Supervised machine learning for the prediction of post-operative clinical outcomes of hip and knee replacements: a review.

Prediction models are being increasingly used in the medical field to identify risk factors and possible outcomes. Some of these are presently being used to develop guidelines for improving clinical practice. The application of machine learning (ML), comprising a powerful set of computational tools for analysing data, has been clearly expanding in the role of predictive modelling. This paper reviews the latest developments of supervised ML techniques that have been used to analyse data related to post-operative total hip and knee replacements. The aim was to review the most recent findings of relevant published studies by outlining the methodologies employed (most-widely used supervised ML techniques), data sources, domains, limitations of predictive analytics and the quality of predictions.

What Is the Most Appropriate Comparator to Use in Assessing the Comparative Performance of Primary Total Knee Prostheses? A Registry-Based Study.

Background: The Australian Orthopedic Association National Joint Replacement Registry has developed a standardized multi-stage approach to identify prostheses with a higher-than-anticipated rate of revision when comparing a prosthesis of interest to all other prostheses within the same broad class. However, the approach does not adequately differentiate between the conventional and complex design prostheses, and the comparator classes need to be re-evaluated. This study aimed to identify a more relevant comparator to better reflect conventional and complex surgical practices according to the stability design and also explore how the rate of revision estimated in the comparator groups affects the identification of "prosthesis outliers." Methods: The cumulative percent revision (CPR) was calculated for 640,045 primary total knee replacements (TKRs) undertaken for Osteoarthritis from 1 January 2003 to 31 December 2019. At first, survivorship analyses were undertaken to calculate the rate of revision for primary TKR by stability design. A modified TKR comparator group was developed by excluding the "complex" group of prostheses with fully stabilized and hinged designs. The effectiveness of the modified comparator groups, including cruciate retaining and posterior stabilized designs, was evaluated based on the ability to detect additional prostheses by performing the Australian Orthopedic Association National Joint Replacement Registry standardized method for identifying prosthesis outliers. Results: The modified comparator to include only conventional designs had a 10-year CPR of 5.2% (5.1, 5.3). When the fully stabilized and hinged design groups were combined as a comparator group of complex devices to reflect devices used only for specific purposes in primary TKR, the CPR at 10 year was 10.3% (8.6, 12.0). Conclusions: The use of modified comparator groups led to identifying additional conventional prostheses but fewer complex designs as being at risk and has the potential to improve the early assessment of TKR prostheses.

What is the most appropriate comparator group to use in assessing the performance of primary total hip prostheses within the community?

BACKGROUND: There are variations in the performance of individual prostheses used in hip replacements. Some of which have unexpectedly higher revision rates - outliers. The Australian Orthopaedic Association National Joint Replacement Registry (AOANJRR) has established a standardised multi-stage approach for identifying these devices. This is done by comparing the revision rates of individual prostheses to all other prostheses in class, with the exception of large head metal-on-metal (LHMoM) prostheses. However, improvements in device design and performance over time have required a need to reconsider the comparator group. This study aimed to identify a more specific comparator to better reflect contemporary surgical practice. METHODS: The time to first revision was estimated on the data of 413,417 primary total conventional hip replacements undertaken for osteoarthritis (OA) from 01 January 2003 to 31 December 2019. Survivorship analyses with stepwise exclusions were undertaken. The first exclusion was LHMoM, followed by other non-modern bearing surfaces (defined as all the bearing couples except metal or ceramic heads on cross-linked polyethylene and mixed ceramic-on-ceramic), and then devices with modular neck-stem design or used for specific purposes (incl. constrained, dual-mobility, and head size <28 mm). Lastly, all remaining prostheses previously identified as having a higher than anticipated rate of revision (HTARR) were also excluded. RESULTS: These exclusions progressively reduced the cumulative percent revision (CPR) rate. The final comparator, which only includes satisfactory-performed prostheses of contemporary design and use, has a 10-year CPR of 4.30% (95% CI, 4.2-4.41) which is lower than 4.93% (95% CI, 4.84-5.02) for the current comparator used by the AOANJRR (all prostheses excluding LHMOM). Over the study period, 13 additional components were identified utilising the modified comparator. CONCLUSIONS: The calculation of the comparator revision rate should be re-evaluated to include only modern prosthesis constructs to ensure that poorly performing prostheses are identified early.

