0.71, 28% and 27% for the metrics of root-mean-square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), mean absolute percentage error (MAPE) and proportion of estimated result within 10% variation, respectively. We have presented each department-specific result with our estimated results between 5 and 10 min deviation would be more informative to the users in the real application. Our study shows comparable performance with previous studies, and the machine learning methods use fewer features that are better suited for universal usability.

Breast cancer recurrence prediction with ensemble methods and cost-sensitive learning.

Breast cancer is one of the most common cancers in women all over the world. Due to the improvement of medical treatments, most of the breast cancer patients would be in remission. However, the patients have to face the next challenge, the recurrence of breast cancer which may cause more severe effects, and even death. The prediction of breast cancer recurrence is crucial for reducing mortality. This paper proposes a prediction model for the recurrence of breast cancer based on clinical nominal and numeric features. In this study, our data consist of 1,061 patients from Breast Cancer Registry from Shin Kong Wu Ho-Su Memorial Hospital between 2011 and 2016, in which 37 records are denoted as breast cancer recurrence. Each record has 85 features. Our approach consists of three stages. First, we perform data preprocessing and feature selection techniques to consolidate the dataset. Among all features, six features are identified for further processing in the following stages. Next, we apply resampling techniques to resolve the issue of class imbalance. Finally, we construct two classifiers, AdaBoost and cost-sensitive learning, to predict the risk of recurrence and carry out the performance evaluation in three-fold cross-validation. By applying the AdaBoost method, we achieve accuracy of 0.973 and sensitivity of 0.675. By combining the AdaBoost and cost-sensitive method of our model, we achieve a reasonable accuracy of 0.468 and substantially high sensitivity of 0.947 which guarantee almost no false dismissal. Our model can be used as a supporting tool in the setting and evaluation of the follow-up visit for early intervention and more advanced treatments to lower cancer mortality.

Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records.

The International Statistical Classification of Disease and Related Health Problems (ICD) is an international standard system for categorizing and reporting diseases, injuries, disorders, and health conditions. Most previously-proposed disease predicting systems need clinical information collected by the medical staff from the patients in hospitals. In this paper, we propose a deep learning algorithm to classify disease types and identify diagnostic codes by using only the subjective component of progress notes in medical records. In this study, we have a dataset, consisting of about one hundred and sixty-eight thousand medical records, from a medical center, collected during 2003 and 2017. First, we apply standard text processing procedures to parse the sentences and word embedding techniques for vector representations. Next, we build a convolution neural network model on the medical records to predict the ICD-9 code by using a subjective component of the progress note. The prediction performance is evaluated by ten-fold cross-validation and yields an accuracy of 0.409, recall of 0.409 and precision of 0.436. If we only consider the "chapter match" of ICD-9 code, our model achieves an accuracy of 0.580, recall of 0.580, and precision of 0.582. Since our diagnostic code prediction model is solely based on subjective components (mainly, patients' self-report descriptions), the proposed approach could serve as a remote and self-diagnosis assistance tool, prior to seeking medical advice or going to the hospital. In addition, our work may be used as a primary evaluation tool for discomfort in the rural area where medical resources are restricted.

Digitizing abdominal palpation with a pressure measurement and positioning device.

An abdominal physical examination is one of the most important tools in evaluating patients with acute abdominal pain. We focused on palpation, in which assessment is made according to the patient's response and force feedback. Since palpation is performed manually by the examiner, the uniformity of force and location is difficult to achieve during examinations. We propose an integrated system to quantify palpation pressure and location. A force sensor continuously collects pressure data, while a camera locates the precise position of contact. The system recorded, displayed average and maximum pressure by creating a pressure/time curve for computer-aided diagnosis. Compared with previous work on pressure sensors of quantifying abdominal palpation, our proposed system is the integrated approach to measure palpation force and track the corresponding position at the same time, for further diagnosis. In addition, we only make use of a sensing device and a general web camera, rather than commercial algometry and infrared cameras used in the previous work. Based on our clinical trials, the statistics of palpation pressure values and the corresponding findings are also reported. We performed abdominal palpation with our system for twenty-three healthy participants, including fourteen males and nine females. We applied two grades of force on the abdomen (light and deep) by four-quadrant and nine-region schemes, record the value of pressure and location. In the four-quadrant scheme, the average pressures of abdominal palpation with light and deep force levels were 0.506(N) and 0.552(N), respectively. In the nine-region scheme, the average pressures were 0.496(N) and 0.577(N), respectively. Two episodes of contact dermal reaction were identified. According to our experiment statistics, there is no significant difference in the force level between the four-quadrant and nine-region scheme. Our results have the potential to be used as a reference guide while designing digital abdominal palpation devices.

Serum Glutamine Levels as a Potential Diagnostic Biomarker in Sepsis following Surgery for Peritonitis.

