Predicting quality of life after breast cancer surgery using ANN-based models: performance comparison with MR

Using machine learning to predict health-related quality of life outcomes in patients with low grade glioma, meningioma, and acoustic neuroma

Background

Predicting reduced health-related quality of life (HRQoL) after resection of a benign or low-grade brain tumour provides the opportunity for early intervention, and targeted expenditure of scarce supportive care resources. We aimed to develop, and evaluate the performance of, machine learning (ML) algorithms to predict HRQoL outcomes in this patient group.

Methods

Using a large prospective dataset of HRQoL outcomes in patients surgically treated for low grade glioma, acoustic neuroma and meningioma, we investigated the capability of ML to predict a) HRQoL-impacting symptoms persisting between 12 and 60 months from tumour resection and b) a decline in global HRQoL by more than the minimum clinically important difference below a normative population mean within 12 and 60 months after resection. Ten-fold cross-validation was used to measure the area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (PR-AUC), sensitivity, and specificity of models. Six ML algorithms were explored per outcome: Random Forest Classifier, Decision Tree Classifier, Logistic Regression, K Neighbours Classifier, Support Vector Machine, and Gradient Boosting Machine.

Results

The final cohort included 262 patients. Outcome measures for which AUC>0.9 were Appetite loss, Constipation, Nausea and vomiting, Diarrhoea, Dyspnoea and Fatigue. AUC was between 0.8 and 0.9 for global HRQoL and Financial difficulty. Pain and Insomnia achieved AUCs below 0.8. PR-AUCs were similar overall to the AUC of each respective classifier.

Conclusions

ML algorithms based on routine demographic and perioperative data show promise in their ability to predict HRQoL outcomes in patients with low grade and benign brain tumours between 12 and 60 months after surgery.

A Proposed Multi-Criteria Optimization Approach to Enhance Clinical Outcomes Evaluation for Diabetes Care: A Commentary

There are several challenges in diabetes care management including optimizing the currently used therapies, educating patients on selfmanagement, and improving patient lifestyle and systematic healthcare barriers. The purpose of performing a systems approach to implementation science aided by artificial intelligence techniques in diabetes care is two-fold: 1) to explicate the systems approach to formulate predictive analytics that will simultaneously consider multiple input and output variables to generate an ideal decision-making solution for an optimal outcome; and 2) to incorporate contextual and ecological variations in practicing diabetes care coupled with specific health educational interventions as exogenous variables in prediction. A similar taxonomy of modeling approaches proposed by Brennon et al (2006) is formulated to examining the determinants of diabetes care outcomes in program evaluation. The discipline-free methods used in implementation science research, applied to efficiency and quality-of-care analysis are presented. Finally, we illustrate a logically formulated predictive analytics with efficiency and quality criteria included for evaluation of behavioralchange intervention programs, with the time effect included, in diabetes care and research.

Self-reported physical functional health predicts future bone mineral density in EPIC-Norfolk cohort

Using a large population sample from the UK, we found that self-reported physical functional health may be used to predict future bone mineral density especially in women. It may be a useful and inexpensive way to identify individuals before further decline in bone mineral density and the risk of fracture.

PURPOSE

Self-reported physical functional health may predict bone mineral density (BMD) and thus provide a method to identify people at risk of low BMD. In this study, the association between the 36-item short-form questionnaire (SF-36) physical component summary (PCS) score and future BMD in participants aged 40-79 years enrolled in the European Prospective Investigation of Cancer-Norfolk study was investigated.

METHODS

Associations between a participant's SF-36 PCS score, measured 18 months after baseline health check, and broadband ultrasound attenuation (BUA-a measure of BMD), measured 2-5 years after baseline, were examined using sex-specific linear and logistic regression analyses adjusting for age, BMI, medical co-morbidities, lifestyle and socioeconomic factors.

RESULTS

Data from 10,203 participants, mean (standard deviation (SD)) age 61.5 (8.9) years (57.4% women), were analysed from 1993 to 2000. For every five points lower PCS score in men and women, there was approximately a 0.5 dB/MHz lower mean BUA. In women, a PCS score of less than one standard deviation (1SD) below the sex-specific mean was associated with having a low BUA (< 1SD below sex-specific mean) and very low BUA (< 2.5SD below the sex specific mean); odds ratio (OR) (95% confidence interval) 1.53 (1.24, 1.88) and 8.28 (2.67, 25.69), respectively. The relationship was lesser so in men; corresponding OR (95% CI) were 1.34 (0.91, 1.98) and 2.57 (0.72, 9.20), respectively.

CONCLUSIONS

Self-reported physical functioning predicts BMD in an apparently healthy population, particularly in women. This could potentially provide an inexpensive, simple screening tool to identify individuals at risk of osteoporosis.

Modern perioperative medicine - past, present, and future

Modern perioperative medicine has dramatically altered the care for patients undergoing major surgery. Anaesthetic and surgical practice has been directed at mitigating the surgical stress response and reducing physiological insult. The development of standardised enhanced recovery programmes combined with minimally invasive surgical techniques has lead to reduction in length of stay, morbidity, costs, and improved outcomes. The enhanced recovery after surgery (ERAS) society and its national chapters provide a means for sharing best practice in this field and developing evidence based guidelines. Research has highlighted persisting challenges with compliance as well as ensuring the effectiveness and sustainability of ERAS. There is also a growing need for increasingly personalised care programmes as well as complex geriatric assessment of frailer patients. Continuous collection of outcome and process data combined with machine learning, offers a potentially powerful solution to delivering bespoke care pathways and optimising individual management. Long-term data from ERAS programmes remain scarce and further evaluation of functional recovery and quality of life is required.

Predicting centre of mass horizontal speed in low to severe swimming intensities with linear and non-linear models

We aimed to compare multilayer perceptron (MLP) neural networks, radial basis function neural networks (RBF) and linear models (LM) accuracy to predict the centre of mass (CM) horizontal speed at low-moderate, heavy and severe swimming intensities using physiological and biomechanical dataset. Ten trained male swimmers completed a 7 × 200 m front crawl protocol (0.05 m.s^-1 increments and 30 s intervals) to assess expiratory gases and blood lactate concentrations. Two surface and four underwater cameras recorded independent images subsequently processed focusing a three-dimensional reconstruction of two upper limb cycles at 25 and 175 m laps. Eight physiological and 13 biomechanical variables were inputted to predict CM horizontal speed. MLP, RBF and LM were implemented with the Levenberg-Marquardt algorithm (feed forward with a six-neuron hidden layer), orthogonal least squares algorithm and decomposition of matrices. MLP revealed higher prediction error than LM at low-moderate intensity (2.43 ± 1.44 and 1.67 ± 0.60%), MLP and RBF depicted lower mean absolute percentage errors than LM at heavy intensity (2.45 ± 1.61, 1.82 ± 0.92 and 3.72 ± 1.67%) and RBF neural networks registered lower errors than MLP and LM at severe intensity (2.78 ± 0.96, 3.89 ± 1.78 and 4.47 ± 2.36%). Artificial neural networks are suitable for speed model-fit at heavy and severe swimming intensities when considering physiological and biomechanical background.

Comparison of Models for Predicting Quality of Life After Surgical Resection of Hepatocellular Carcinoma: a Prospective Study

BACKGROUND

The essential issue of internal validity has not been adequately addressed in prediction models such as artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR), and multiple linear regression (MLR) models.

METHODS

This prospective study compared the accuracy of these four models in predicting quality of life (QOL) after hepatic resection received by 332 patients with hepatocellular carcinoma (HCC) during 2012-2015. An estimation subset was used to train the models, and a validation subset was used to evaluate their performance. Sensitivity score approach was also used to assess the relative significance of input parameters in the system models.

RESULTS

The ANN model had significantly higher performance indicators compared to the SVM, GPR, and MLR models (P < 0.05). Additionally, the ANN prediction of QOL at 6 months after hepatic resection significantly correlated with age, gender, marital status, Charlson comorbidity index (CCI) score, chemotherapy, radiotherapy, hospital volume, surgeon volume, and preoperational functional status (P < 0.05). Preoperational functional status was the most influential (sensitive) variable affecting sixth-month QOL followed by surgeon volume, hospital volume, age, and CCI score.

CONCLUSIONS

The comparisons showed that, in preoperative and postoperative healthcare consultations with HCC surgery candidates, QOL at 6 months post-surgery should be estimated with an ANN model rather than with SVM, GPR, or MLR models. The best QOL predictors identified in this study can also be used to educate candidates for HCC surgery in the expected course of recovery and other surgical outcomes.

Modelling and Predicting Backstroke Start Performance Using Non-Linear and Linear Models

Our aim was to compare non-linear and linear mathematical model responses for backstroke start performance prediction. Ten swimmers randomly completed eight 15 m backstroke starts with feet over the wedge, four with hands on the highest horizontal and four on the vertical handgrip. Swimmers were videotaped using a dual media camera set-up, with the starts being performed over an instrumented block with four force plates. Artificial neural networks were applied to predict 5 m start time using kinematic and kinetic variables and to determine the accuracy of the mean absolute percentage error. Artificial neural networks predicted start time more robustly than the linear model with respect to changing training to the validation dataset for the vertical handgrip (3.95 ± 1.67 vs. 5.92 ± 3.27%). Artificial neural networks obtained a smaller mean absolute percentage error than the linear model in the horizontal (0.43 ± 0.19 vs. 0.98 ± 0.19%) and vertical handgrip (0.45 ± 0.19 vs. 1.38 ± 0.30%) using all input data. The best artificial neural network validation revealed a smaller mean absolute error than the linear model for the horizontal (0.007 vs. 0.04 s) and vertical handgrip (0.01 vs. 0.03 s). Artificial neural networks should be used for backstroke 5 m start time prediction due to the quite small differences among the elite level performances.

Cloud-Based Service Information System for Evaluating Quality of Life after Breast Cancer Surgery

Objective

Although recent studies have improved understanding of quality of life (QOL) outcomes of breast conserving surgery, few have used longitudinal data for more than two time points, and few have examined predictors of QOL over two years. Additionally, the longitudinal data analyses in such studies rarely apply the appropriate statistical methodology to control for censoring and inter-correlations arising from repeated measures obtained from the same patient pool. This study evaluated an internet-based system for measuring longitudinal changes in QOL and developed a cloud-based system for managing patients after breast conserving surgery.

Methods

This prospective study analyzed 657 breast cancer patients treated at three tertiary academic hospitals. Related hospital personnel such as surgeons and other healthcare professionals were also interviewed to determine the requirements for an effective cloud-based system for surveying QOL in breast cancer patients. All patients completed the SF-36, Quality of Life Questionnaire (QLQ-C30) and its supplementary breast cancer measure (QLQ-BR23) at baseline, 6 months, 1 year, and 2 years postoperatively. The 95% confidence intervals for differences in responsiveness estimates were derived by bootstrap estimation. Scores derived by these instruments were interpreted by generalized estimating equation before and after surgery.

Results

All breast cancer surgery patients had significantly improved QLQ-C30 and QLQ-BR23 subscale scores throughout the 2-year follow-up period (p<0.05). During the study period, QOL generally had a negative association with advanced age, high Charlson comorbidity index score, tumor stage III or IV, previous chemotherapy, and long post-operative LOS. Conversely, QOL was positively associated with previous radiotherapy and hormone therapy. Additionally, patients with high scores for preoperative QOL tended to have high scores for QLQ-C30, QLQ-BR23 and SF-36 subscales. Based on the results of usability testing, the five constructs were rated on a Likert scale from 1–7 as follows: system usefulness (5.6±1.8), ease of use (5.6±1.5), information quality (5.4±1.4), interface quality (5.5±1.4), and overall satisfaction (5.5±1.6).

Conclusions

The current trend in clinical medicine is applying therapies and interventions that improve QOL. Therefore, a potentially vast amount of internet-based QOL data is available for use in defining patient populations that may benefit from therapeutic intervention. Additionally, before undergoing breast conserving surgery, patients should be advised that their postoperative QOL depends not only on the success of the surgery, but also on their preoperative functional status.

The use of artificial neural networks to predict delayed discharge and readmission in enhanced recovery following laparoscopic colorectal cancer surgery

BACKGROUND

Artificial neural networks (ANNs) can be used to develop predictive tools to enable the clinical decision-making process. This study aimed to investigate the use of an ANN in predicting the outcomes from enhanced recovery after colorectal cancer surgery.

METHODS

Data were obtained from consecutive colorectal cancer patients undergoing laparoscopic surgery within the enhanced recovery after surgery (ERAS) program between 2002 and 2009 in a single center. The primary outcomes assessed were delayed discharge and readmission within a 30-day period. The data were analyzed using a multilayered perceptron neural network (MLPNN), and a prediction tools were created for each outcome. The results were compared with a conventional statistical method using logistic regression analysis.

RESULTS

A total of 275 cancer patients were included in the study. The median length of stay was 6 days (range 2-49 days) with 67 patients (24.4 %) staying longer than 7 days. Thirty-four patients (12.5 %) were readmitted within 30 days. Important factors predicting delayed discharge were related to failure in compliance with ERAS, particularly with the postoperative elements in the first 48 h. The MLPNN for delayed discharge had an area under a receiver operator characteristic curve (AUROC) of 0.817, compared with an AUROC of 0.807 for the predictive tool developed from logistic regression analysis. Factors predicting 30-day readmission included overall compliance with the ERAS pathway and receiving neoadjuvant treatment for rectal cancer. The MLPNN for readmission had an AUROC of 0.68.

CONCLUSIONS

These results may plausibly suggest that ANN can be used to develop reliable outcome predictive tools in multifactorial intervention such as ERAS. Compliance with ERAS can reliably predict both delayed discharge and 30-day readmission following laparoscopic colorectal cancer surgery.

Breast cancer in young women: special considerations in multidisciplinary care

Breast cancer is one of the most prevalent cancers in females, and 5%-7% of breast cancer cases occur in women under 40 years of age. Breast cancer in the young has gained increased attention with an attempt to improve diagnosis and prognosis. Young patients tend to have different epidemiology, presenting with later stages and more aggressive phenotypes. Diagnostic imaging is also more difficult in this age group. Multidisciplinary care generally encompasses surgeons, medical oncologists, radiation oncologists, radiologists, and social workers. Other special considerations include reconstruction options, fertility, genetics, and psychosocial issues. These concerns enlarge the already diverse multidisciplinary team to incorporate new expertise, such as reproductive specialists and genetic counselors. This review encompasses an overview of the current multimodal treatment regimens and the unique challenges in treating this special population. Integration of diagnosis, treatment, and quality of life issues should be addressed and understood by each member in the interdisciplinary team in order to optimize outcomes.