Efficient clean-up of waters contaminated with diazinon pesticide using photo-decomposition of peroxymonosulfate by ZnO decorated on a magnetic core/shell structure.

In the present study, ZnO nanoparticles were anchored on a magnetic core/shell structure (SiO2@Fe3O4) to perpetrate ZnO@SiO2@Fe3O4 and then coupled with UV light as a heterogeneous nanocatalyst for activating peroxymonosulfate (PMS) into diazinon (DZ) degradation. Several techniques like XRD (X-ray diffraction), BET (Brunaeur, Emmett and Teller), TEM (Transmission electron microscope), FESEM (Field emission-scanning electron microscope) coupled with EDS (Energy Dispersive X-ray Spectrometer), PL (photoluminescence), VSM (Vibrating Sample Magnetometer) and UV-vis diffuse reflectance spectroscopy (DRS) were applied for identification of catalyst features. A possible mechanism for PMS activation and DZ degradation was proposed in details. The effect of solution pH, various concentrations of catalyst, PMS and DZ, quenching agents, different chemical oxidants and co-existing anions was assessed as operating factors to determine the optimum conditions. PMS decomposed effectively in coupling with ZnO@SiO2@Fe3O4 and UV. At optimal conditions, over 95 and 56% of DZ and TOC were removed during 60 min reaction, respectively. The complete degradation of DZ was confirmed using its absorption peak in UV-vis spectra analysis over 60 min treatment. A wide variety of free radicals was identified during quenching tests. HO• and h+ played a pivotal role in the degradation process of DZ. Decreasing the degradation efficiency in the presence of anions was as Cl- > CO32- > NO3- > PO43- > SO42- > HCO3-. A negligible amount of leaching Fe (<0.2 mg/L) was found for ZnO@SiO2@Fe3O4, indicating that the catalyst possesses a high stability in oxidation systems. In addition, a significant potential was achieved in reusing of catalyst within five consecutive runs. In conclusion, ZnO@SiO2@Fe3O4/PMS/UV hybrid system can be utilized as a promising advanced oxidation process into efficient degradation of pesticides, thanks to easy recovery, high catalytic activity, co-production of different reactive species and high durability and recyclability potential.

Photo-assisted catalytic degradation of acetaminophen using peroxymonosulfate decomposed by magnetic carbon heterojunction catalyst.

Catalytic oxidative degradation of acetaminophen (ACT) was evaluated using magnetic mesoporous carbon (MNPs@C) coupled with UV light and peroxymonosulfate (PMS). The performance of hybrid system (i.e., MNPs@C/UV/PMS) was assessed as a function of some operational factors (e.g., reaction time and different concentrations of catalyst, PMS and ACT) in a batch system. MNPs@C represented a high magnetic response and was easily recovered from aqueous solution via an external magnet. A significant synergistic effect was observed among the applied techniques in MNPs@C/UV/PMS system for ACT degradation. After 40 min reaction, the removal efficiencies of 97.4 and 63.5% were obtained for ACT and TOC, respectively. Both adsorption and oxidation mechanisms were responsible simultaneously for ACT removal in MNPs@C/UV/PMS system. Under optimum conditions, the removal rates of ACT and TOC were reduced slightly to 91.7 and 49.4% after five consecutive catalyst uses, which indicates the excellent reusing potential of MNPs@C. In addition, a high stability was detected for as-prepared catalyst during recycling tests, since the quantity of leached Fe was <0.2 mg/L. Methanol and tert-butyl alcohol showed a strong quenching effect on the performance of MNPs@C/UV/PMS system, demonstrating the dominant role of SO4•- and HO radicals in ACT degradation process. MNPs@C in comparison with ferrous ions, as a homogeneous catalyst, showed a better performance in the activation of PMS and ACT degradation. Integration of MNPs@C, UV and PMS exhibited an excellent performance into ACT removal over 40 min reaction, which can be utilized as an effective and promising technique for the efficient decontamination of polluted waters.