Machine Learning for Detecting Total Knee Arthroplasty Implant Loosening on Plain Radiographs.

(1) Background: The purpose of this study was to investigate whether the loosening of total knee arthroplasty (TKA) implants could be detected accurately on plain radiographs using a deep convolution neural network (CNN). (2) Methods: We analyzed data for 100 patients who underwent revision TKA due to prosthetic loosening at a single institution from 2012 to 2020. We extracted 100 patients who underwent primary TKA without loosening through a propensity score, matching for age, gender, body mass index, operation side, and American Society of Anesthesiologists class. Transfer learning was used to prepare a detection model using a pre-trained Visual Geometry Group (VGG) 19. For transfer learning, two methods were used. First, the fully connected layer was removed, and a new fully connected layer was added to construct a new model. The convolutional layer was frozen without training, and only the fully connected layer was trained (transfer learning model 1). Second, a new model was constructed by adding a fully connected layer and varying the range of freezing for the convolutional layer (transfer learning model 2). (3) Results: The transfer learning model 1 gradually increased in accuracy and ultimately reached 87.5%. After processing through the confusion matrix, the sensitivity was 90% and the specificity was 100%. Transfer learning model 2, which was trained on the convolutional layer, gradually increased in accuracy and ultimately reached 97.5%, which represented a better improvement than for model 1. Processing through the confusion matrix affirmed that the sensitivity was 100% and the specificity was 97.5%. (4) Conclusions: The CNN algorithm, through transfer learning, shows high accuracy for detecting the loosening of TKA implants on plain radiographs.

Efficacy and Safety of Intravenous Ferric Carboxymaltose in Patients with Postoperative Anemia Following Same-Day Bilateral Total Knee Arthroplasty: A Randomized Controlled Trial.

(1) Background: The purpose of this study was to evaluate the efficacy and safety of intravenous (IV) ferric carboxymaltose (FCM) to treat acute postoperative anemia following same-day bilateral total knee arthroplasty (TKA). (2) Methods: A total of 118 patients who underwent same-day bilateral TKA were randomly assigned to two groups: an FCM group (FCM infusion, 58 patients) and a Control group (placebo with normal saline, 60 patients). The primary endpoint was the number of responders with a Hb increase of two or more points by the second postoperative week. The secondary endpoints were Hb level, iron metabolism variables and blood transfusion rate at 2, 6 and 12 weeks after surgery. (3) Results: The FCM group had more Hb responders than the Control group (62.1% vs. 31.6%, p < 0.001). The Hb level was significantly higher in the FCM group during 12 weeks after surgery (all p < 0.05). Ferritin, iron and transferrin saturation levels were significantly higher in the FCM group from 2 to 12 weeks postoperatively (all p < 0.05). There was no difference in transfusion rate after surgery (p > 0.05). (4) Conclusion: In patients with postoperative anemia after same-day bilateral TKA, IV FCM infusion significantly improved Hb response two weeks after surgery without severe adverse events compared to placebo. In contrast, transfusion rate and various parameters of quality of life assessment up to 12 weeks did not vary between these groups. Level of evidence: Level I.

Efficacy of duloxetine compared with opioid for postoperative pain control following total knee arthroplasty.

BACKGROUND: The purpose of this study was to assess the efficacy of duloxetine as an alternative to opioid treatment for postoperative pain management following total knee arthroplasty (TKA). METHODS: Among 944 patients, 290 (30.7%) of patients received opioid or duloxetine for pain control for 6 weeks when the pain Visual Analogue Scale (VAS) score was greater than 4 out of 10 at the time of discharge. 121 patients in the Opioid group and 118 in the Duloxetine group were followed up for more than one year. Preoperative and postoperative patient reported outcome measures (pain VAS score, Western Ontario and McMaster Universities OA Index (WOMAC) score were compared. The rate of further drug prescription (opioid or duloxetine) after 6 weeks of first prescription, 30-day readmission rate, and side effects were also investigated. RESULTS: There was no significant difference in pain VAS score, WOMAC Pain and Function score, at each time point between before and after surgery (all p>0.05). Fifteen (9.8%) patients in the opioid group and six (4.4%) patients in the duloxetine group were prescribed additional medication after first 6 weeks, showing no significant (p>0.05) difference in proportion. The 30-day readmission rate and the incidence of side effects were also similar (all p>0.05). There was no difference in the incidence of side effects between the two groups (p>0.05). CONCLUSION: Duloxetine and opioid did not show any difference in pain control, function, and side effects for up to one year after TKA. Although large-scale randomized controlled trials are still required to further confirm the side effects of duloxetine, it can be considered as an alternative to opioid for postoperative pain control following TKA.

