Posts

The application of machine learning methods for predicting the progression of adolescent idiopathic scoliosis: a systematic review

Lening Li, Man-Sang Wong 

Skeletal Radiol. 2024 Aug;53(8):1517-1528.doi: 10.1007/s00256-024-04592-9. Epub 2024 Feb 21.

Abstract

Predicting curve progression during the initial visit is pivotal in the disease management of patients with adolescent idiopathic scoliosis (AIS)-identifying patients at high risk of progression is essential for timely and proactive interventions. Both radiological and clinical factors have been investigated as predictors of curve progression. With the evolution of machine learning technologies, the integration of multidimensional information now enables precise predictions of curve progression. This review focuses on the application of machine learning methods to predict AIS curve progression, analyzing 15 selected studies that utilize various machine learning models and the risk factors employed for predictions. Key findings indicate that machine learning models can provide higher precision in predictions compared to traditional methods, and their implementation could lead to more personalized patient management. However, due to the model interpretability and data complexity, more comprehensive and multi-center studies are needed to transition from research to clinical practice.

Keywords: Adolescent idiopathic scoliosis; Machine learning; Prediction.

https://pubmed.ncbi.nlm.nih.gov/39118179/

Distances and angles in standing long-leg radiographs: comparing conventional radiography, digital radiography, and EOS

Christof Birkenmaier, Louise Levrard , Carolin Melcher , Bernd Wegener, Jens Ricke, Boris M Holzapfel, Andrea Baur-Melnyk , Dirk Mehrens 

Skeletal Radiol. 2024 Aug;53(8):1517-1528.doi: 10.1007/s00256-024-04592-9. Epub 2024 Feb 21.

Abstract

Objective: Distances and angles measured from long-leg radiographs (LLR) are important for surgical decision-making. However, projectional radiography suffers from distortion, potentially generating differences between measurement and true anatomical dimension. These phenomena are not uniform between conventional radiography (CR) digital radiography (DR) and fan-beam technology (EOS). We aimed to identify differences between these modalities in an experimental setup.

Materials and methods: A hemiskeleton was stabilized using an external fixator in neutral, valgus and varus knee alignment. Ten images were acquired for each alignment and each modality: one CR setup, two different DR systems, and an EOS. A total of 1680 measurements were acquired and analyzed.

Results: We observed great differences for dimensions and angles between the 4 modalities. Femoral head diameter measurements varied in the range of > 5 mm depending on the modality, with EOS being the closest to the true anatomical dimension. With functional leg length, a difference of 8.7% was observed between CR and EOS and with the EOS system being precise in the vertical dimension on physical-technical grounds, this demonstrates significant projectional magnification with CR-LLR. The horizontal distance between the medial malleoli varied by 20 mm between CR and DR, equating to 21% of the mean.

Conclusions: Projectional distortion resulting in variations approaching 21% of the mean indicate, that our confidence on measurements from standing LLR may not be justified. It appears likely that among the tested equipment, EOS-generated images are closest to the true anatomical situation most of the time.

Keywords: Cone-beam; Conventional radiography; Digital radiography; Distortion; EOS; Fan-beam; Lower extremity; Projectional distortion; Slot-scanner; Valgus; Varus.

https://pubmed.ncbi.nlm.nih.gov/38378861/

Immediate vs Gradual Brace Weaning Protocols in Adolescent Idiopathic Scoliosis: A Randomized Clinical Trial

Prudence Wing Hang Cheung, Oi Kiu Olivia Chan, Hao Wu, Marcus Kin Long Lai, Lester Po Kwan Wong, Shiyu Tang, Jason Pui Yin Cheung 

JAMA Pediatr. 2024 Jul 1;178(7):657-668.doi: 10.1001/jamapediatrics.2024.1484

Abstract

Importance: Lack of evidence and consensus for brace weaning protocol in adolescent idiopathic scoliosis (AIS) results in clinicians prescribing gradual weaning in the hope of avoiding curve deterioration after weaning. However, gradual weaning contributes to prolonged brace wear, which can affect spinal stiffness and health-related quality of life (HRQoL).

