Prognosis of patients with post-Covid-19 condition: Prospective cohort cluster analysis at one year.

OBJECTIVE: We aimed to identify clinically relevant clusters among patients with post-Covid-19 condition (PCC) and assess prognosis overall and within clusters. METHODS: Prospective cohort study of patients with PCC attending a rehabilitation clinic. We monitored patient reported outcome measures (PROMs): EuroHIS quality of life and symptoms. Unsupervised hierarchical cluster analyses were performed to identify clusters of patients with different quantity of symptoms, and symptoms presenting together. Preliminary findings on symptom prevalence and quality of life at 12 months are reported. RESULTS: Among 409 patients, 70.4% were women, with an average baseline of 20.3 (SD 6.8) symptoms. Three clusters emerged based on symptom quantity, labelled by the average number of symptoms at baseline: Cluster-11 (17% of all patients), Cluster-17 (35%), and Cluster-25 (48%). Multinomial logistic regression showed female sex, multiple comorbidities predicting more symptoms. Four symptom-based clusters were defined: fatigue and cognitive complaints; pain, trouble sleeping, palpitations and other symptoms; gastrointestinal symptoms; and emotion-related symptoms. Linear regression models showed that female sex, multiple comorbidities, anxiety, use of antidepressants, BMI and smoking were among the determinants of symptom clusters. In 12-month follow-up, symptom count decreased, and quality of life improved across all clusters, with 9% having good quality of life at baseline and 33% at 12 months. CONCLUSION: Four patient clusters based on symptoms were identified in the PCC cohort. Prognosis was favorable across all clusters, with symptom reduction and improved quality of life observed. Female sex, comorbidities, BMI, and mental-health related variables predicted higher symptom burden, suggesting multifactorial origins of PCC.

Proteomics screening after pediatric allogenic hematopoietic stem cell transplantation reveals an association between increased expression of inhibitory receptor FCRL6 on γδ T cells and cytomegalovirus reactivation.

We studied the associations between inflammation-related proteins in circulation and complications after pediatric allogenic hematopoietic stem cell transplantation (HSCT), to reveal proteomic signatures or individual soluble proteins associated with specific complications after HSCT. We used a proteomics method called Proximity Extension Assay to repeatedly measure 180 different proteins together with clinical variables, cellular immune reconstitution and blood viral copy numbers in 27 children (1-18 years of age) during a 2-year follow-up after allogenic HSCT. Protein profile analysis was performed using unsupervised hierarchical clustering and a regression-based method, while the Bonferroni-corrected Mann-Whitney U-test was used for time point-specific comparison of individual proteins against outcome. At 6 months after allogenic HSCT, we could identify a protein profile pattern associated with occurrence of the complications such as chronic graft-versus-host disease, viral infections, relapse and death. When protein markers were analyzed separately, the plasma concentration of the inhibitory and cytotoxic T-cell surface protein FCRL6 (Fc receptor-like 6) was higher in patients with cytomegalovirus (CMV) viremia [log2-fold change 1.5 (P = 0.00099), 2.5 (P = 0.00035) and 2.2 (P = 0.045) at time points 6, 12 and 24 months]. Flow cytometry confirmed that FCRL6 expression was higher in innate-like γδ T cells, indicating that these cells are involved in controlling CMV reactivation in HSCT recipients. In conclusion, the potentially druggable FCRL6 receptor on cytotoxic T cells appears to have a role in controlling CMV viremia after HSCT. Furthermore, our results suggest that system-level analysis is a useful addition to the studying of single biomarkers in allogenic HSCT.

Periprosthetic Joint Infection After Total Knee Arthroplasty With or Without Antibiotic Bone Cement.