Efficacy and safety of celecoxib combined with JOINS in the treatment of degenerative knee osteoarthritis: study protocol of a randomized controlled trial.

BACKGROUND: The aim of this study will be to investigate the therapeutic effect and safety of non-steroidal anti-inflammatory drugs (NSAIDs) along with symptomatic slow-acting drugs for the treatment of osteoarthritis (SYSADOA), JOINS tablets, for degenerative knee osteoarthritis (OA) treatment and to determine the analgesic and anti-inflammatory effects of the combination therapy. In addition, we will investigate whether JOINS treatment alone after NSAID and JOINS combination treatment is effective in relieving and maintaining knee OA symptoms. METHODS: This study will be a prospective, randomized, double-blind endpoint study design. All patients will be randomly assigned to either intervention (celecoxib+JOINS) or control (celecoxib+placebo) groups. In Part 1, the intervention group will be administered celecoxib once a day and JOINS three times a day for a total of 12 weeks. In the control group, celecoxib will be administered once a day and JOINS placebo three times a day for a total of 12 weeks. In Part 2, JOINS alone and JOINS placebo alone will be administered for an additional 24 weeks in both groups, respectively. The primary endpoint will be the amount of change during the 12 weeks as assessed using the Western Ontario and McMaster Universities Osteoarthritis Index total score compared with baseline. The secondary endpoint will be the amount of change at 1, 4, 12, 24, and 36 weeks from the baseline for pain visual analog scale, Brief Pain Inventory, Short Form Health Survey-36 and biomarkers. RESULTS: The trial was registered with Clinical-Trials.gov (NCT04718649). The clinical trial was also registered on Clinical Research Information Service (CRIS) with the trial registration number KCT0005742. CONCLUSIONS: The combination treatment of the most commonly used SYSADOA drug, JOINS, and selective COX-2 inhibitor celecoxib as the representative NSAID for knee OA treatment, can be compared with celecoxib alone treatment to determine the safety or therapeutic effect.

Comparative study of the influence of room-temperature and warmed fluid irrigation on body temperature in arthroscopic shoulder surgery.

PURPOSE: The purpose of this study was to evaluate the effect of irrigation fluid temperature on body temperature and other variables, and to determine their correlations. METHODS: A prospective randomized study was performed of 50 patients undergoing arthroscopic shoulder surgery who received irrigation fluid either with room temperature or warmed to 37 degrees C to 39 degrees C. Core body temperature was checked at regular intervals, and additional variables, such as length of anesthesia and surgery, amount of irrigation fluid and intravenous fluid used, amount of bleeding, weight gain, and postoperative pain were collected during surgery and postoperatively. RESULTS: The final core body temperature was 35.5 +/- 0.3 degrees C in the room-temperature fluid group and 36.2 +/- 0.3 degrees C in the warmed fluid group (P < .001). The temperature drop was 0.86 +/- 0.2 degrees C in the room-temperature fluid group and 0.28 +/- 0.2 degrees C in the warmed fluid group (P < .001). Hypothermia occurred in 91.3% of patients in the room-temperature fluid group; the incidence of hypothermia was much lower in the warmed fluid group (17.4%; P < .001). Of the variables measured, the patient's age and amount of irrigation fluid used correlated with core body temperature in the room-temperature fluid group. No variables correlated with core body temperature in the warmed fluid group. CONCLUSIONS: Hypothermia occurred more often in shoulder arthroscopic surgery with room-temperature fluid irrigation than with warmed fluid irrigation. The patient's age and amount of irrigation fluid used correlate with core body temperature when using room-temperature irrigation fluid. The use of warm irrigation fluid during arthroscopic shoulder surgery decreases perioperative hypothermia, especially in elderly patients. LEVEL OF EVIDENCE: Level I, therapeutic randomized controlled trial.