Objective: To determine whether gradual weaning results in better curve magnitude and truncal balance maintenance after brace weaning vs immediate brace removal for patients with AIS.

Design, setting, and participants: This was an open-labeled randomized clinical trial commenced in April 2017 with 24-month follow-up completed in January 2023. Outcome assessors were masked to weaning protocol assigned. The study took place at a territory-wide tertiary scoliosis clinic serving the largest number of referrals in the local population. Patients with AIS ready to wean off of brace wear were eligible (402 were screened; 33 were excluded [15 for <18 hours/day of brace-wear compliance before weaning, 11 were treated with Milwaukee brace, and 7 declined to participate]; and 369 were included), and those who were treated with a custom molded thoracolumbosacral orthosis and had reached skeletal maturity were consecutively recruited.

Interventions: Patients were randomized to gradual weaning protocol (n = 176) with an additional 6 months of nighttime wear before completely stopping or immediate weaning protocol (n = 193) with immediate brace removal at recruitment.

Main outcomes and measures: Changes in major curve Cobb angle and truncal balance from the time of weaning to 6-month, 12-month, and 24-month follow-up. HRQoL was also assessed using the refined Scoliosis Research Society 22-item and EuroQol 5-dimension questionnaires.

Results: A total of 369 patients (mean [SD] age, 14.9 [1.1] years; 304 [83.4%] girls) were randomized with 284 (77.0%) completing 24-month longitudinal follow-up. Immediate and gradual weaning groups had no significant differences in change of major Cobb angle at postweaning 6-month (difference, -0.6°; 95% CI, -1.4 to 0.2; P = .17), 12-month (difference, -0.3°; 95% CI, -1.2 to 0.6; P = .47), and 24-month (difference, -0.3°; 95% CI, -1.2 to 0.7; P = .60) follow-up. The number of curve progression, nonprogression, and rebound cases were comparable (χ22 = 2.123; P = .35). Postweaning changes in truncal balance and HRQoL demonstrated no significant differences between groups.

Conclusions: Gradual weaning did not demonstrate superiority to immediate weaning with predefined criteria of Cobb angle and truncal balance maintenance and HRQoL after brace weaning. Gradual and immediate weaning achieved very similar maintenance of brace outcomes in AIS. We therefore recommend the consideration of immediate brace weaning, which aims to benefit patients with earlier time for increased exercises and activity level.

Trial registration: ClinicalTrials.gov Identifier: NCT03329716.

https://pubmed.ncbi.nlm.nih.gov/38829664/

Development of a Motion-Based Video Game for Postural Training: A Feasibility Study on Older Adults With Adult Degenerative Scoliosis

Frances K W Wan, Alex T H Mak, Claire W Y Chung, Joanne Y

EEE Trans Neural Syst Rehabil Eng. 2024:32:2106-2113. doi: 10.1109/TNSRE.2024.3398029 Epub 2024 Jun 7

Abstract

Forward sagittal alignment affects physical performance, is associated with pain and impacts the health-related quality of life of the elderly. Interventions that help seniors to improve sagittal balance are needed to inhibit the progression of pain and disability.