Importance: Despite increased use of antibiotic-loaded bone cement (ALBC) in joint arthroplasty over recent decades, current evidence for prophylactic use of ALBC to reduce risk of periprosthetic joint infection (PJI) is insufficient. Objective: To compare the rate of revision attributed to PJI following primary total knee arthroplasty (TKA) using ALBC vs plain bone cement. Design, Setting, and Participants: This international cohort study used data from 14 national or regional joint arthroplasty registries in Australia, Denmark, Finland, Germany, Italy, New Zealand, Norway, Romania, Sweden, Switzerland, the Netherlands, the UK, and the US. The study included primary TKAs for osteoarthritis registered from January 1, 2010, to December 31, 2020, and followed-up until December 31, 2021. Data analysis was performed from April to September 2023. Exposure: Primary TKA with ALBC vs plain bone cement. Main Outcomes and Measures: The primary outcome was risk of 1-year revision for PJI. Using a distributed data network analysis method, data were harmonized, and a cumulative revision rate was calculated (1 - Kaplan-Meier), and Cox regression analyses were performed within the 10 registries using both cement types. A meta-analysis was then performed to combine all aggregated data and evaluate the risk of 1-year revision for PJI and all causes. Results: Among 2 168 924 TKAs included, 93% were performed with ALBC. Most TKAs were performed in female patients (59.5%) and patients aged 65 to 74 years (39.9%), fully cemented (92.2%), and in the 2015 to 2020 period (62.5%). All participating registries reported a cumulative 1-year revision rate for PJI of less than 1% following primary TKA with ALBC (range, 0.21%-0.80%) and with plain bone cement (range, 0.23%-0.70%). The meta-analyses based on adjusted Cox regression for 1 917 190 TKAs showed no statistically significant difference at 1 year in risk of revision for PJI (hazard rate ratio, 1.16; 95% CI, 0.89-1.52) or for all causes (hazard rate ratio, 1.12; 95% CI, 0.89-1.40) among TKAs performed with ALBC vs plain bone cement. Conclusions and Relevance: In this study, the risk of revision for PJI was similar between ALBC and plain bone cement following primary TKA. Any additional costs of ALBC and its relative value in reducing revision risk should be considered in the context of the overall health care delivery system.

Deep Learning Enables Automatic Detection of Joint Damage Progression in Rheumatoid Arthritis-Model Development and External Validation.

OBJECTIVES: Although deep learning has demonstrated substantial potential in automatic quantification of joint damage in rheumatoid arthritis (RA), evidence for detecting longitudinal changes at an individual patient level is lacking. Here, we introduce and externally validate our automated RA scoring algorithm (AuRA), and demonstrate its utility for monitoring radiographic progression in a real-world setting. METHODS: The algorithm, originally developed during the Rheumatoid Arthritis 2-Dialogue for Reverse Engineering Assessment and Methods (RA2-DREAM) challenge, was trained to predict expert-curated Sharp-van der Heijde total scores in hand and foot radiographs from two previous clinical studies (n = 367). We externally validated AuRA against data (n = 205) from Turku University Hospital and compared the performance against two top-performing RA2-DREAM solutions. Finally, for 54 patients, we extracted additional radiograph sets from another control visit to the clinic (average time interval of 4.6 years). RESULTS: In the external validation cohort, with a root-mean-square-error (RMSE) of 23.6, AuRA outperformed both top-performing RA2-DREAM algorithms (RMSEs 35.0 and 35.6). The improved performance was explained mostly by lower errors at higher expert-assessed scores. The longitudinal changes predicted by our algorithm were significantly correlated with changes in expert-assessed scores (Pearson's R = 0.74, p< 0.001). CONCLUSION: AuRA had the best external validation performance and demonstrated potential for detecting longitudinal changes in joint damage. Available in https://hub.docker.com/r/elolab/aura, our algorithm can easily be applied for automatic detection of radiographic progression in the future, reducing the need for laborious manual scoring.

Development and validation of a weight-loss predictor to assist weight loss management.

