Patient-specific Information Research Articles

Core functions of a financial navigation intervention: An in-depth assessment of the Lessening the Impact of Financial Toxicity (LIFT) intervention to inform adaptation and scale-up in diverse oncology care settings.

Lessening the Impact of Financial Toxicity (LIFT) is an intervention designed to address financial toxicity (FT) and improve cancer care access and outcomes through financial navigation (FN). FN identifies patients at risk for FT, assesses eligibility for financial support, and develops strategies to cope with those costs. LIFT successfully reduced FT and improved care access in a preliminary study among patients with high levels of FT in a single large academic cancer center. Adapting LIFT requires distinguishing between core functions (components that are key to its implementation and effectiveness) and forms (specific activities that carry out core functions). Our objective was to complete the first stage of adaptation, identifying LIFT core functions. We reviewed LIFT's protocol and internal standard-operating procedures. We then conducted 45-90 min in-depth interviews, using Kirk's method of identifying core functions, with key LIFT staff (N = 8), including the principal investigators. Interviews focused on participant roles and intervention implementation. Recorded interviews were transcribed verbatim. Using ATLAS.ti and a codebook based on the Model for Adaptation Design and Impact, we coded interview transcripts. Through thematic analysis, we then identified themes related to LIFT's intervention and implementation core functions. Two report back sessions with interview participants were incorporated to further refine themes. Six intervention core functions (i.e., what makes LIFT effective) and five implementation core functions (i.e., what facilitated LIFT's implementation) were identified to be sufficient to reduce FT. Intervention core functions included systematically cataloging knowledge and tracking patient-specific information related to eligibility criteria for FT relief. Repeat contacts between the financial navigator and participant created an ongoing relationship, removing common barriers to accessing resources. Implementation core functions included having engaged sites with the resources and willingness necessary to implement FN. Developing navigators' capabilities to implement LIFT-through training, an established case management system, and connections to peer navigators-were also identified as implementation core functions. This study adds to the growing evidence on FN by characterizing intervention and implementation core functions, a critical step toward promoting LIFT's implementation and effectiveness.

Abstract 12087: Improving Characterization of Abdominal Aortic Aneurysms by Modeling Thrombosis

Introduction: In seniors, the prevalence of abdominal aortic aneurysms (AAA) is high (9-10%). We aim to characterize AAA growth rates (slow vs. rapid) to help inform management strategies, including individualized imaging surveillance frequency. Hypothesis: Modeling thrombosis may improve the characterization of AAAs' growth status. Methods: 3D geometrical AAA models with and without thrombosis (vessel lumen only) were generated for 70 human subjects using available contrast-enhanced CTA data. AAA growth rates were categorized as slow (< 5 mm/year) or rapid (≥ 5 mm/year) based on serial imaging. Python scripts were used to calculate geometrical parameters (83) with and without thrombosis. Patient-specific relevant health information was retrieved through a review of medical records. Support vector machine (SVM), a well-established machine learning method, was run with 10-fold cross-validation (100 iterations) to assess the predictive accuracy. Results: Among 70 AAAs studied, the ratio between rapidly-growing and slowly-growing was nearly 1:2. The combination of antihypertensive medication, coronary artery disease, juxta-aneurysm aortic size, and five geometrical parameters quantifying the extent of thrombosis provided the best accuracy for AAA's growth status. The area under receiving operating curve (AUROC) was 0.85, and total accuracy was 0.81, with 57% and 93% of rapidly- and slowly-growing AAAs correctly identified, respectively. Excluding patients with aneurysm thrombus, the AUROC and accuracy in predicting rapidly-growing AAAs decreased to 0.82 and 48%, respectively. Conclusions: machine-learning-based predictive modeling appears feasible for characterizing AAA's growth rate status. Manual aortic image segmentation, required for data analytics, is labor-intensive (on average, 1 hour). Leveraging artificial intelligence-based segmentation methodology may provide an automated solution to improve workflow and feasibility.

Open Source Repository and Online Calculator of Prediction Models for Diagnosis and Prognosis in Oncology.