A motion-sensing video game (active game) is developed in this study to monitor sitting and standing postures in real-time and facilitate the postural learning process by using optical sensors to measure body movement and a video game to provide visual feedback.
Ten female subjects (mean age: 60.0 ± 5.2 years old; mean BMI: 21.4 ± 1.9) with adult degenerative scoliosis (mean major Cobb’s angle: 38.1° ± 22.7°) participate in a 6-week postural training programme with three one-hour postural training sessions a week.
Eleven body alignment measurements of their perceived “ideal” sitting and standing postures are obtained before and after each training session to evaluate the effectiveness of postural learning with the game.
The participants learn to sit and stand with increased sagittal alignment with a raised chest and more retracted head position. The forward shift of their head and upper body is significantly reduced after each training session.
Although this immediate effect only partially sustained after the 6-week program, the participants learned to adjust their shoulder and pelvis level for a better lateral alignment in standing.
The proposed postural training system, which is presented as a gameplay with real-time visual feedback, can effectively help players to improve their postures.
This pilot feasibility study explores the development and initial assessment of a motion-based video game designed for postural training in older adults with adult degenerative scoliosis, and demonstrates the usability and benefits of active gameplay in motor training.

https://pubmed.ncbi.nlm.nih.gov/38717877/

Factors Influencing Optimal Bracing Compliance in Adolescent Idiopathic Scoliosis: A Single Center Prospective Cohort Study

Tomoyuki Asadasa, Toshiaki Kotani, Tsuyoshi Sakuma, Yasushi Iijima, Kotaro Sakashita, Yosuke Ogata, 
Tsutomu Akazawa, Shohei Minami, Seiji Ohtori, Masao Koda, Masashi Yamazaki

Spine (Phila Pa 1976). 2024 Apr 10.doi: 10.1097/BRS.0000000000004997

Abstract

Study design: Retrospective cohort study.

Objective: To identify factors contributing to optimal bracing compliance in adolescent idiopathic scoliosis (AIS).

Summary of background data: Poor brace compliance is a key factor affecting brace treatment success in AIS. Predictive factors influencing optimal brace compliance to achieve brace treatment success remain unknown.

Materials and methods: This study included AIS patients, aged 10-15, with a Cobb angle of 20-40 degrees. Demographics data, radiographic assessments, and patient-reported outcomes (including the SRS-22r patient questionnaire) were collected. Brace compliance was monitored using in-brace thermometers, defining optimal bracing time as more than 18 hours/day. Multivariable logistic regression analysis was employed to identify predictors of optimal bracing time from the demographic and patient- reported outcomes score before bracing.

Results: Among 122 patients, 59.0% achieved optimal bracing time by six months. The achieved group indicated higher scores in satisfaction domain before bracing (3.3±0.7 vs. 3.1±0.6; P=0.034). Multivariable logistic regression analysis demonstrated that Satisfaction domain before bracing was an independent factor associated with achievement of the optimal bracing time (OR 1.97 [95%CI 1.00 – 3.89], P=0.049). The model with bracing at 1-month follow-up also demonstrated the bracing at 1-month was a significant factor (OR 1.52 [95%CI 1.30 – 1.79], P<0.001).

Conclusion: Optimal bracing compliance in AIS is significantly influenced by pre-bracing satisfaction and brace compliance at earlier time point. These findings highlight the need to address psychological factors and early compliance in AIS bracing treatment. SRS-22r can be useful to identify the need for psychological support.

https://pubmed.ncbi.nlm.nih.gov/38597189/

Development and validation of AI-based automatic measurement of coronal Cobb angles in degenerative scoliosis using sagittal lumbar MRI

Jasper W van der Graaf, Miranda L van Hooff, Bram van Ginneken, Merel Huisman, Matthieu Rutten, Dominique Lamers, Nikolas Lessmann, Marinus de Kleuver 
Eur Radiol 2024 Feb 21.doi: 10.1007/s00330-024-10616-8

Abstract

Objectives: Severity of degenerative scoliosis (DS) is assessed by measuring the Cobb angle on anteroposterior radiographs. However, MRI images are often available to study the degenerative spine. This retrospective study aims to develop and evaluate the reliability of a novel automatic method that measures coronal Cobb angles on lumbar MRI in DS patients.

Materials and methods: Vertebrae and intervertebral discs were automatically segmented using a 3D AI algorithm, trained on 447 lumbar MRI series. The segmentations were used to calculate all possible angles between the vertebral endplates, with the largest being the Cobb angle. The results were validated with 50 high-resolution sagittal lumbar MRI scans of DS patients, in which three experienced readers measured the Cobb angle. Reliability was determined using the intraclass correlation coefficient (ICC).