This study aims to develop and validate a modeling framework to predict long-term weight change on the basis of self-reported weight data. The aim is to enable focusing resources of health systems on individuals that are at risk of not achieving their goals in weight loss interventions, which would help both health professionals and the individuals in weight loss management. The weight loss prediction models were built on 327 participants, aged 21-78, from a Finnish weight coaching cohort, with at least 9 months of self-reported follow-up weight data during weight loss intervention. With these data, we used six machine learning methods to predict weight loss after 9 months and selected the best performing models for implementation as modeling framework. We trained the models to predict either three classes of weight change (weight loss, insufficient weight loss, weight gain) or five classes (high/moderate/insufficient weight loss, high/low weight gain). Finally, the prediction accuracy was validated with an independent cohort of overweight UK adults (n = 184). Of the six tested modeling approaches, logistic regression performed the best. Most three-class prediction models achieved prediction accuracy of > 50% already with half a month of data and up to 97% with 8 months. The five-class prediction models achieved accuracies from 39% (0.5 months) to 89% (8 months). Our approach provides an accurate prediction method for long-term weight loss, with potential for easier and more efficient management of weight loss interventions in the future. A web application is available: https://elolab.shinyapps.io/WeightChangePredictor/ .The trial is registered at clinicaltrials.gov/ct2/show/NCT04019249 (Clinical Trials Identifier NCT04019249), first posted on 15/07/2019.

Prognosis of patients with long COVID symptoms: a protocol for a longitudinal cohort study at a primary care referred outpatient clinic in Helsinki, Finland.

INTRODUCTION: After COVID-19, many continue to experience persistent debilitating symptoms, that is, long COVID. Its most prevalent symptoms are chest pain, difficulties with breathing, painful muscles, ageusia or anosmia, tingling extremities and general tiredness. This paper describes the protocol of the Long COVID Cohort Study to assess the prognosis and prognostic determinants of patients with long COVID by implementing patient-reported outcome measures (PROMs), patient-reported experience measures (PREMs) and clinical examinations during a 1-year follow-up. METHODS AND ANALYSIS: This is a prospective, single-site cohort study consisting of administering questionnaires and clinical examinations to adult patients referred to the Clinic for Long-Term Effects of COVID-19 at Helsinki University Hospital (Hospital district of Helsinki and Uusimaa). The referrals are from all healthcare units within HUS and other hospital districts during years 2021-2023. All admitted patients have had laboratory-confirmed COVID-19. The targeted study sample size is 500 participants. The questionnaires are administered at 0, 3, 6 and 12 months. The main outcome variables are the changes in self-reported functional abilities and quality of life. In addition, we will evaluate functional abilities at baseline using neurocognitive evaluation, a 6MWT and a measurement of hand grip strength. The Long COVID Cohort Study will form a quality register for the clinic and characterise the first systematic collection of PROMs, PREMs, questionnaire and clinical examinations related to long COVID in Finland. The Study belongs to a study consortium Long COVID-HORIZON-HLTH-2021-DISEASE-04 that aims to reveal the biomechanisms of long COVID. ETHICS AND DISSEMINATION: This study has been approved by the Helsinki University Hospital research ethics committee board, ID HUS/1493/2021 on 6 March 2021. All study participants sign written informed consent for participation. The study findings will be reported for publication in peer-reviewed journals. TRIAL REGISTRATION NUMBER: NCT05699512; Pre-results.

Development of prediction model for alanine transaminase elevations during the first 6 months of conventional synthetic DMARD treatment.

Frequent laboratory monitoring is recommended for early identification of toxicity when initiating conventional synthetic disease-modifying antirheumatic drugs (csDMARDs). We aimed at developing a risk prediction model to individualize laboratory testing at csDMARD initiation. We identified inflammatory joint disease patients (N = 1196) initiating a csDMARD in Turku University Hospital 2013-2019. Baseline and follow-up safety monitoring results were drawn from electronic health records. For rheumatoid arthritis patients, diagnoses and csDMARD initiation/cessation dates were manually confirmed. Primary endpoint was alanine transaminase (ALT) elevation of more than twice the upper limit of normal (ULN) within 6 months after treatment initiation. Computational models for predicting incident ALT elevations were developed using Lasso Cox proportional hazards regression with stable iterative variable selection (SIVS) and were internally validated against a randomly selected test cohort (1/3 of the data) that was not used for training the models. Primary endpoint was reached in 82 patients (6.9%). Among baseline variables, Lasso model with SIVS predicted subsequent ALT elevations of > 2 × ULN using higher ALT, csDMARD other than methotrexate or sulfasalazine and psoriatic arthritis diagnosis as important predictors, with a concordance index of 0.71 in the test cohort. Respectively, at first follow-up, in addition to baseline ALT and psoriatic arthritis diagnosis, also ALT change from baseline was identified as an important predictor resulting in a test concordance index of 0.72. Our computational model predicts ALT elevations after the first follow-up test with good accuracy and can help in optimizing individual testing frequency.