(1) Background: The main aim was to develop a prototype application that would serve as an open-source repository for a curated subset of predictive and prognostic models regarding oncology, and provide a user-friendly interface for the included models to allow online calculation. The focus of the application is on providing physicians and health professionals with patient-specific information regarding treatment plans, survival rates, and side effects for different expected treatments. (2) Methods: The primarily used models were the ones developed by our research group in the past. This selection was completed by a number of models, addressing the same cancer types but focusing on other outcomes that were selected based on a literature search in PubMed and Medline databases. All selected models were publicly available and had been validated TRIPOD (Transparent Reporting of studies on prediction models for Individual Prognosis Or Diagnosis) type 3 or 2b. (3) Results: The open source repository currently incorporates 18 models from different research groups, evaluated on datasets from different countries. Model types included logistic regression, Cox regression, and recursive partition analysis (decision trees). (4) Conclusions: An application was developed to enable physicians to complement their clinical judgment with user-friendly patient-specific predictions using models that have received internal/external validation. Additionally, this platform enables researchers to display their work, enhancing the use and exposure of their models.

A novel security framework for healthcare data through IOT sensors

The Internet of Things (IoT) has played a crucial role in the distribution of health records and poses security issues to the patient-specific health information needed for remote hospital attention. The majority of publicly accessible security mechanisms for health information do not concentrate on the flow of information from IoT different sensors installed upon the person's blood through networking devices to primary health care centers. In this paper, we investigated the potential risks of unprotected transmission data, particularly among IoT sensor systems and network gateways. The study encourages the transmission of health insurance data to hospitals remotely. The proposed health care information model would encode immediately so that the sensing element before even being transferred to cryptographic techniques. To use a laboratory configuration with two-stage cryptography at the IoT sensor and two-stage decoding at the physician's surgery receptor, the prototype system was validated. The test results for a complete safety system for IoT - based on the transmission of healthcare data seem good. The study opens up new avenues for information security on IoT devices.

Area Deprivation Index Is Associated with Quality of Life and Psychosocial Well-being after Breast Cancer Surgery

INTRODUCTION: Neighborhood-level factors have been shown to influence operative outcomes. To date, no study has been conducted to examine the relationship between area-level deprivation (ADI) and postmastectomy outcomes. METHODS: We conducted a cross-sectional survey of all adult female breast cancer patients who underwent lumpectomy or mastectomy between January 2018 and June 2019. Patient-specific demographics, clinical history, and ADI information were abstracted and correlated with postoperative global- (SF-12) and condition-specific (Breast-Q) quality-of-life performance via multivariable regression. Patients were classified into 3 groups based on their ADI scores: 0–39 (prosperous/comfortable), 40–59 (mid-tier), and 60–100 (at risk/distressed). RESULTS: A total of 564 consecutive patients were identified; mostly White (75%) with a mean age of 60.2 ± 12.4 years, mean BMI of 28.8±7.1, mean Charlson Comorbidity Index of 3.5±2.0, and mean ADI of 42.3±25.7. Minority patients and those with high BMI were more likely to reside in highly deprived neighborhoods (p = 0.003 and p < 0.001). In adjusted models, patients at risk/distressed had significantly lower mean SF-12 physical (44.9 [95% CI 43.8–46.0] vs 44.9 [95% CI 43.7–46.1] vs 46.3 [95% CI, 45.3-47.3], p = 0.03) and BREAST-Q psychosocial well-being scores (63.5 [95% CI 59.32–67.8] vs 69.3 [95% CI 65.1–73.6] vs 69.7 [95% CI 66.4–73.1], p = 0.01) than the mid-tier and prosperous/comfortable groups. CONCLUSION: Patients residing in deprived neighborhoods were more likely to have worse psychological well-being and quality of life. ADI should be incorporated in the shared-decision making process and perioperative counseling to engender value-based and personalized care, especially for vulnerable populations.

What are the ethical considerations of using video social media platforms such as TikTok in your dental practice?

What are the ethical considerations of using video social media platforms such as TikTok in your dental practice?

Development of a Semiautomated Database for Patients With Adult Congenital Heart Disease.

