Artificial neural networks for the prediction of transfusion rates in primary total hip arthroplasty.

BACKGROUND: Despite advancements in total hip arthroplasty (THA) and the increased utilization of tranexamic acid, acute blood loss anemia necessitating allogeneic blood transfusion persists as a post-operative complication. The prevalence of allogeneic blood transfusion in primary THA has been reported to be as high as 9%. Therefore, this study aimed to develop and validate novel machine learning models for the prediction of transfusion rates following primary total hip arthroplasty. METHODS: A total of 7265 consecutive patients who underwent primary total hip arthroplasty were evaluated using a single tertiary referral institution database. Patient charts were manually reviewed to identify patient demographics and surgical variables that may be associated with transfusion rates. Four state-of-the-art machine learning algorithms were developed to predict transfusion rates following primary THA, and these models were assessed by discrimination, calibration, and decision curve analysis. RESULTS: The factors most significantly associated with transfusion rates include tranexamic acid usage, bleeding disorders, and pre-operative hematocrit (< 33%). The four machine learning models all achieved excellent performance across discrimination (AUC > 0.78), calibration, and decision curve analysis. CONCLUSION: This study developed machine learning models for the prediction of patient-specific transfusion rates following primary total hip arthroplasty. The results represent a novel application of machine learning, and has the potential to improve outcomes and pre-operative planning. LEVEL OF EVIDENCE: III, case-control retrospective analysis.

The utilization of artificial neural networks for the prediction of 90-day unplanned readmissions following total knee arthroplasty.

BACKGROUND: A reliable predictive tool to predict unplanned readmissions has the potential to lower readmission rates through targeted pre-operative counseling and intervention with respect to modifiable risk factors. This study aimed to develop and internally validate machine learning models for the prediction of 90-day unplanned readmissions following total knee arthroplasty. METHODS: A total of 10,021 consecutive patients underwent total knee arthroplasty. Patient charts were manually reviewed to identify patient demographics and surgical variables that may be associated with 90-day unplanned hospital readmissions. Four machine learning algorithms (artificial neural networks, support vector machine, k-nearest neighbor, and elastic-net penalized logistic regression) were developed to predict 90-day unplanned readmissions following total knee arthroplasty and these models were evaluated using ROC AUC statistics as well as calibration and decision curve analysis. RESULTS: Within the study cohort, 644 patients (6.4%) were readmitted within 90 days. The factors most significantly associated with 90-day unplanned hospital readmissions included drug abuse, surgical operative time, and American Society of Anaesthesiologist Physical Status (ASA) score. The machine learning models all achieved excellent performance across discrimination (AUC > 0.82), calibration, and decision curve analysis. CONCLUSION: This study developed four machine learning models for the prediction of 90-day unplanned hospital readmissions in patients following total knee arthroplasty. The strongest predictors for unplanned hospital readmissions were drug abuse, surgical operative time, and ASA score. The study findings show excellent model performance across all four models, highlighting the potential of these models for the identification of high-risk patients prior to surgery for whom coordinated care efforts may decrease the risk of subsequent hospital readmission. LEVEL OF EVIDENCE: Level III, case-control retrospective analysis.

Artificial Neural Networks Can Predict Early Failure of Cementless Total Hip Arthroplasty in Patients With Osteoporosis.

BACKGROUND: Total hip arthroplasty (THA) done in the aging population is associated with osteoporosis-related complications. The altered bone density in osteoporotic patients is a risk factor for revision surgery. This study aimed to develop and validate machine learning (ML) models to predict revision surgery in patients with osteoporosis after primary noncemented THA. METHODS: We retrospectively reviewed a consecutive series of 350 patients with osteoporosis (T-score less than or equal to -2.5) who underwent primary noncemented THA at a tertiary referral center. All patients had a minimum 2-year follow-up (range: 2.1 to 5.6). Four ML algorithms were developed to predict the probability of revision surgery, and these were assessed by discrimination, calibration, and decision curve analysis. RESULTS: The overall incidence of revision surgery was 5.2% at a mean follow-up of 3.7 years after primary noncemented THA in osteoporotic patients. Revision THA was done because of periprosthetic fracture in nine patients (50%), aseptic loosening/subsidence in five patients (28%), periprosthetic joint infection in two patients (11%) and dislocation in two patients (11%). The strongest predictors for revision surgery in patients after primary noncemented THA were female sex, BMI (>35 kg/m2), age (>70 years), American Society of Anesthesiology score (≥3), and T-score. All four ML models demonstrated good model performance across discrimination (AUC range: 0.78 to 0.81), calibration, and decision curve analysis. CONCLUSION: The ML models presented in this study demonstrated high accuracy for the prediction of revision surgery in osteoporotic patients after primary noncemented THA. The presented ML models have the potential to be used by orthopaedic surgeons for preoperative patient counseling and optimization to improve the outcomes of primary noncemented THA in osteoporotic patients.