Risk factors for revision due to prosthetic joint infection following total knee arthroplasty based on 62,087 knees in the Finnish Arthroplasty Register from 2014 to 2020.

BACKGROUND AND PURPOSE: Periprosthetic joint infection (PJI) is the commonest reason for revision after total knee arthroplasty (TKA). We assessed the risk factors for revision due to PJI following TKA based on the Finnish Arthroplasty Register (FAR). PATIENTS AND METHODS: We analyzed 62,087 primary condylar TKAs registered between June 2014 and February 2020 with revision for PJI as the endpoint. Cox proportional hazards regression was used to estimate hazard ratios (HR) with 95% confidence intervals (CI) for the first PJI revision using 25 potential patient- and surgical-related risk factors as covariates. RESULTS: 484 knees were revised for the first time during the first postoperative year because of PJI. The HRs for revision due to PJI in unadjusted analysis were 0.5 (0.4-0.6) for female sex, 0.7 (0.6-1.0) for BMI 25-29, and 1.6 (1.1-2.5) for BMI > 40 compared with BMI < 25, 4.0 (1.3-12) for preoperative fracture diagnosis compared with osteoarthritis, and 0.7 (0.5-0.9) for use of an antimicrobial incise drape. In adjusted analysis the HRs were 2.2 (1.4-3.5) for ASA class III-IV compared with class I, 1.7 (1.4-2.1) for intraoperative bleeding ≥ 100 mL, 1.4 (1.2-1.8) for use of a drain, 0.7 (0.5-1.0) for short duration of operation of 45-59 minutes, and 1.7 (1.3-2.3) for long operation duration > 120 min compared with 60-89 minutes, and 1.3 (1.0-1.8) for use of general anesthesia. CONCLUSION: We found increased risk for revision due to PJI when no incise drape was used. The use of drainage also increased the risk. Specializing in performing TKA reduces operative time and thereby also the PJI rate.

A novel easy-to-use index to predict institutionalization and death in older population - a 10-year population-based follow-up study.

BACKGROUND: Various indexes have been developed to estimate the risk for mortality, institutionalization, and other adverse outcomes for older people. Most indexes are based on a large number of clinical or laboratory parameters. An index based on only a few parameters would be more practical to use in every-day clinical practice. Our aim was to create an index to predict the risk for mortality and institutionalization with as few parameters as possible without compromising their predictive ability. METHODS: A prospective study with a 10-year follow-up period. Thirty-six clinical and fourteen laboratory parameters were combined to form an index. Cox regression model was used to analyze the association of the index with institutionalization and mortality. A backward statistical method was used to reduce the number of parameters to form an easy-to-use index for predicting institutionalization and mortality. RESULTS: The mean age of the participants (n = 1172) was 73.1 (SD 6.6, range 64‒97) years. Altogether, 149 (14%) subjects were institutionalized, and 413 (35%) subjects deceased during the follow-up. Institutionalization and mortality rates increased as index scores increased both for the large 50-parameter combined index and for the reduced indexes. After a backward variable selection in the Cox regression model, three clinical parameters remained in the index to predict institutionalization and six clinical and three laboratory parameters in the index to predict mortality. The reduced indexes showed a slightly better predictive value for both institutionalization and mortality compared to the full index. CONCLUSIONS: A large index with fifty parameters included many unimportant parameters that did not increase its predictive value, and therefore could be replaced with a reduced index with only a few carefully chosen parameters, that were individually associated with institutionalization or death.

Median 10-year whole blood metal ion levels and clinical outcome of ReCap-M2a-Magnum metal-on-metal total hip arthroplasty.

BACKGROUND AND PURPOSE: We have previously reported that the whole blood (WB) chromium (Cr) and cobalt (Co) ion levels decrease in the short term after ReCap-M2a-Magnum large-diameter head (LDH) metal-on-metal (MoM) total hip arthroplasty (THA). This study reports long-term metal ion levels and clinical outcomes after ReCap-Magnum THA. PATIENTS AND METHODS: ReCap-M2a-Magnum LDH THA was used in 1,450 patients in our hospital district from 2005 to 2012. Median follow-up time was 10 years. 991 patients had 2 or more metal ion measurements. The median measurement interval was 4 years. Individual metal ion change was assessed using logarithmic metal ion values in a random coefficient model. Kaplan-Meier survival estimates were calculated for revision surgery for any reason for revision, and separately for metal-related adverse events (metal ions above safe upper limit [SUL], revision due to ARMD, or pseudotumor). RESULTS: Geometric mean of Cr decreased from 1.8 ppb (geometric standard deviation [GSD] 1.8) to 1.0 ppb (GSD 2.8, p < 0.001). The Co levels decreased from 1.7 ppb (GSD 2.4) to 1.4 ppb (GSD 2.8, p < 0.001). The hip-specific survival was 85% for revision due to any reason at 14 years and the hip-specific survival for any metal-related adverse event was 69% at 14 years. INTERPRETATION: WB Cr and Co levels continued to decrease in the long-term follow-up of ReCap-M2a-Magnum THA patients. The amount of metal-related adverse events was rather high, but revision surgery was seldom required. We suggest that after 10 years from the implantation a 5-year measurement interval may be sufficient for asymptomatic ReCap-M2a-Magnum patients.

Weight Loss Trajectories in Healthy Weight Coaching: Cohort Study.

BACKGROUND: As global obesity prevalence continues to increase, there is a need for accessible and affordable weight management interventions, such as web-based programs. OBJECTIVE: This paper aims to assess the outcomes of healthy weight coaching (HWC), a web-based obesity management program integrated into standard Finnish clinical care. METHODS: HWC is an ongoing, structured digital 12-month program based on acceptance and commitment therapy. It includes weekly training sessions focused on lifestyle, general health, and psychological factors. Participants received remote one-on-one support from a personal coach. In this real-life, single-arm, prospective cohort study, we examined the total weight loss, weight loss profiles, and variables associated with weight loss success and program retention in 1189 adults (963 women) with a BMI >25 kg/m² among participants of the program between October 2016 and March 2019. Absolute (kg) and relative (%) weight loss from the baseline were the primary outcomes. We also examined the weight loss profiles, clustered based on the dynamic time-warping distance, and the possible variables associated with greater weight loss success and program retention. We compared different groups using the Mann-Whitney test or Kruskal-Wallis test for continuous variables and the chi-squared test for categorical variables. We analyzed changes in medication using the McNemar test. RESULTS: Among those having reached the 12-month time point (n=173), the mean weight loss was 4.6% (SE 0.5%), with 43% (n=75) achieving clinically relevant weight loss (≥5%). Baseline BMI ≥40 kg/m² was associated with a greater weight loss than a lower BMI (mean 6.6%, SE 0.9%, vs mean 3.2%, SE 0.6%; P=.02). In addition, more frequent weight reporting was associated with greater weight loss. No significant differences in weight loss were observed according to sex, age, baseline disease, or medication use. The total dropout rate was 29.1%. Dropouts were slightly younger than continuers (47.2, SE 0.6 years vs 49.2, SE 0.4 years; P=.01) and reported their weight less frequently (3.0, SE 0.1 entries per month vs 3.3, SE 0.1 entries per month; P<.001). CONCLUSIONS: A comprehensive web-based program such as HWC is a potential addition to the repertoire of obesity management in a clinical setting. Heavier patients lost more weight, but weight loss success was otherwise independent of baseline characteristics.

Long-term blood metal ion levels and clinical outcome after Birmingham hip arthroplasty.

BACKGROUND AND OBJECTIVE: Our aim was to assess long-term metal ion level changes and clinical outcome in patients with a Birmingham hip arthroplasty. METHODS: For the purpose of this study, we identified all BHR hip resurfacing arthroplasty (HRA) and total hip arthroplasty (THA) operations performed in Turku University Hospital. A random coefficient model was used to compare the change between the first and last metal ion measurement. A Kaplan-Meier estimator was used to assess the survivorship of the BHR HRA and BHR THA with metal related adverse events (pseudotumor, elevated metal ions above the safe upper limit, revision due to metallosis), or revision due to any reason as endpoints with 95% confidence intervals (CIs). RESULTS: BHR HRA was used in 274 hips (233 patients). In addition, we identified 38 BHR-Synergy THAs (38 patients). Operations were performed between 2003 and 2010. Median follow-up time was 14 years for BHR HRA (range: 0.6-17) and 11 years for BHR THA (range: 4.7-13). In the BHR HRA group, geometric means of Cr and Co levels decreased from 2.1 to 1.6 ppb and 2.4 to 1.5 ppb, respectively, during a 3.0-year measurement interval. Metal ion levels in the BHR THA group did not show notable increase. The survivorship of BHR HRA was 66% in 16 years and 34% for BHR THA at 12 years for any metal-related adverse event. CONCLUSIONS: Patients with a Birmingham hip device do not seem to benefit from frequent repeated metal ion measurements. The amount of patients with metal-related adverse events was relatively high, but many of them did not require surgery.

Repeated metal ion measurements and long-term outcome of Durom/MMC total hip arthroplasty.

Background and purpose - Data regarding long-term behavior of metal ion levels in metal-on-metal total hip arthroplasty (MoM THA) patients is scarce. Therefore, we assessed whether there is any change in whole blood (WB) chromium (Cr), and cobalt (Co) ion measurements in Durom and MMC MoM THA patients over time. The secondary aim was to report the clinical outcomes using these devices in a single district. Patients and methods - Durom and MMC cups were used in 249 MoM THAs from 2005 to 2011 in our district. Median follow-up time was 12 years for Durom THA (interquartile range [IQR] = 3) and 9 years for MMC THA (IQR = 1). A random coefficient model was used to compare individual differences in repeated WB Cr and Co ion measurements. The Kaplan-Meier estimator was used to analyze implant survival with any reason for revision as the endpoint. Results - Geometric means of Cr in Durom THA and MMC THA patients decreased from 2.2 ppb (geometric standard deviation [SD] = 1.9) to 1.5 ppb (geometric SD = 2.5, p< 0.001) and from 1.8 ppb (geometric SD = 1.8) to 1.1 ppb (geometric SD = 2.8, p = 0.01) respectively. The geometric means of Co values remained unchanged. The 10-year survival of Durom THA was 82%, and that of MMC THA 89% for any revision reason as endpoint. Interpretation - WB Cr levels decreased over time, and Co levels remained unchanged at long-term follow-up. Despite this we recommend continuing the follow-up of these devices due to relatively low implant survival.

Improved risk prediction of chemotherapy-induced neutropenia-model development and validation with real-world data.

BACKGROUND: The existing risk prediction models for chemotherapy-induced febrile neutropenia (FN) do not necessarily apply to real-life patients in different healthcare systems and the external validation of these models are often lacking. Our study evaluates whether a machine learning-based risk prediction model could outperform the previously introduced models, especially when validated against real-world patient data from another institution not used for model training. METHODS: Using Turku University Hospital electronic medical records, we identified all patients who received chemotherapy for non-hematological cancer between the years 2010 and 2017 (N = 5879). An experimental surrogate endpoint was first-cycle neutropenic infection (NI), defined as grade IV neutropenia with serum C-reactive protein >10 mg/l. For predicting the risk of NI, a penalized regression model (Lasso) was developed. The model was externally validated in an independent dataset (N = 4594) from Tampere University Hospital. RESULTS: Lasso model accurately predicted NI risk with good accuracy (AUROC 0.84). In the validation cohort, the Lasso model outperformed two previously introduced, widely approved models, with AUROC 0.75. The variables selected by Lasso included granulocyte colony-stimulating factor (G-CSF) use, cancer type, pre-treatment neutrophil and thrombocyte count, intravenous treatment regimen, and the planned dose intensity. The same model predicted also FN, with AUROC 0.77, supporting the validity of NI as an endpoint. CONCLUSIONS: Our study demonstrates that real-world NI risk prediction can be improved with machine learning and that every difference in patient or treatment characteristics can have a significant impact on model performance. Here we outline a novel, externally validated approach which may hold potential to facilitate more targeted use of G-CSFs in the future.

scShaper: an ensemble method for fast and accurate linear trajectory inference from single-cell RNA-seq data.