Results: The ICCs between the readers ranged from 0.90 (95% CI 0.83-0.94) to 0.93 (95% CI 0.88-0.96). The ICC between the maximum angle found by the algorithm and the average manually measured Cobb angles was 0.83 (95% CI 0.71-0.90). In 9 out of the 50 cases (18%), all readers agreed on both vertebral levels for Cobb angle measurement. When using the algorithm to extract the angles at the vertebral levels chosen by the readers, the ICCs ranged from 0.92 (95% CI 0.87-0.96) to 0.97 (95% CI 0.94-0.98).

Conclusion: The Cobb angle can be accurately measured on MRI using the newly developed algorithm in patients with DS. The readers failed to consistently choose the same vertebral level for Cobb angle measurement, whereas the automatic approach ensures the maximum angle is consistently measured.

Clinical relevance statement: Our AI-based algorithm offers reliable Cobb angle measurement on routine MRI for degenerative scoliosis patients, potentially reducing the reliance on conventional radiographs, ensuring consistent assessments, and therefore improving patient care.

Key points: • While often available, MRI images are rarely utilized to determine the severity of degenerative scoliosis. • The presented MRI Cobb angle algorithm is more reliable than humans in patients with degenerative scoliosis. • Radiographic imaging for Cobb angle measurements is mitigated when lumbar MRI images are available.

Keywords: Cobb angle; Deep learning; Magnetic resonance imaging; Scoliosis; Spine.

https://pubmed.ncbi.nlm.nih.gov/38383922/

Introduction to target trial emulation in rehabilitation: a systematic approach to emulate a randomized controlled trial using observational data

Pierre Côté, Stefano Negrini, Sabrina Donzelli, Carlotte Kiekens, Chiara Arienti, Maria G Ceravolo, Douglas P Gross, Irene Battel, Giorgio Ferriero,, Stefano G Lazzarini, Bernard Dan, Heather M Shearer, Jessica J Wong,; Participants in the 5th Cochrane Rehabilitation Methodological Meeting
Eur J Phys Rehabil Med. 2024 Feb;60(1):145-153.doi: 10.23736/S1973-9087.24.08435-1.

Abstract

Rehabilitation providers and policymakers need valid evidence to make informed decisions about the healthcare needs of the population. Whenever possible, these decisions should be informed by randomized controlled trials (RCTs). However, there are circumstances when evidence needs to be generated rapidly, or when RCTs are not ethical or feasible. These situations apply to studying the effects of complex interventions, including rehabilitation as defined by Cochrane Rehabilitation.
Therefore, we explore using the target trial emulation framework by Hernán and colleagues to obtain valid estimates of the causal effects of rehabilitation when RCTs cannot be conducted. Target trial emulation is a framework guiding the design and analysis of non-randomized comparative effectiveness studies using observational data, by emulating a hypothetical RCT.
In the context of rehabilitation, we outline steps for applying the target trial emulation framework using real world data, highlighting methodological considerations, limitations, potential mitigating strategies, and causal inference and counterfactual theory as foundational principles to estimating causal effects. Overall, we aim to strengthen methodological approaches used to estimate causal effects of rehabilitation when RCTs cannot be conducted.

https://pubmed.ncbi.nlm.nih.gov/38420907/

Adolescent idiopathic scoliosis: is there a relationship between Risser staging and the proximal humerus ossification system?

Calcagni Julián, Davies Néstor Ricardo, Remondino Rodrigo, Tello Carlos A, Piantoni Lucas, Galaretto Eduardo, Arispe Juan Pablo, Noel Mariano 
Spine Deform. 2024 Feb 5. doi: 10.1007/s43390-023-00812-9. 