Databases for Congenital Heart Disease (CHD) are effective in delivering accessible datasets ready for statistical inference. Data collection hitherto has, however, been labour and time intensive and has required substantial financial support to ensure sustainability. We propose here creation and piloting of a semiautomated technique for data extraction from clinic letters to populate a clinical database. PDF formatted clinic letters stored in a local folder, through a series of algorithms, underwent data extraction, preprocessing, and analysis. Specific patient information (diagnoses, diagnostic complexity, interventions, arrhythmia, medications, and demographic data) was processed into text files and structured data tables, used to populate a database. A specific data validation schema was predefined to verify and accommodate the information populating the database. Unsupervised learning in the form of a dimensionality reduction technique was used to project data into 2 dimensions and visualize their intrinsic structure in relation to the diagnosis, medication, intervention, and European Society of Cardiology classification lists of disease complexity. Ninety-three randomly selected letters were reviewed manually for accuracy. There were 1409 consecutive outpatient clinic letters used to populate the Scottish Adult Congenital Cardiac Database. Mean patient age was 35.4 years; 47.6% female; with 698 (49.5%) having moderately complex, 369 (26.1%) greatly complex, and 284 (20.1%) mildly complex lesions. Individual diagnoses were successfully extracted in 96.95%, and demographic data were extracted in 100% of letters. Data extraction, database upload, data analysis and visualization took 571 seconds (9.51 minutes). Manual data extraction in the categories of diagnoses, intervention, and medications yielded accuracy of the computer algorithm in 94%, 93%, and 93%, respectively. Semiautomated data extraction from clinic letters into a database can be achieved successfully with a high degree of accuracy and efficiency.

Statistical Shape Model-Based Tibiofibular Assessment of Syndesmotic Ankle Lesions using Weightbearing CT

Category: Trauma; Ankle Introduction/Purpose: Forced external rotation is hypothesized as the key mechanism of syndesmotic ankle injuries, inducing a three-dimensional deviation from the normal distal tibiofibular joint alignment. These lesions, especially when subtle, present a deceitful diagnostic challenge. Current diagnostic imaging modalities are impeded by a two-dimensional assessment, without considering ligamentous stabilizers. Accurate diagnosis of syndesmotic lesions should involve 3D weightbearing osseous imaging in combination with - preferably automated- inclusion of patient-specific ligamentous information. Therefore, our aim is two-fold: (1) to construct a three-dimensional articulated statistical shape model of the normal distal tibiofibular joint with inclusion of ligamentous morphometry and (2) to detect differences in predicted syndesmotic ligament length of patients with syndesmotic lesions with respect to normative data. Methods: Training data comprised non-weightbearing CT scans from asymptomatic controls (N= 76, Mean age 63 +/- 19 years), weightbearing CT scans from patients with syndesmotic ankle injury (N = 13, Mean Age 35 +/- 15 years) and their weightbearing healthy contralateral side (N = 13). CT scan segmentation was used to generate 3D bone models in the control and patient group. All ankles were aligned based on the tibia. Path and length of the syndesmotic ligaments were predicted using a discrete element model, wrapped around bony contours. Statistical shape model evaluation was based on accuracy, generalization and compactness. The predicted ligament length in patients with syndesmotic lesions was compared to healthy controls by use of two-tailed Two- Sample student's t-test. Results: Our presented skeletal shape model described the training data with an accuracy of 0.23 +/- 0.028 mm. Mean prediction accuracy of ligament insertions was 0.53 +/- 0.12 mm. Mean length of the Anterior inferior tibiofibular ligament was 12.26 +- 1.89mm for the control cases, 12.32 +- 1.58 mm for the contralateral cases and 14.13 +- 1.48 mm for the cases with syndesmotic lesions. Statistically significant differences were found between the latter two (95% CI [ 0.323.29], p = 0.017) There was a significant correlation between presence of syndesmotic injury and the positional alignment between the distal tibia and fibula (r = 0.873, p &lt; 0,001). Conclusion: Statistical shape modelling combined with patient-specific ligament wrapping techniques can facilitate the diagnostic workup of syndesmotic ankle lesions under weightbearing conditions. In doing so, an increased anterior tibiofibular distance was detected, corresponding to an 'anterior open-book injury' of the ankle syndesmosis as a result of anterior inferior tibiofibular ligament elongation/rupture (Figure 1).

Physician Perspectives on Implementation of Real-Time Benefit Tools: A Qualitative Study.