MOTIVATION: Computational models are needed to infer a representation of the cells, i.e. a trajectory, from single-cell RNA-sequencing data that model cell differentiation during a dynamic process. Although many trajectory inference methods exist, their performance varies greatly depending on the dataset and hence there is a need to establish more accurate, better generalizable methods. RESULTS: We introduce scShaper, a new trajectory inference method that enables accurate linear trajectory inference. The ensemble approach of scShaper generates a continuous smooth pseudotime based on a set of discrete pseudotimes. We demonstrate that scShaper is able to infer accurate trajectories for a variety of trigonometric trajectories, including many for which the commonly used principal curves method fails. A comprehensive benchmarking with state-of-the-art methods revealed that scShaper achieved superior accuracy of the cell ordering and, in particular, the differentially expressed genes. Moreover, scShaper is a fast method with few hyperparameters, making it a promising alternative to the principal curves method for linear pseudotemporal ordering. AVAILABILITY AND IMPLEMENTATION: scShaper is available as an R package at https://github.com/elolab/scshaper. The test data are available at https://doi.org/10.5281/zenodo.5734488. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Stable Iterative Variable Selection.

MOTIVATION: The emergence of datasets with tens of thousands of features, such as high-throughput omics biomedical data, highlights the importance of reducing the feature space into a distilled subset that can truly capture the signal for research and industry by aiding in finding more effective biomarkers for the question in hand. A good feature set also facilitates building robust predictive models with improved interpretability and convergence of the applied method due to the smaller feature space. RESULTS: Here, we present a robust feature selection method named Stable Iterative Variable Selection (SIVS) and assess its performance over both omics and clinical data types. As a performance assessment metric, we compared the number and goodness of the selected feature using SIVS to those selected by Least Absolute Shrinkage and Selection Operator regression. The results suggested that the feature space selected by SIVS was, on average, 41% smaller, without having a negative effect on the model performance. A similar result was observed for comparison with Boruta and caret RFE. AVAILABILITY AND IMPLEMENTATION: The method is implemented as an R package under GNU General Public License v3.0 and is accessible via Comprehensive R Archive Network (CRAN) via https://cran.r-project.org/package=sivs. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Risk factors for prosthetic joint infections following total hip arthroplasty based on 33,337 hips in the Finnish Arthroplasty Register from 2014 to 2018.

Background and purpose - Periprosthetic joint infection (PJI) is a devastating complication and more information on risk factors for PJI is required to find measures to prevent infections. Therefore, we assessed risk factors for PJI after primary total hip arthroplasty (THA) in a large patient cohort.Patients and methods - We analyzed 33,337 primary THAs performed between May 2014 and January 2018 based on the Finnish Arthroplasty Register (FAR). Cox proportional hazards regression was used to estimate hazard ratios with 95% confidence intervals (CI) for first PJI revision operation using 25 potential patient- and surgical-related risk factors as covariates.Results - 350 primary THAs were revised for the first time due to PJI during the study period. The hazard ratios for PJI revision in multivariable analysis were 2.0 (CI 1.3-3.2) for ASA class II and 3.2 (2.0-5.1) for ASA class III-IV compared with ASA class I, 1.4 (1.1-1.7) for bleeding > 500 mL compared with < 500 mL, 0.4 (0.2-0.7) for ceramic-on-ceramic bearing couple compared with metal-on-polyethylene and for the first 3 postoperative weeks, 3.0 (1.6-5.6) for operation time of > 120 minutes compared with 45-59 minutes, and 2.6 (1.4-4.9) for simultaneous bilateral operation. In the univariable analysis, hazard ratios for PJI revision were 2.3 (1.7-3.3) for BMI of 31-35 and 5.0 (3.5-7.1) for BMI of > 35 compared with patients with BMI of 21-25.Interpretation - We found several modifiable risk factors associated with increased PJI revision risk after THA to which special attention should be paid preoperatively. In particular, high BMI may be an even more prominent risk factor for PJI than previously assessed.

Preoperative Risk Prediction Models for Short-Term Revision and Death After Total Hip Arthroplasty: Data from the Finnish Arthroplasty Register.

Because of the increasing number of total hip arthroplasties (THAs), even a small proportion of complications after the operation can lead to substantial individual difficulties and health-care costs. The aim of this study was to develop simple-to-use risk prediction models to assess the risk of the most common reasons for implant failure to facilitate clinical decision-making and to ensure long-term survival of primary THAs. METHODS: We analyzed patient and surgical data reported to the Finnish Arthroplasty Register (FAR) on 25,919 primary THAs performed in Finland between May 2014 and January 2018. For the most frequent adverse outcomes after primary THA, we developed multivariable Lasso regression models based on the data of the randomly selected training cohort (two-thirds of the data). The performances of all models were validated using the remaining, independent test set consisting of 8,640 primary THAs (one-third of the data) not used for building the models. RESULTS: The most common outcomes within 6 months after the primary THA were revision operations due to periprosthetic joint infection (1.1%), dislocation (0.7%), or periprosthetic fracture (0.5%), and death (0.7%). For each of these outcomes, Lasso regression identified subsets of variables required for accurate risk predictions. The highest discrimination performance, in terms of area under the receiver operating characteristic curve (AUROC), was observed for death (0.84), whereas the performance was lower for revisions due to periprosthetic joint infection (0.68), dislocation (0.64), or periprosthetic fracture (0.65). CONCLUSIONS: Based on the small number of preoperative characteristics of the patient and modifiable surgical parameters, the developed risk prediction models can be easily used to assess the risk of revision or death. All developed models hold the potential to aid clinical decision-making, ultimately leading to improved clinical outcomes. LEVEL OF EVIDENCE: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge.

Consumer wearables and sensors are a rich source of data about patients' daily disease and symptom burden, particularly in the case of movement disorders like Parkinson's disease (PD). However, interpreting these complex data into so-called digital biomarkers requires complicated analytical approaches, and validating these biomarkers requires sufficient data and unbiased evaluation methods. Here we describe the use of crowdsourcing to specifically evaluate and benchmark features derived from accelerometer and gyroscope data in two different datasets to predict the presence of PD and severity of three PD symptoms: tremor, dyskinesia, and bradykinesia. Forty teams from around the world submitted features, and achieved drastically improved predictive performance for PD status (best AUROC = 0.87), as well as tremor- (best AUPR = 0.75), dyskinesia- (best AUPR = 0.48) and bradykinesia-severity (best AUPR = 0.95).

Discrete element and finite element methods provide similar estimations for hip joint contact mechanics during walking gait.

Finite element analysis (FEA) provides a powerful approach for estimating the in-vivo loading characteristics of the hip joint during various locomotory and functional activities. However, time-consuming procedures, such as the generation of high-quality FE meshes and setup of FE simulation, typically make the method impractical for rapid applications which could be used in clinical routine. Alternatively, discrete element analysis (DEA) has been developed to quantify mechanical conditions of the hip joint in a fraction of time compared to FEA. Although DEA has proven effective in the estimation of contact stresses and areas in various complex applications, it has not yet been well characterised by its ability to evaluate contact mechanics for the hip joint during gait cycle loading using data from several individuals. The objective of this work was to compare DEA modelling against well-established FEA for analysing contact mechanics of the hip joint during walking gait. Subject-specific models were generated from magnetic resonance images of the hip joints in five asymptomatic subjects. The DEA and FEA models were then simulated for 13 loading time-points extracted from a full gait cycle. Computationally, DEA was substantially more efficient compared to FEA (simulation times of seconds vs. hours). The DEA and FEA methods had similar predictions for contact pressure distribution for the hip joint during normal walking. In all 13 simulated loading time-points across five subjects, the maximum difference in average contact pressures between DEA and FEA was within ±0.06 MPa. Furthermore, the difference in contact area ratio computed using DEA and FEA was less than ±6%.