scholarly journals The application of machine learning to balance a total knee arthroplasty

2020 ◽  
Vol 1 (6) ◽  
pp. 236-244 ◽  
Author(s):  
Matthias A. Verstraete ◽  
Ryan E. Moore ◽  
Martin Roche ◽  
Michael A. Conditt
Keyword(s):  
Machine Learning ◽  
Decision Process ◽  
Sagittal Plane ◽  
New Technology ◽  
Numerical Data ◽  
Supervised Machine Learning ◽  
Patient Specific ◽  
Surgical Decision ◽  
Clinical Series ◽  
Total Knee

Aims The use of technology to assess balance and alignment during total knee surgery can provide an overload of numerical data to the surgeon. Meanwhile, this quantification holds the potential to clarify and guide the surgeon through the surgical decision process when selecting the appropriate bone recut or soft tissue adjustment when balancing a total knee. Therefore, this paper evaluates the potential of deploying supervised machine learning (ML) models to select a surgical correction based on patient-specific intra-operative assessments. Methods Based on a clinical series of 479 primary total knees and 1,305 associated surgical decisions, various ML models were developed. These models identified the indicated surgical decision based on available, intra-operative alignment, and tibiofemoral load data. Results With an associated area under the receiver-operator curve ranging between 0.75 and 0.98, the optimized ML models resulted in good to excellent predictions. The best performing model used a random forest approach while considering both alignment and intra-articular load readings. Conclusion The presented model has the potential to make experience available to surgeons adopting new technology, bringing expert opinion in their operating theatre, but also provides insight in the surgical decision process. More specifically, these promising outcomes indicated the relevance of considering the overall limb alignment in the coronal and sagittal plane to identify the appropriate surgical decision.

scholarly journals The application of machine learning to balance a total knee arthroplasty

2020 ◽  
Vol 1 (6) ◽  
pp. 236-244
Author(s):  
Matthias A. Verstraete ◽  
Ryan E. Moore ◽  
Martin Roche ◽  
Michael A. Conditt
Keyword(s):  
Machine Learning ◽  
Decision Process ◽  
Sagittal Plane ◽  
New Technology ◽  
Numerical Data ◽  
Supervised Machine Learning ◽  
Patient Specific ◽  
Surgical Decision ◽  
Clinical Series ◽  
Total Knee

Aims The use of technology to assess balance and alignment during total knee surgery can provide an overload of numerical data to the surgeon. Meanwhile, this quantification holds the potential to clarify and guide the surgeon through the surgical decision process when selecting the appropriate bone recut or soft tissue adjustment when balancing a total knee. Therefore, this paper evaluates the potential of deploying supervised machine learning (ML) models to select a surgical correction based on patient-specific intra-operative assessments. Methods Based on a clinical series of 479 primary total knees and 1,305 associated surgical decisions, various ML models were developed. These models identified the indicated surgical decision based on available, intra-operative alignment, and tibiofemoral load data. Results With an associated area under the receiver-operator curve ranging between 0.75 and 0.98, the optimized ML models resulted in good to excellent predictions. The best performing model used a random forest approach while considering both alignment and intra-articular load readings. Conclusion The presented model has the potential to make experience available to surgeons adopting new technology, bringing expert opinion in their operating theatre, but also provides insight in the surgical decision process. More specifically, these promising outcomes indicated the relevance of considering the overall limb alignment in the coronal and sagittal plane to identify the appropriate surgical decision.

scholarly journals Recapitulation of patient-specific 3D chromatin conformation using machine learning and validation of identified enhancer-gene targets

2021 ◽  
Author(s):  
Duo Xu ◽  
Andre Neil Forbes ◽  
Sandra Cohen ◽  
Ann Palladino ◽  
Tatiana Karadimitriou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Target Genes ◽  
Characteristic Curve ◽  
Regulatory Elements ◽  
Supervised Machine Learning ◽  
Patient Specific ◽  
Cancer Type ◽  
Omics Data ◽  
Cancer Genes ◽  
Large Patient

Regulatory networks containing enhancer to gene edges define cellular state and their rewiring is a hallmark of cancer. While efforts, such as ENCODE, have revealed these networks for reference tissues and cell-lines by integrating multi-omics data, the same methods cannot be applied for large patient cohorts due to the constraints on generating ChIP-seq and three-dimensional data from limited material in patient biopsies. We trained a supervised machine learning model using genomic 3D signatures of physical enhancer-gene connections that can predict accurate connections using data from ATAC-seq and RNA-seq assays only, which can be easily generated from patient biopsies. Our method overcomes the major limitations of correlation-based approaches that cannot distinguish between distinct target genes of given enhancers in different samples, which is a hallmark of network rewiring in cancer. Our model achieved an AUROC (area under receiver operating characteristic curve) of 0.91 and, importantly, can distinguish between active regulatory elements with connections to target genes and poised elements with no connections to target genes. Our predicted regulatory elements are validated by multi-omics data, including histone modification marks from ENCODE, with an average specificity of 0.92. Application of our model on chromatin accessibility and transcriptomic data from 400 cancer patients across 22 cancer types revealed novel cancer-type and subtype-specific enhancer-gene connections for known cancer genes. In one example, we identified two enhancers that regulate the expression of ESR1 in only ER+ breast cancer (BRCA) samples but not in ER- samples. These enhancers are predicted to contribute to the high expression of ESR1 in 93% of ER+ BRCA samples. Functional validation using CRISPRi confirms that inhibition of these enhancers decreases the expression of ESR1 in ER+ samples.

scholarly journals Machine Learning and Primary Total Knee Arthroplasty: Patient Forecasting for a Patient-Specific Payment Model

2018 ◽  
Vol 33 (12) ◽  
pp. 3617-3623 ◽  
Author(s):  
Sergio M. Navarro ◽  
Eric Y. Wang ◽  
Heather S. Haeberle ◽  
Michael A. Mont ◽  
Viktor E. Krebs ◽  
...  
Keyword(s):  
Machine Learning ◽  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
Primary Total Knee Arthroplasty ◽  
Patient Specific ◽  
Total Knee Arthroplasty Patient ◽  
Payment Model ◽  
Total Knee ◽  
Primary Total Knee

Total Hospital Costs and Readmission Rate of Patient-Specific Instrument in Total Knee Arthroplasty Patients

2020 ◽  
Author(s):  
Stephen Thomas ◽  
Ankur Patel ◽  
Corey Patrick ◽  
Gary Delhougne
Keyword(s):  
Total Knee Arthroplasty ◽  
Knee Arthroplasty ◽  
Hospital Cost ◽  
Readmission Rate ◽  
Hospital Costs ◽  
Patient Specific ◽  
P Value ◽  
Total Hospital Cost ◽  
Total Hospital ◽  
Total Knee

AbstractDespite advancements in surgical technique and component design, implant loosening, stiffness, and instability remain leading causes of total knee arthroplasty (TKA) failure. Patient-specific instruments (PSI) aid in surgical precision and in implant positioning and ultimately reduce readmissions and revisions in TKA. The objective of the study was to evaluate total hospital cost and readmission rate at 30, 60, 90, and 365 days in PSI-guided TKA patients. We retrospectively reviewed patients who underwent a primary TKA for osteoarthritis from the Premier Perspective Database between 2014 and 2017 Q2. TKA with PSI patients were identified using appropriate keywords from billing records and compared against patients without PSI. Patients were excluded if they were < 21 years of age; outpatient hospital discharges; evidence of revision TKA; bilateral TKA in same discharge or different discharges. 1:1 propensity score matching was used to control patients, hospital, and clinical characteristics. Generalized Estimating Equation model with appropriate distribution and link function were used to estimate hospital related cost while logistic regression models were used to estimate 30, 60, and 90 days and 1-year readmission rate. The study matched 3,358 TKAs with PSI with TKA without PSI patients. Mean total hospital costs were statistically significantly (p < 0.0001) lower for TKA with PSI ($14,910; 95% confidence interval [CI]: $14,735–$15,087) than TKA without PSI patients ($16,018; 95% CI: $15,826–$16,212). TKA with PSI patients were 31% (odds ratio [OR]: 0.69; 95% CI: 0.51–0.95; p-value = 0.0218) less likely to be readmitted at 30 days; 35% (OR: 0.65; 95% CI: 0.50–0.86; p-value = 0.0022) less likely to be readmitted at 60 days; 32% (OR: 0.68; 95% CI: 0.53–0.88; p-value = 0.0031) less likely to be readmitted at 90 days; 28% (OR: 0.72; 95% CI: 0.60–0.86; p-value = 0.0004) less likely to be readmitted at 365 days than TKA without PSI patients. Hospitals and health care professionals can use retrospective real-world data to make informed decisions on using PSI to reduce hospital cost and readmission rate, and improve outcomes in TKA patients.

Exploring the Use of Machine Learning to Automate the Qualitative Coding of Church-related Tweets

2020 ◽  
Vol 14 (2) ◽  
pp. 140-159
Author(s):  
Anthony-Paul Cooper ◽  
Emmanuel Awuni Kolog ◽  
Erkki Sutinen
Keyword(s):  
Machine Learning ◽  
Online Community ◽  
High Volume ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Social Media Data ◽  
Twitter Data ◽  
Resource Intensity ◽  
Media Data ◽  
Better Than

This article builds on previous research around the exploration of the content of church-related tweets. It does so by exploring whether the qualitative thematic coding of such tweets can, in part, be automated by the use of machine learning. It compares three supervised machine learning algorithms to understand how useful each algorithm is at a classification task, based on a dataset of human-coded church-related tweets. The study finds that one such algorithm, Naïve-Bayes, performs better than the other algorithms considered, returning Precision, Recall and F-measure values which each exceed an acceptable threshold of 70%. This has far-reaching consequences at a time where the high volume of social media data, in this case, Twitter data, means that the resource-intensity of manual coding approaches can act as a barrier to understanding how the online community interacts with, and talks about, church. The findings presented in this article offer a way forward for scholars of digital theology to better understand the content of online church discourse.

Sign in / Sign up

Export Citation Format

Share Document