Few diagnostic biomarkers for sepsis after emergency peritonitis surgery are available to clinicians, and, thus, it is important to develop new biomarkers for patients undergoing this procedure. We investigated whether serum glutamine and selenium levels could be diagnostic biomarkers of sepsis in individuals recovering from emergency peritonitis surgery. From February 2012 to March 2013, patients who had peritonitis diagnosed at the emergency department and underwent emergency surgery were screened for eligibility. Serum glutamine and selenium levels were obtained at pre-operative, post-operative and recovery time points. The average level of pre-operation serum glutamine was significantly different from that on the recovery day (0.317 ± 0.168 vs. 0.532 ± 0.155 mM, P < 0.001); moreover, serum glutamine levels were unaffected by surgery. Selenium levels were significantly lower on the day of surgery than they were at recovery (106.6 ± 36.39 vs. 130.68 ± 56.98 ng/mL, P = 0.013); no significant difference was found between pre-operation and recovery selenium levels. Unlike selenium, glutamine could be a sepsis biomarker for individuals with peritonitis. We recommend including glutamine as a biomarker for sepsis severity assessment in addition to the commonly used clinical indicators.

Viral warts (Human Papilloma Virus) as a potential risk for breast cancer among younger females.

INTRODUCTION: There have been several reports on the role of human papillomavirus (HPV) in the etiology of breast cancer. To our knowledge, this is first study to use disease-disease association data-mining approach to analyzing viral warts and breast cancer to be conducted in Taiwanese population. MATERIALS AND METHODS: We analyzed the Taiwan's National Health Insurance database (NHIDM data comprising of 23 million patient data) to examine the association between viral warts and female breast carcinoma. The patients were categorized into three groups: breast cancer only, viral warts only, and those with both breast cancer and viral warts. The Cox proportion hazard regression analysis was used to measure the effect of HPV on the time to breast cancer diagnosis. Multivariable analyzes and stratified analyzes using hazard ratios (HRs) were presented with 95% confidence intervals (CIs) after adjusting for age, and CCI. RESULT: Among 807,578 HPV population, we identified 6014 breast cancer cases. The HPV group was associated with a significantly higher risk of developing breast cancer (HR, 1.18; 95% CI, 1.15-1.21; p< 0.001) compared with the non-HPV group. HPV patients with age group 18-39 was slightly higher risk of breast cancer occurrence (HR, 1.07; 95% CI, 1.01-1.13; p<.05). The risk of breast cancer in 10-year incidence was 7% higher for females less than 40 years and 23% for over 40 year's patients when compared with non-HPV patients of the same age group. CONCLUSION: Our study indicates that women who develop viral warts are at a significantly higher risk of developing breast cancer than women who have not diagnosed with viral warts. Thus, the presence of viral warts is a potential risk to breast cancer. Therefore, we suggest patients diagnosed with viral warts may get early screening for breast cancer.

Applying under-sampling techniques and cost-sensitive learning methods on risk assessment of breast cancer.

Breast cancer is one of the most common cause of cancer mortality. Early detection through mammography screening could significantly reduce mortality from breast cancer. However, most of screening methods may consume large amount of resources. We propose a computational model, which is solely based on personal health information, for breast cancer risk assessment. Our model can be served as a pre-screening program in the low-cost setting. In our study, the data set, consisting of 3976 records, is collected from Taipei City Hospital starting from 2008.1.1 to 2008.12.31. Based on the dataset, we first apply the sampling techniques and dimension reduction method to preprocess the testing data. Then, we construct various kinds of classifiers (including basic classifiers, ensemble methods, and cost-sensitive methods) to predict the risk. The cost-sensitive method with random forest classifier is able to achieve recall (or sensitivity) as 100 %. At the recall of 100 %, the precision (positive predictive value, PPV), and specificity of cost-sensitive method with random forest classifier was 2.9 % and 14.87 %, respectively. In our study, we build a breast cancer risk assessment model by using the data mining techniques. Our model has the potential to be served as an assisting tool in the breast cancer screening.

Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks.

BACKGROUND: Diagnosing acute appendicitis clinically is still difficult. We developed random forests, support vector machines, and artificial neural network models to diagnose acute appendicitis. METHODS: Between January 2006 and December 2008, patients who had a consultation session with surgeons for suspected acute appendicitis were enrolled. Seventy-five percent of the data set was used to construct models including random forest, support vector machines, artificial neural networks, and logistic regression. Twenty-five percent of the data set was withheld to evaluate model performance. The area under the receiver operating characteristic curve (AUC) was used to evaluate performance, which was compared with that of the Alvarado score. RESULTS: Data from a total of 180 patients were collected, 135 used for training and 45 for testing. The mean age of patients was 39.4 years (range, 16-85). Final diagnosis revealed 115 patients with and 65 without appendicitis. The AUC of random forest, support vector machines, artificial neural networks, logistic regression, and Alvarado was 0.98, 0.96, 0.91, 0.87, and 0.77, respectively. The sensitivity, specificity, positive, and negative predictive values of random forest were 94%, 100%, 100%, and 87%, respectively. Random forest performed better than artificial neural networks, logistic regression, and Alvarado. CONCLUSION: We demonstrated that random forest can predict acute appendicitis with good accuracy and, deployed appropriately, can be an effective tool in clinical decision making.