Dataset Information

Predicting Total Knee Replacement from Symptomology and Radiographic Structural Change Using Artificial Neural Networks-Data from the Osteoarthritis Initiative (OAI).

ABSTRACT: The aim of the study was to longitudinally investigate symptomatic and structural factors prior to total knee replacement (TKR) surgery in order to identify influential factors that can predict a patient's need for TKR surgery. In total, 165 participants (60% females; 64.5 ± 8.4 years; 29.7 ± 4.7 kg/m2) receiving a TKR in any of both knees within a four-year period were analyzed. Radiographic change, knee pain, knee function and quality of life were annually assessed prior to the TKR procedure. Self-learning artificial neural networks were applied to identify driving factors for the surgical procedure. Significant worsening of radiographic structural change was observed prior to TKR (p ? 0.0046), whereas knee symptoms (pain, function, quality of life) worsened significantly only in the year prior to the TKR procedure. By using our prediction model, we were able to predict correctly 80% of the classified individuals to undergo TKR surgery with a positive predictive value of 84% and a negative predictive value of 73%. Our prediction model offers the opportunity to assess a patient's need for TKR surgery two years in advance based on easily available patient data and could therefore be used in a primary care setting.

SUBMITTER: Heisinger S

PROVIDER: S-EPMC7288322 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting Total Knee Replacement from Symptomology and Radiographic Structural Change Using Artificial Neural Networks-Data from the Osteoarthritis Initiative (OAI).

Heisinger Stephan S Hitzl Wolfgang W Hobusch Gerhard M GM Windhager Reinhard R Cotofana Sebastian S

Journal of clinical medicine 20200501 5

The aim of the study was to longitudinally investigate symptomatic and structural factors prior to total knee replacement (TKR) surgery in order to identify influential factors that can predict a patient's need for TKR surgery. In total, 165 participants (60% females; 64.5 ± 8.4 years; 29.7 ± 4.7 kg/m<sup>2</sup>) receiving a TKR in any of both knees within a four-year period were analyzed. Radiographic change, knee pain, knee function and quality of life were annually assessed prior to the TKR ...[more]

PMID: 32369985

Similar Datasets

Project description:To evaluate the influence of the mtDNA haplogroups on knee osteoarthritis progression in Osteoarthritis Initiative (OAI) participants through longitudinal data from radiographs and magnetic resonance imaging (MRI).Four-year knee osteoarthritis progression was analyzed as increase in Kellgren and Lawrence (KL) grade, in addition to increase in OARSI atlas grade for joint space narrowing (JSN), osteophytes and subchondral sclerosis in the tibia medial compartment of 891 Caucasian individuals from the progression subcohort. The influence of the haplogroups on the rate of structural progression was also assessed as the four-year change in minimum joint space width (mJSW in millimetres) in both knees of (n?=?216) patients with baseline unilateral medial-tibiofemoral JSN. Quantitative cartilage measures from longitudinal MRI data were those related to cartilage thickness and volume with a 24 month follow-up period (n?=?381).During the four-year follow-up period, knee OA patients with the haplogroup T showed the lowest increase in KL grade (Hazard Risk [HR]?=?0.499; 95% Confidence Interval [CI]: 0.261-0.819; p<0.05) as well as the lowest cumulative probability of progression for JSN (HR?=?0.547; 95% CI: 0.280-0.900; p<0.05), osteophytes (HR?=?0.573; 95% CI: 0.304-0.893; p<0.05) and subchondral sclerosis (HR?=?0.549; 95% CI: 0.295-0.884; p<0.05). They also showed the lowest decline in mJSW (standardized response means (SRM)?=?-0.39; p?=?0.037) in those knees without baseline medial JSN (no-JSN knees). Normalized cartilage volume loss was significantly lower in patients carrying the haplogroup T at medial tibia femoral (SRM?=?-0.33; p?=?0.023) and central medial femoral (SRM?=?-0.27; p?=?0.031) compartments. Cartilage thickness loss was significantly lower in carriers of haplogroup T at central medial tibia-femoral (SRM?=?-0.42; p?=?0.011), medial tibia femoral (SRM?=?-0.32; p?=?0.018), medial tibia anterior (SRM?=?+0.31; p?=?0.013) and central medial femoral (SRM?=?-0.19; p?=?0.013) compartments.Mitochondrial genome seems to play a role in the progression of knee osteoarthritis. mtDNA variation could improve identification of patients predisposed to faster or severe progression of the disease.