Laboratory and clinical reliability of two spectrophotometers.

OBJECTIVE: To evaluate the repeatability, interexaminer, and interdevice reliability of two clinically applicable spectrophotometers under laboratory and clinical conditions. MATERIAL AND METHODS: For the in vitro part of the study, measurements were performed by the use of Vita Easyshade Advance 4.0 (ES-A) and the Easyshade V (ES-V) at identical positions on different shade tabs (3D-Master; Vita Zahnfabrik, Bad Säckingen, Germany). To test repeatability, one shade tab was measured 50 times by one operator. To determine interrater and interdevice agreement, two operators used both devices to perform 10 measurements on five different shade tabs. Clinical interdevice and interexaminer reliability was checked with a positioning jig used (15 participants). Measurement accuracy of both devices was evaluated for the recommended color of shade tabs. RESULTS: Repeatability of results from both Easyshades was excellent for all color components (maximum deviation between measurements was ≤0.1 units). Interrater agreement was also perfect (intraclass correlation, ICC = 1.000). Interdevice agreement was lower, but still good (ICC ≥ 0.834). In the clinical environment, interrater and interdevice agreements were similar (ICC > 0.964 and ICC > 0.873). Accuracy was satisfactory for both devices, with both observers in full agreement for nearly 80% of ratings. CONCLUSIONS: Both Easyshades produced reliable and accurate measurements and can therefore be recommended for clinical determination of tooth color. CLINICAL SIGNIFICANCE: The outcome of this study might help clinicians estimate the performance of a new digital shade determination device.

Neural network models accurately predict discharge disposition after revision total knee arthroplasty?

PURPOSE: Based on the rising incidence of revision total knee arthroplasty (TKA), bundled payment models may be applied to revision TKA in the near future. Facility discharge represents a significant cost factor for those bundled payment models; however, accurately predicting discharge disposition remains a clinical challenge. The purpose of this study was to develop and validate artificial intelligence algorithms to predict discharge disposition following revision total knee arthroplasty. METHODS: A retrospective review of electronic patient records was conducted to identify patients who underwent revision total knee arthroplasty. Discharge disposition was defined as either home discharge or non-home discharge, which included rehabilitation and skilled nursing facilities. Four artificial intelligence algorithms were developed to predict this outcome and were assessed by discrimination, calibration and decision curve analysis. RESULTS: A total of 2228 patients underwent revision TKA, of which 1405 patients (63.1%) were discharged home, whereas 823 patients (36.9%) were discharged to a non-home facility. The strongest predictors for non-home discharge following revision TKA were American Society of Anesthesiologist (ASA) score, Medicare insurance type and revision surgery for peri-prosthetic joint infection, non-white ethnicity and social status (living alone). The best performing artificial intelligence algorithm was the neural network model which achieved excellent performance across discrimination (AUC = 0.87), calibration and decision curve analysis. CONCLUSION: This study developed four artificial intelligence algorithms for the prediction of non-home discharge disposition for patients following revision total knee arthroplasty. The study findings show excellent performance on discrimination, calibration and decision curve analysis for all four candidate algorithms. Therefore, these models have the potential to guide preoperative patient counselling and improve the value (clinical and functional outcomes divided by costs) of revision total knee arthroplasty patients. LEVEL OF EVIDENCE: IV.

Machine learning models accurately predict recurrent infection following revision total knee arthroplasty for periprosthetic joint infection.

PURPOSE: This study aimed to develop and validate machine-learning models for the prediction of recurrent infection in patients following revision total knee arthroplasty for periprosthetic joint infection. METHODS: A total of 618 consecutive patients underwent revision total knee arthroplasty for periprosthetic joint infection. The patient cohort included 165 patients with confirmed recurrent periprosthetic joint infection (PJI). Potential risk factors including patient demographics and surgical characteristics served as input to three machine-learning models which were developed to predict recurrent periprosthetic joint. The machine-learning models were assessed by discrimination, calibration and decision curve analysis. RESULTS: The factors most significantly associated with recurrent PJI in patients following revision total knee arthroplasty for PJI included irrigation and debridement with/without modular component exchange (p < 0.001), > 4 prior open surgeries (p < 0.001), metastatic disease (p < 0.001), drug abuse (p < 0.001), HIV/AIDS (p < 0.01), presence of Enterococcus species (p < 0.01) and obesity (p < 0.01). The machine-learning models all achieved excellent performance across discrimination (AUC range 0.81-0.84). CONCLUSION: This study developed three machine-learning models for the prediction of recurrent infections in patients following revision total knee arthroplasty for periprosthetic joint infection. The strongest predictors were previous irrigation and debridement with or without modular component exchange and prior open surgeries. The study findings show excellent model performance, highlighting the potential of these computational tools in quantifying increased risks of recurrent PJI to optimize patient outcomes. LEVEL OF EVIDENCE: IV.

Three-year clinical performance of monolithic and partially veneered zirconia ceramic fixed partial dentures.

OBJECTIVE: To compare the 3-year survival and success rates of monolithic (M) and partially veneered (PV) zirconia-fixed partial dentures (FPDs). MATERIALS AND METHODS: Sixty-seven FPDs (n = 33 M-FPDs; n = 34 PV-FPDs) were placed in 51 patients (n = 23 males; mean age 61.5 years) and clinically followed up 1 week, 6 months, and then yearly after placement. One hundred per cent (100%) of M-FPDs and 70% of PV-FPDs were located in the posterior region. Ninety-two per cent (92%) of M-FPDs had three units, whereas 50% of PV-FPDs had more than three units. A facial veneer was present in 73% of the PV-FPDs units. Survival and success were calculated using the Kaplan-Meier method and compared using the log-rank test (α = .05). RESULTS: The mean observation period was 3.5 years for M-FPDs and 3.1 years for PV-FPDs. Most complications associated with FPDs were biological in nature. Ceramic defects occurred exclusively among PV-FPDs. Three-year survival was 96.7% for M-FPDs and 93.8% for PV-FPDs (P = .064). Three-year success was 93.8% for M-FPDs and 81.7% for PV-FPDs (P = .039). CONCLUSIONS: The use of both M-FPDs and PV-FPDs yielded clinically successful results over a mean period of 3 years. CLINICAL SIGNIFICANCE: By using monolithic or facially veneered zirconia, ceramic FPDs could be fabricated which showed only a minimum of technical complications over the period of investigation without sacrificing adequate esthetics.

How reliable and accurate is the shade determination of premolars by spectrophotometry?

OBJECTIVES: To evaluate the reliability and accuracy of spectrophotometric shade determination of premolars and to compare the results with those for incisors. MATERIAL AND METHODS: Fifty-seven participants with natural maxillary incisors and premolars were recruited to investigate the research question. The colour of test teeth (incisors, n = 210; premolars, n = 192) was measured by use of the Vita Easyshade Advance (ES-A) and Vita Easyshade V (ES-V). Accuracy was evaluated by rating the shade tab matches recommended by the devices (scale, 1 = excellent match to 3 = mismatch). Inter-device reliability between the ES-A and ES-V for measurement of incisors and premolars was evaluated using intra-class correlation coefficients (ICC). The ratings for the accuracy of the devices were analysed using descriptive and bivariate statistics. A linear regression model was used to evaluate possible independent influencing confounders on the shade match. RESULTS: Inter-device agreement of the ES-A and ES-V for measurement of incisors and premolars was excellent for all colour components (ICC > 0.9). The accuracy of both devices was acceptable to excellent for incisors and premolars, although the ES-V was more accurate than the ES-A (p < 0.001). No significant difference in accuracy was detected between premolars and incisors (p = 0.182). The linear regression model confirmed the bivariate testing. CONCLUSIONS: The reliability and accuracy of spectrophotometric shade determination seem comparable for incisors and premolars. The recently introduced ES-V seems more accurate than its predecessor model. Further studies are needed to validate the results of this study.