Abstract

Purpose: To evaluate whether there is a mismatch between Risser staging and the proximal humerus ossification system (PHOS); and to analyze the correlation in the skeletal maturity stages between the two humeral epiphyses.

Methods: Data from patients aged 10 to 18 years with adolescent idiopathic scoliosis (AIS) seen between 2018 to 2021 were analyzed. In an anteroposterior (AP) spine radiograph the ossification process was evaluated using the Risser classification method and bilateral PHOS (if both humeral epiphyses were visualized). A mismatch between methods was defined as a Risser 0-1 (relatively skeletally immature) with a PHOS 4-5 (skeletally mature), or a Risser 2-5 (relatively skeletally mature) with a PHOS 1-3 (skeletally immature). The McNemar test was used to calculate the significance of the mismatch.

Results: A mismatch between Risser and PHOS stages was observed in 28.5% of 105 patients, which was statistically significant (p < 0.001). Of the 49 patients with a Risser 0-1, 55.1% (n = 27) had a PHOS 4-5. None of the patients with a Risser 2-5 had a PHOS 1-3. In the 47 patients in whom both humeri were visualized, the absolute correlation between the left and right PHOS values was 95.7%.

Conclusion: Of AIS patients who are relatively skeletally immature according to Risser staging, more than half may be skeletally mature when measured with PHOS. In patients with a Risser 0-1, it is recommended to measure skeletal maturity in an AP spine radiograph using the PHOS method, which may more accurately guide treatment decision-making, without the need to visualize both humeral epiphyses in this radiographic projection.

Level of evidence: IV.

Keywords: Adolescent idiopathic scoliosis; Peak height velocity; Proximal humerus ossification system; Risser.

https://pubmed.ncbi.nlm.nih.gov/38316729/

Heath-related quality of life and functional outcomes in patients with congenital or juvenile idiopathic scoliosis after an average follow-up of 25 years: a cohort study

Heemskerk, Nienke W Willigenburg , Ben E E M J Veraart, Eric W Bakker, René M Castelein, Mark C Altena, Diederik H R Kempen
Spine J. 2023 Nov 28:S1529-9430(23)03503-9.doi:10.1016/j. spinee.2023.11.012.

Abstract

Background context: Congenital and juvenile scoliosis are both early-onset deformities that develop before the age of 10. Children are treated to prevent curve progression and problems in adulthood such as back pain and a decreased quality of life but literature on long-term outcomes remains scarce.

Purpose: To evaluate the health-related quality of life (HRQoL) and potential disability of children with congenital scoliosis (CS) or juvenile idiopathic scoliosis (JIS) after a minimum of 20 years follow-up.

Study design: Comparative cohort study.

Patient sample: A consecutive cohort of CS and JIS patients were retrospectively identified from a single-center scoliosis database. Patients born between 1968 and 1981 and treated during skeletal growth were eligible for participation.

Outcome measures: HRQoL (SF-36, SRS-22r, ODI).

Methods: The primary aim was to evaluate the HRQoL of CS and JIS patients using the general SF-36 questionnaire. Both patient cohorts were compared with age-matched national norms. The secondary aim was to analyze the differences between conservatively and surgically treated patients using the scoliosis-specific Scoliosis Research Society-22r questionnaire (SRS-22r) and the Oswestry Disability Index (ODI). T-tests were used for statistical comparison.

Results: In total, 114 patients (67% of the eligible patients) completed the questionnaire, with a mean follow-up of 25.5±5.5 years after their final clinical follow-up. Twenty-nine patients with CS were included with a mean age of 44.4±3.8 years (79.3% female), and 85 patients with JIS with a mean age of 43.7±4.2 years (89.4% female). Of the SF-36 domains, only the vitality score (60.6±18.0 for CS and 58.1±17.6 for JIS cohort) and mental health score (70.0±18.4 for CS and 72.1±18.1 for JIS cohort) were significantly lower compared with the general population (68.6±19.3 for vitality, and 76.8±17.4 for mental health). These decreased scores were larger than the determined minimum clinically important difference threshold of 4.37. Surgically treated JIS patients had a significantly lower score on the SRS-22r pain domain than their non-surgically treated peers (3.6±0.9 vs. 4.1±0.7l p=.019). Surgically treated CS patients had a significantly higher score on the SRS-22r mental health domain than their non-surgically treated peers (4.3±0.5 vs. 3.5±1.0; p=.023). No significant differences were found in the other domains.

Conclusions: Except for vitality and mental health domains, congenital and juvenile idiopathic scoliosis patients treated during skeletal growth had similar HRQoL on most SF-36 domains in adulthood compared with national norms. Surgical treated JIS patients experienced more pain compared with brace treated patients, while braced CS patients had a significantly lower mental scores compared with surgical treated patients. These long-term outcomes are essential to inform patients and can guide shared decision-making between clinicians and patients.

Keywords: Back pain; Brace; Bracing; Congenital scoliosis; EOS, early-onset scoliosis; HRQoL, health-related quality of life; JIS, juvenile idiopathic scoliosis; Long-term outcome; ODI, Oswestry Disability Index; QoL, quality of life; Refined SRS-22r; SF-36; Scoliosis Research Society 22-item Questionnaire; Surgery; Treatment.

https://pubmed.ncbi.nlm.nih.gov/38029931/

BrAIST-Calc: Prediction of Individualized Benefit from Bracing for Adolescent Idiopathic Scoliosis

Lori A Dolan, Stuart L Weinstein, Matthew B Dobbs, John M Jack Flynn, Daniel W Green, Matthew F Halsey, M Timothy Hresko, Walter F Krengel 3rd, Charles T Mehlman, Todd A Milbrandt, Peter O Newton, Nigel Price , James O Sanders, Michael L Schmitz, Richard M Schwend, Suken A Shah, Kit Song, Vishwas Talwalkar
Spine (Phila Pa 1976). 2023 Nov 23.doi: 10.1097/BRS.0000000000004879.

Abstract

Study design: Prospective multicenter study data used for model derivation; externally-validated using retrospective cohort data.

Objective: Derive and validate a prognostic model of benefit from bracing for adolescent idiopathic scoliosis (AIS).

Summary of background data: The Bracing in Adolescent Idiopathic Scoliosis Trial (BrAIST) demonstrated superiority of bracing over observation to prevent curve progression to surgical threshold; 42% of untreated subjects had a good outcome and 28% progressed to surgical threshold despite bracing, likely due to poor adherence. To avoid over-treatment and to promote patient goal setting and adherence, bracing decisions (who and how much) should be based on physician and patient discussions informed by individual-level data from high-quality predictive models.

Methods: Logistic regression was used to predict curve progression to <45 degrees at skeletal maturity (good prognosis) in 269 BrAIST subjects who were observed or braced. Predictors included age, sex, body mass index (BMI), Risser stage, Cobb angle, curve pattern and treatment characteristics (hours of brace wear and in-brace correction). Internal and external validity were evaluated using jackknifed samples of the BrAIST dataset and an independent cohort (n=299) via estimates of discrimination and calibration.

Results: The final model included age, sex, BMI, Risser stage, Cobb angle and hours of brace wear/day. The model demonstrated strong discrimination (c-statistics 0.83 – 0.87) and calibration in all datasets. Classifying patients as low risk (high probability of a good prognosis) at the probability cut point of 70% resulted in a specificity of 92% and positive predictive value of 89%.

Conclusion: This externally-validated model can be used by clinicians and families to make informed, individualized decisions about when, and how much, to brace to avoid progression to surgery. If widely adopted, this model could decrease over-bracing of AIS, improve adherence and most importantly, decrease the likelihood of spinal fusion in this population.

https://pubmed.ncbi.nlm.nih.gov/37994691