Project description:Background The methods for assessing knee osteoarthritis (OA) do not provide enough comprehensive information to make robust and accurate outcome predictions. Purpose To develop a deep learning (DL) prediction model for risk of OA progression by using knee radiographs in patients who underwent total knee replacement (TKR) and matched control patients who did not undergo TKR. Materials and Methods In this retrospective analysis that used data from the OA Initiative, a DL model on knee radiographs was developed to predict both the likelihood of a patient undergoing TKR within 9 years and Kellgren-Lawrence (KL) grade. Study participants included a case-control matched subcohort between 45 and 79 years. Patients were matched to control patients according to age, sex, ethnicity, and body mass index. The proposed model used a transfer learning approach based on the ResNet34 architecture with sevenfold nested cross-validation. Receiver operating characteristic curve analysis and conditional logistic regression assessed model performance for predicting probability and risk of TKR compared with clinical observations and two binary outcome prediction models on the basis of radiographic readings: KL grade and OA Research Society International (OARSI) grade. Results Evaluated were 728 participants including 324 patients (mean age, 64 years ± 8 [standard deviation]; 222 women) and 324 control patients (mean age, 64 years ± 8; 222 women). The prediction model based on DL achieved an area under the receiver operating characteristic curve (AUC) of 0.87 (95% confidence interval [CI]: 0.85, 0.90), outperforming a baseline prediction model by using KL grade with an AUC of 0.74 (95% CI: 0.71, 0.77; P < .001). The risk for TKR increased with probability that a person will undergo TKR from the DL model (odds ratio [OR], 7.7; 95% CI: 2.3, 25; P < .001), KL grade (OR, 1.92; 95% CI: 1.17, 3.13; P = .009), and OARSI grade (OR, 1.20; 95% CI: 0.41, 3.50; P = .73). Conclusion The proposed deep learning model better predicted risk of total knee replacement in osteoarthritis than did binary outcome models by using standard grading systems. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Richardson in this issue.

Project description:Objectives To evaluate the impact of total knee replacement on quality of life in people with knee osteoarthritis and to estimate associated differences in lifetime costs and quality adjusted life years (QALYs) according to use by level of symptoms.Design Marginal structural modeling and cost effectiveness analysis based on lifetime predictions for total knee replacement and death from population based cohort data.Setting Data from two studies-Osteoarthritis Initiative (OAI) and the Multicenter Osteoarthritis Study (MOST)-within the US health system.Participants 4498 participants with or at high risk for knee osteoarthritis aged 45-79 from the OAI with no previous knee replacement (confirmed by baseline radiography) followed up for nine years. Validation cohort comprised 2907 patients from MOST with two year follow-up.Intervention Scenarios ranging from current practice, defined as total knee replacement practice as performed in the OAI (with procedural rates estimated by a prediction model), to practice limited to patients with severe symptoms to no surgery.Main outcome measures Generic (SF-12) and osteoarthritis specific quality of life measured over 96 months, model based QALYs, costs, and incremental cost effectiveness ratios over a lifetime horizon.Results In the OAI, total knee replacement showed improvements in quality of life with small absolute changes when averaged across levels of confounding variables: 1.70 (95% uncertainty interval 0.26 to 3.57) for SF-12 physical component summary (PCS); -10.69 (-13.39 to -8.01) for Western Ontario and McMaster Universities arthritis index (WOMAC); and 9.16 (6.35 to 12.49) for knee injury and osteoarthritis outcome score (KOOS) quality of life subscale. These improvements became larger with decreasing functional status at baseline. Provision of total knee replacement to patients with SF-12 PCS scores <35 was the optimal scenario given a cost effectiveness threshold of $200 000/QALY, with cost savings of $6974 ($5789 to $8269) and a minimal loss of 0.008 (-0.056 to 0.043) QALYs compared with current practice. These findings were reproduced among patients with knee osteoarthritis from the MOST cohort and were robust against various scenarios including increased rates of total knee replacement and mortality and inclusion of non-healthcare costs but were sensitive to increased deterioration in quality of life without surgery. In a threshold analysis, total knee replacement would become cost effective in patients with SF-12 PCS scores ≤40 if the associated hospital admission costs fell below $14 000 given a cost effectiveness threshold of $200 000/QALY.Conclusion Current practice of total knee replacement as performed in a recent US cohort of patients with knee osteoarthritis had minimal effects on quality of life and QALYs at the group level. If the procedure were restricted to more severely affected patients, its effectiveness would rise, with practice becoming economically more attractive than its current use.