Mechanic hands: clinical and capillaroscopy manifestations of patients with connective tissue diseases presented with and without mechanic hands.

OBJECTIVES: The condition known as 'Mechanic's Hands' is a thickened, hyperkeratotic eruption, which is bilaterally symmetric along the fingers, and often occurs in patients with some connective tissue diseases. Nail fold capillaroscopy is a non-invasive technique for evaluation of connective tissue diseases. We evaluated the prevalence of mechanic hands in patients with connective tissue diseases and compared the clinical manifestations and capillaroscopic changes in the patients with and without mechanic hands. METHODS: The clinical manifestations and capillaroscopy of 576 patients with scleroderma, dermatomyositis, systemic lupus erythematosus, Sjogren's syndrome, undifferentiated and mixed connective tissue diseases were evaluated and compared in patients with and without mechanic hands. RESULTS: A total of 576 patients were enrolled. Mechanic hands were observed in 17.2% of patients: 50% of mixed connective tissue disease, 35% of dermatomyositis, 15.4% of scleroderma, 14.9% of undifferentiated connective tissue disease, 14.3% of Sjogren's syndrome, and no patient with SLE. Among them, 80.8% had abnormal capillaroscopic findings. In dermatomyositis patients, Raynaud's phenomenon, anti-Jo-1 positivity, and some capillaroscopy findings were detected more frequently in patients with mechanic hand. In scleroderma, positive Scl70 and capillary loss were observed more frequently in patients without mechanic hands. CONCLUSIONS: Mechanic hands can be a presenting sign of some systemic connective tissue diseases. Probably, finding this sign on examination, especially together with Raynaud's phenomenon or abnormal capillaroscopy, can be helpful in the early diagnosis of the connective tissue diseases and can be used as a predictive and prognostic tool in future studies.

Re-exposure in cone beam CT of the dentomaxillofacial region: a retrospective study.

METHODS:: In a retrospective cohort study CBCT images of 4986 patients from the patient database from the Department of Oral Radiology, University Medical Center of the Johannes Gutenberg University, Mainz, Germany were included and the rate of re-exposures was counted. Patients were stratified into those who received a scan with the small field-of-view CBCT or the large field-of-view CBCT. The effect of patient-related parameters as age and gender was implicated. As a further device-specific parameter, the statistical analysis included whether the selection of the field of view due to the device type had a significant influence on the occurrence of re-exposures. Furthermore, the rescans were analyzed with regard to their causes. RESULTS:: In total, CBCT images of 82 (1.6%) patients had to be repeated. Looking at the two different devices, in 42 (1.3%) patients that received a scan with the large field-of-view CBCT and in 40 (2.3%) patients that received a scan with the small field-of-view CBCT respectively needed a retake. There was no statistically significant correlation between age and gender to retakes. For the small field-of-view-size significantly more retakes were observed than for the large one. With 46% motion artifacts were the most frequent causes for a re-exposure of the patient. CONCLUSIONS:: Gender and age did not have an impact on the occurrence of re-exposures. Patients who received a scan with the small field-of-view CBCT were significantly more often rescanned than those with the large field-of-view CBCT.

Are there associations between sleep bruxism, chronic stress, and sleep quality?

OBJECTIVES: The purpose of this study was to identify associations between definite sleep bruxism, as defined by the American academy of sleep medicine, and chronic stress and sleep quality. METHODS: Sleep bruxism was determined by use of questionnaires, assessment of clinical symptoms, and recording of electromyographic and electrocardiographic data (recorded by the Bruxoff® device). The study included 67 participants. Of these, 38 were identified as bruxers and 29 as non-bruxers. The 38 bruxers were further classified as 17 moderate and 21 intense bruxers. Self-reported stress and self-reported sleep quality were determined by use of the validated questionnaires "Trier Inventory for the Assessment of Chronic Stress" (TICS) and the "Pittsburgh Sleep Quality Index" (PSQI). RESULTS: No statistically significant association was found between sleep bruxism and self-reported stress or sleep quality. However, a significant association between specific items of chronic stress and poor sleep quality was identified. CONCLUSIONS: The results of this study indicate an association between subjective sleep quality and subjective chronic stress, irrespective of the presence or absence of sleep bruxism. CLINICAL SIGNIFICANCE: Chronic stress and sleep quality do not seem to be associated with sleep bruxism. (clinical trial no. NCT03039985).