Congress and Medicare have required real-time benefit tools (RTBT) to provide patient-specific medication price information during prescribing to decrease the cost of medications. We sought physicians' perspectives on how these tools might most effectively improve their selection of low-cost medication. We conducted 15 semi-structured interviews of physicians (6 oncologists, 1 endocrinologist, 4 rheumatologists, and 4 from internal medicine) and identified key themes across interviews during coding and analysis. Although physicians saw value in real-time medication price information, they were wary of the complexity of obtaining specific information and the potential for inaccuracies. Physicians described how medication price information would be used in various prescribing scenarios including from simple substitutions (different drug formulations) to more complex decisions (different drug classes). In more complex situations, physicians were concerned that price information might only be available after discussing options with the patient, which would be too late to inform decisions. Concern about adding more information to the electronic health record was common. While most physicians saw value in implementation of RTBTs, they also expressed concerns related to the accuracy of information, the availability of information at the right time in the clinical workflow, and the most effective format for information. Many concerns raised paralleled the "Five Rights of Clinical Decision Support" framework and indicate the need for additional design work to achieve benefit from RTBTs. Beyond the public policy that has supported the availability of RTBTs, substantial development will be required to ensure that information is used to improve prescribing decisions.

Experiences and challenges faced by patients with COVID-19 who were hospitalised and participated in a randomised controlled trial: a qualitative study

ObjectivesAs part of a randomised controlled trial, this qualitative study aimed to identify experiences and challenges of hospitalised patients with COVID-19 during illness and treatment (objective 1: COVID-19-related perspectives; objective...

Herbal medicine use in Thai patients with type 2 diabetes mellitus and its association with glycemic control: A cross-sectional evaluation

IntroductionHerbal medicine has been integrated into Thai culture for many centuries. However, studies on using herbal medicine in combination with antidiabetic agents for glycemic control in managing diabetes are limited. Herein, we aimed to assess the use of herbal medicines with different dosages of antidiabetic agents and their association with glycemic control in Thai patients with type 2 diabetes mellitus (T2DM). MethodsThis hospital-based study included 739 patients with T2DM who consecutively visited four district hospitals in Thailand. An interviewer-administered questionnaire was used to collect patient-specific information, including hemoglobin A1c (HbA1c) levels. Chi-square and logistic regression analyses were used to assess associations and predictors, respectively. ResultsThe prevalence of herbal medicine use was 37.5% (n = 264); 70.5% of the patients received information about herbal medicine usage for glycemic control from their relatives and friends, and 21 herbal plants were consumed in combination with their prescribed antidiabetic drugs. The use of herbal medicine was associated with the patients’ educational level (p = 0.001), income (p < 0.001), and duration of diabetes (p < 0.001). Good glycemic control (HbA1c < 7.0%) was associated with the use of bitter gourd in combination with 500 mg/day of the antidiabetic drug metformin (adjusted odds ratio = 8.33, 95% confidence interval = 1.04–66.49, p = 0.046). These patients were 2.92 times more likely to have good glycemic control than those who relied solely on 500 mg/day of metformin (adjusted OR = 2.921, 95% CI = 1.227–6.952, p = 0.015). ConclusionsThe prevalence of herbal plant use was associated with different variables, including age, BMI, T2DM duration, and metformin dosage. Among the 21 herbal plants, the consumption of bitter gourd with 500 mg/day of metformin was associated with good glycemic control.

Effective nursing shift handover in critical care: A concept analysis.

To explore the concept of effective shift handover in critical care settings.Ineffective handover is one of the leading causes of adverse events in healthcare settings. Nursing shift handover in the intensive care unit (ICU) is more complex and detailed than in other in-patient wards due to the complexity of medical issues experienced by ICU patients. It is, therefore, critical that nurses be able to conduct handover effectively. Despite the importance of handover, the definition and attributes of effective handover are not clearly understood.Walker and Avant's eight-step approach to concept analysis.Effective handover in nursing is an interactive process between two nurses, resulting in the direct transfer of adequate patient-specific recent information in a manner that creates a shared understanding of information. Its defining attributes are (1) content-related and (2) process-related attributes. The antecedents of effective handover are organizational support, interpersonal relationship, and work environment. Its consequences include patient and nurse satisfaction, improved care, and continuity of care. Empirical referents include several tools developed to measure some of the effective handover attributes.The definition provides a connotative meaning and is the first step toward concept validation and instrument development to measure effective handover practice in the ICU.

Real-time Prescription Benefit Tools—The Promise and Peril

This Invited Comentary considers the potential challenges and benefits of implementation of real-time benefit tools, which allow prescribers to have patient-specific drug pricing information at the point of prescribing, as they become more pervasive

Area Deprivation Index is Associated with Variation in Quality of Life and Psychosocial Well-being Following Breast Cancer Surgery.

Neighborhood-level factors have been shown to influence surgical outcomes through material deprivation, psychosocial mechanisms, health behaviors, and access to resources. To date, no study has examined the relationship between area-level deprivation (ADI) and post-mastectomy outcomes. A cross-sectional survey of adult female breast cancer patients who underwent lumpectomy or mastectomy between January 2018 to June 2019 was carried out. Patient-specific characteristics and ADI information were abstracted and correlated with postoperative global- (SF-12) and condition-specific (BREAST-Q) quality-of-life performance via multivariable regression. Patients were classified into three ADI terciles: 0-39 (low deprivation), 40-59 (moderate deprivation), and 60-100 (high deprivation). A total of 564 consecutive patients were identified, being mostly white (75%) with mean age of 60.2 ± 12.4 years, median body mass index of 27.8 [interquartile range (IQR) 24.3-32.2) kg/m2, median Charlson Comorbidity Index of 3 (IQR 2-5), and mean ADI of 42.3 ± 25.7. African American and Hispanic patients and those with high BMI were more likely to reside in highly deprived neighborhoods (p = 0.003 and p < 0.001). In adjusted models, patients in highly deprived neighborhoods had significantly lower mean SF-12 physical (44.9 [95% CI, 43.8-46.0] versus 44.9 [95% CI, 43.7-46.1] versus 46.3 [95% CI, 45.3-47.3], p = 0.03) and BREAST-Q psychosocial well-being scores (63.5 [95% CI, 59.32-67.8] versus 69.3 [95% CI, 65.1-73.6] versus 69.7 [95% CI, 66.4-73.1], p = 0.01) relative to moderate- and low-deprivation groups. Patients residing in the most deprived neighborhoods were identified to have worse psychological well-being and quality-of-life. The ADI should be incorporated into the shared decision-making process and perioperative counseling to engender value-based and personalized care, especially for vulnerable populations.

Understanding the role of community pharmacies in current medication for opioid use disorder care practices

BackgroundMany barriers for patient access to medications for opioid use disorder (MOUD) exist in current care practices. Previous literature has evaluated subsets of pharmacists, patients, and prescribers; however, few have collectively evaluated the perspectives of all 3 groups. ObjectiveThe objective of the study was to identify barriers, facilitators, and opportunities for improvement in Indiana community pharmacy MOUD care practices from the perspectives of peer recovery coaches, community pharmacists, and prescribers to optimize patient care. MethodsIndividual semistructured interviews were conducted with each participant. Interviews explored stakeholders’ perspectives on their current role in MOUD care practices and how current pharmacy practices could be improved. Data were analyzed using preconceived deductive and iterative inductive codes. The first author analyzed all transcripts, of which 3 were also analyzed separately by the last author to confirm consistent utilization of codes. All transcripts were coded once, followed by a second coding to ensure inductive codes were thoroughly applied. ResultsTen peer recovery coaches, 10 pharmacists, and 6 prescribers were included. Interviews identified barriers, facilitators, and opportunities for improvement in current MOUD care practices. Stigma was a major barrier identified by all groups. Other barriers identified included limited patient engagement at pharmacies and lack of access to patient-specific health information in community pharmacy settings. Pharmacists also identified additional barriers including Drug Enforcement Administration regulations and difficulties balancing patient care with external factors like insurance and legal policies. Positive prescriber/pharmacist relationships were identified as a facilitator of care. Opportunities for improvement included having community MOUD resource information available at pharmacies, further education on MOUD for pharmacists, and increased collaboration between pharmacists and prescribers. ConclusionMany barriers exist in current MOUD care practices. Additional pharmacist MOUD education and intentional collaboration between pharmacists, peer recovery coaches, and prescribers would facilitate better care and leverage the accessibility of pharmacists within their communities.

Prioritization of cancer driver gene with prize-collecting steiner tree by introducing an edge weighted strategy in the personalized gene interaction network

BackgroundCancer is a heterogeneous disease in which tumor genes cooperate as well as adapt and evolve to the changing conditions for individual patients. It is a meaningful task to discover the personalized cancer driver genes that can provide diagnosis and target drug for individual patients. However, most of existing methods mainly ranks potential personalized cancer driver genes by considering the patient-specific nodes information on the gene/protein interaction network. These methods ignore the personalized edge weight information in gene interaction network, leading to false positive results.ResultsIn this work, we presented a novel algorithm (called PDGPCS) to predict the Personalized cancer Driver Genes based on the Prize-Collecting Steiner tree model by considering the personalized edge weight information. PDGPCS first constructs the personalized weighted gene interaction network by integrating the personalized gene expression data and prior known gene/protein interaction network knowledge. Then the gene mutation data and pathway data are integrated to quantify the impact of each mutant gene on every dysregulated pathway with the prize-collecting Steiner tree model. Finally, according to the mutant gene’s aggregated impact score on all dysregulated pathways, the mutant genes are ranked for prioritizing the personalized cancer driver genes. Experimental results on four TCGA cancer datasets show that PDGPCS has better performance than other personalized driver gene prediction methods. In addition, we verified that the personalized edge weight of gene interaction network can improve the prediction performance.ConclusionsPDGPCS can more accurately identify the personalized driver genes and takes a step further toward personalized medicine and treatment. The source code of PDGPCS can be freely downloaded from https://github.com/NWPU-903PR/PDGPCS.

Radiation Oncology: Future Vision for Quality Assurance and Data Management in Clinical Trials and Translational Science.

The future of radiation oncology is exceptionally strong as we are increasingly involved in nearly all oncology disease sites due to extraordinary advances in radiation oncology treatment management platforms and improvements in treatment execution. Due to our technology and consistent accuracy, compressed radiation oncology treatment strategies are becoming more commonplace secondary to our ability to successfully treat tumor targets with increased normal tissue avoidance. In many disease sites including the central nervous system, pulmonary parenchyma, liver, and other areas, our service is redefining the standards of care. Targeting of disease has improved due to advances in tumor imaging and application of integrated imaging datasets into sophisticated planning systems which can optimize volume driven plans created by talented personnel. Treatment times have significantly decreased due to volume driven arc therapy and positioning is secured by real time imaging and optical tracking. Normal tissue exclusion has permitted compressed treatment schedules making treatment more convenient for the patient. These changes require additional study to further optimize care. Because data exchange worldwide have evolved through digital platforms and prisms, images and radiation datasets worldwide can be shared/reviewed on a same day basis using established de-identification and anonymization methods. Data storage post-trial completion can co-exist with digital pathomic and radiomic information in a single database coupled with patient specific outcome information and serve to move our translational science forward with nimble query elements and artificial intelligence to ask better questions of the data we collect and collate. This will be important moving forward to validate our process improvements at an enterprise level and support our science. We have to be thorough and complete in our data acquisition processes, however if we remain disciplined in our data management plan, our field can grow further and become more successful generating new standards of care from validated datasets.

A streak artifact reduction algorithm in sparse-view CT using a self-supervised neural representation.

Sparse-view computed tomography (CT) has been attracting attention for its reduced radiation dose and scanning time. However, analytical image reconstruction methods suffer from streak artifacts due to insufficient projection views. Recently, various deep learning-based methods have been developed to solve this ill-posed inverse problem. Despite their promising results, they are easily overfitted to the training data, showing limited generalizability to unseen systems and patients. In this work, we propose a novel streak artifact reduction algorithm that provides a system- and patient-specificsolution. Motivated by the fact that streak artifacts are deterministic errors, we regenerate the same artifacts from a prior CT image under the same system geometry. This prior image need not be perfect but should contain patient-specific information and be consistent with full-view projection data for accurate regeneration of the artifacts. To this end, we use a coordinate-based neural representation that often causes image blur but can greatly suppress the streak artifacts while having multiview consistency. By employing techniques in neural radiance fields originally proposed for scene representations, the neural representation is optimized to the measured sparse-view projection data via self-supervised learning. Then, we subtract the regenerated artifacts from the analytically reconstructed original image to obtain the final correctedimage. To validate the proposed method, we used simulated data of extended cardiac-torso phantoms and the 2016 NIH-AAPM-Mayo Clinic Low-Dose CT Grand Challenge and experimental data of physical pediatric and head phantoms. The performance of the proposed method was compared with a total variation-based iterative reconstruction method, naive application of the neural representation, and a convolutional neural network-based method. In visual inspection, it was observed that the small anatomical features were best preserved by the proposed method. The proposed method also achieved the best scores in the visual information fidelity, modulation transfer function, and lung nodulesegmentation. The results on both simulated and experimental data suggest that the proposed method can effectively reduce the streak artifacts while preserving small anatomical structures that are easily blurred or replaced with misleading features by the existing methods. Since the proposed method does not require any additional training datasets, it would be useful in clinical practice where the large datasets cannot becollected.

NeuroSAFE PROOF: study protocol for a single-blinded, IDEAL stage 3, multi-centre, randomised controlled trial of NeuroSAFE robotic-assisted radical prostatectomy versus standard robotic-assisted radical prostatectomy in men with localized prostate cancer

BackgroundRobotic radical prostatectomy (RARP) is a first-line curative treatment option for localized prostate cancer. Postoperative erectile dysfunction and urinary incontinence are common associated adverse side effects that can negatively impact patients’ quality of life. Preserving the lateral neurovascular bundles (NS) during RARP improves functional outcomes. However, selecting men for NS may be difficult when there is concern about incurring in positive surgical margin (PSM) which in turn risks adverse oncological outcomes. The NeuroSAFE technique (intra-operative frozen section examination of the neurovascular structure adjacent prostate margin) can provide real-time pathological consult to promote optimal NS whilst avoiding PSM.MethodsNeuroSAFE PROOF is a single-blinded, multi-centre, randomised controlled trial (RCT) in which men are randomly allocated 1:1 to either NeuroSAFE RARP or standard RARP. Men electing for RARP as primary treatment, who are continent and have good baseline erectile function (EF), defined by International Index of Erectile Function (IIEF-5) score > 21, are eligible. NS in the intervention arm is guided by the NeuroSAFE technique. NS in the standard arm is based on standard of care, i.e. a pre-operative image-based planning meeting, patient-specific clinical information, and digital rectal examination. The primary outcome is assessment of EF at 12 months. The primary endpoint is the proportion of men who achieve IIEF-5 score ≥ 21. A sample size of 404 was calculated to give a power of 90% to detect a difference of 14% between groups based on a feasibility study. Oncological outcomes are continuously monitored by an independent Data Monitoring Committee. Key secondary outcomes include urinary continence at 3 months assessed by the international consultation on incontinence questionnaire, rate of biochemical recurrence, EF recovery at 24 months, and difference in quality of life.DiscussionNeuroSAFE PROOF is the first RCT of intra-operative frozen section during radical prostatectomy in the world. It is properly powered to evaluate a difference in the recovery of EF for men undergoing RARP assessed by patient-reported outcome measures. It will provide evidence to guide the use of the NeuroSAFE technique around the world.Trial registrationNCT03317990 (23 October 2017). Regional Ethics Committee; reference 17/LO/1978.

Prediction of progression rate and fate of osteoarthritis: Comparison of machine learning algorithms.

Appropriate prediction models can assist healthcare systems in delaying or reversing osteoarthritis (OA) progression. We aimed to identify a reliable algorithm for predicting the progression rate and fate of OA based on patient-specific information. From May 2003 to 2019, 83,280 knees were collected. Age, sex, body mass index, bone mineral density, physical demands for occupation, comorbidities, and initial Kellgren-Lawrence (K-L) grade were used as variables for the prediction models. The prediction targets were divided into dichotomous groups for even distribution. We compared the performances of logistic regression (LR), random forest (RF), and extreme gradient boost (XGB) algorithms. Each algorithm had the best precision when the model used all variables. XGB showed the best results in accuracy, recall, F1 score, specificity, and error rates (progression rate/fate of OA: 0.710/0.877, 0.542/0.637, 0.637/0.758, 0.859/0.981, and 0.290/0.123, respectively). The feature importance of RF and XGB had the same order up to the top six for each prediction target. Age and initial K-L grade had the highest feature importance in RF and XGB for the progression rate and fate of OA, respectively. The XGB and RF machine learning algorithms showed better performance than conventional LR in predicting the progression rate and fate of OA. The best performance was obtained when all variables were combined using the XGB algorithm. For each algorithm, the initial K-L grade and physical demand for occupation were the greatest contributors with superior feature importance compared with the others.