Project description:BackgroundKnee osteoarthritis (OA) worsens health-related quality of life (HRQoL) but the symptom pathway varies from person to person. We aimed to identify groups of people with knee OA or at its increased risk whose HRQoL changed similarly. Our secondary aim was to evaluate if patient-related characteristics, incidence of knee replacement (KR) and prevalence of pain medication use differed between the identified HRQoL trajectory groups.MethodsEight-year follow-up data of 3053 persons with mild knee OA or at increased risk were obtained from the public Osteoarthritis Initiative (OAI) database. Group-based trajectory modeling was used to identify patterns of experiencing a decrease of ≥10 points (Minimal Important Change, MIC) in the Quality of Life subscale of the Knee injury and Osteoarthritis Outcome Score compared to baseline. Multinomial logistic regression, Cox regression and generalized estimating equation models were used to study secondary aims.ResultsFour HRQoL trajectory groups were identified. Persons in the 'no change' group (62.9%) experienced no worsening in HRQoL. 'Rapidly' (9.5%) and 'slowly' worsening (17.1%) groups displayed an increasing probability of experiencing the MIC in HRQoL. The fourth group (10.4%) had 'improving' HRQoL. Female gender, higher body mass index, smoking, knee pain, and lower income at baseline were associated with belonging to the 'rapidly worsening' group. People in 'rapidly' (hazard ratio (HR) 6.2, 95% confidence interval (CI) 3.6-10.7) and 'slowly' worsening (HR 3.4, 95% CI 2.0-5.9) groups had an increased risk of requiring knee replacement. Pain medication was more rarely used in the 'no change' than in the other groups.ConclusionsHRQoL worsening was associated with several risk factors; surgical and pharmacological interventions were more common in the poorer HRQoL trajectory groups indicating that HRQoL does reflect the need for OA treatment. These findings may have implications for targeting interventions to specific knee OA patient groups.

Project description:OBJECTIVE:To determine whether thigh muscle strength predicts the risk of undergoing knee replacement surgery, independent of radiographic severity of osteoarthritis and pain. METHODS:Participants in the Osteoarthritis Initiative study who had received a knee replacement between the 12-month and 60-month follow-up visits (cases) were each matched with 1 control subject (who did not receive a knee replacement over 60 months) for age, sex, height, body mass index, baseline radiographic stage, and location of joint space narrowing. Isometric knee extensor and flexor strength was recorded biennially. The strength examination prior to knee replacement (?2 years) was termed time 0, that 2 years prior to time 0 was termed time -2, and that 4 years prior to time 0 was termed time -4. Muscle strength in patients and controls was compared using paired t-tests and conditional logistic regression analysis adjusted for pain. RESULTS:One hundred thirty-six participants (60% women, mean?±?SD age 65?±?9 years, body mass index 29?±?4 kg/m(2) ) received a knee replacement during follow-up, had strength data for at least time 0, and had a matched control. Knee extensor strength at time 0 (primary outcome measure) was significantly lower in female patients compared with controls (P < 0.001, pain-adjusted odds ratio [ORadj ] 1.72, 95% confidence interval 1.16-2.56), but no significant difference was observed in men. Results were similar for knee flexor strength at time 0 and for longitudinal change in extensor and flexor strength between time -2 and time 0. Thigh muscle strength at time -2 or time -4, or change between time -4 and time -2, did not predict the risk of undergoing knee replacement surgery in men or women. CONCLUSION:Thigh muscle strength predicted the risk of undergoing knee replacement surgery in women, but not in men. The results of this study may identify a window during which the risk of undergoing knee replacement surgery in women can be modified.

Dataset Information

Predicting Total Knee Replacement from Symptomology and Radiographic Structural Change Using Artificial Neural Networks-Data from the Osteoarthritis Initiative (OAI).

Publications

Predicting Total Knee Replacement from Symptomology and Radiographic Structural Change Using Artificial Neural Networks-Data from the Osteoarthritis Initiative (OAI).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets