Application of Artificial Intelligence Methods on Osteoporosis Classification with Radiographs-A Systematic Review.

Osteoporosis is a complex endocrine disease characterized by a decline in bone mass and microstructural integrity. It constitutes a major global health problem. Recent progress in the field of artificial intelligence (AI) has opened new avenues for the effective diagnosis of osteoporosis via radiographs. This review investigates the application of AI classification of osteoporosis in radiographs. A comprehensive exploration of electronic repositories (ClinicalTrials.gov, Web of Science, PubMed, MEDLINE) was carried out in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement (PRISMA). A collection of 31 articles was extracted from these repositories and their significant outcomes were consolidated and outlined. This encompassed insights into anatomical regions, the specific machine learning methods employed, the effectiveness in predicting BMD, and categorizing osteoporosis. Through analyzing the respective studies, we evaluated the effectiveness and limitations of AI osteoporosis classification in radiographs. The pooled reported accuracy, sensitivity, and specificity of osteoporosis classification ranges from 66.1% to 97.9%, 67.4% to 100.0%, and 60.0% to 97.5% respectively. This review underscores the potential of AI osteoporosis classification and offers valuable insights for future research endeavors, which should focus on addressing the challenges in technical and clinical integration to facilitate practical implementation of this technology.

Does Patient Blood Management Affect Outcomes in Metastatic Spine Tumour Surgery? A Review of Current Concepts.

STUDY DESIGN: Narrative review. OBJECTIVE: The spine is the most common site of metastases, associated with decreased quality of life. Increase in metastatic spine tumour surgery (MSTS) has caused us to focus on the management of blood, as blood loss is a significant morbidity in these patients. However, blood transfusion is also not without its own risks, and hence this led to blood conservation strategies and implementation of a concept of patient blood management (PBM) in clinical practise focusing on these patients. METHODS: A narrative review was conducted and all studies that were related to blood management in metastatic spine disease as well as PBM surrounding this condition were included. RESULTS: A total of 64 studies were included in this review. We discussed a new concept of patient blood management in patients undergoing MSTS, with stratification to pre-operative and intra-operative factors, as well as anaesthesia and surgical considerations. The studies show that PBM and reduction in blood transfusion allows for reduced readmission rates, lower risks associated with blood transfusion, and lower morbidity for patients undergoing MSTS. CONCLUSION: Through this review, we highlight various pre-operative and intra-operative methods in the surgical and anaesthesia domains that can help with PBM. It is an important concept with the significant amount of blood loss expected from MSTS. LEVEL OF EVIDENCE: Not applicable.

Implant and construct decision-making in metastatic spine tumour surgery: a review of current concepts with a decision-making algorithm.

STUDY DESIGN: Narrative Review. OBJECTIVE: Metastatic spine tumour surgery (MSTS) is an important treatment modality of metastatic spinal disease (MSD). Increase in MSTS has been due to improvements in our oncological treatment, as patients have increased longevity and even those with poorer comorbidities are now being considered for surgery. However, there is currently no guideline on how MSTS surgeons should select the appropriate levels to instrument, and which type of implants should be utilised. METHODS: The current literature on MSTS was reviewed to study implant and construct decision making factors, with a view to write this narrative review. All studies that were related to instrumentation in MSTS were included. RESULTS: A total of 58 studies were included in this review. We discuss novel decision-making models that should be taken into account when planning for surgery in patients undergoing MSTS. These factors include the quality of bone for instrumentation, the extent of the construct required for MSTS patients, the use of cement augmentation and the choice of implant. Various studies have advocated for the use of these modalities and demonstrated better outcomes in MSTS patients when used appropriately. CONCLUSION: We have established a new instrumentation algorithm that should be taken into consideration for patients undergoing MSTS. It serves as an important guide for surgeons treating MSTS, with the continuous evolvement of our treatment capacity in MSD.

Trends in surgical management of spinal metastases in a Singaporean tertiary referral center: a 17-year retrospective review.

Introduction: Surgical treatment is increasingly the treatment of choice in cancer patients with epidural spinal cord compression and spinal instability. There has also been an evolution in surgical treatment with the advent of minimally invasive surgical (MIS) techniques and separation surgery. This paper aims to investigate the changes in epidemiology, surgical technique, outcomes and complications in the last 17 years in a tertiary referral center in Singapore. Methods: This is a retrospective study of 383 patients with surgically treated spinal metastases treated between January 2005 to January 2022. Patients were divided into 3 groups, patients treated between 2005 - 2010, 2011-2016, and 2017- 2021. Demographic, oncological, surgical, patient outcome and survival data were collected. Statistical analysis with univariate analysis was performed to compare the groups. Results: There was an increase in surgical treatment (87 vs 105 vs 191). Lung, Breast and prostate cancer were the most common tumor types respectively. There was a significant increase in MIS(p<0.001) and Separation surgery (p<0.001). There was also a significant decrease in mean blood loss (1061ml vs 664 ml vs 594ml) (p<0.001) and total transfusion (562ml vs 349ml vs 239ml) (p<0.001). Group 3 patients were more likely to have improved or normal neurology (p=<0.001) and independent ambulatory status(p=0.012). There was no significant change in overall survival. Conclusion: There has been a significant change in our surgical practice with decreased blood loss, transfusion and improved neurological and functional outcomes. Patients should be managed in a multidisciplinary manner and surgical treatment should be recommended when indicated.

Artificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography.

Osteoporosis, marked by low bone mineral density (BMD) and a high fracture risk, is a major health issue. Recent progress in medical imaging, especially CT scans, offers new ways of diagnosing and assessing osteoporosis. This review examines the use of AI analysis of CT scans to stratify BMD and diagnose osteoporosis. By summarizing the relevant studies, we aimed to assess the effectiveness, constraints, and potential impact of AI-based osteoporosis classification (severity) via CT. A systematic search of electronic databases (PubMed, MEDLINE, Web of Science, ClinicalTrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 39 articles were retrieved from the databases, and the key findings were compiled and summarized, including the regions analyzed, the type of CT imaging, and their efficacy in predicting BMD compared with conventional DXA studies. Important considerations and limitations are also discussed. The overall reported accuracy, sensitivity, and specificity of AI in classifying osteoporosis using CT images ranged from 61.8% to 99.4%, 41.0% to 100.0%, and 31.0% to 100.0% respectively, with areas under the curve (AUCs) ranging from 0.582 to 0.994. While additional research is necessary to validate the clinical efficacy and reproducibility of these AI tools before incorporating them into routine clinical practice, these studies demonstrate the promising potential of using CT to opportunistically predict and classify osteoporosis without the need for DEXA.

Outcomes and Complications of Surgery for Symptomatic Spinal Metastases; a Comparison Between Patients Aged ≥ 70 and <70.

STUDY DESIGN: Retrospective cohort study. OBJECTIVE: Physicians may be deterred from operating on elderly patients due to fears of poorer outcomes and complications. We aimed to compare the outcomes of surgical treatment of spinal metastases patients aged ≥70-yrs and <70-yrs. MATERIALS AND METHODS: This is a retrospective study of patients surgically treated for metastatic epidural spinal cord compression and spinal instability between January-2005 to December-2021. Follow-up was till death or minimum 1-year post-surgery. Outcomes included post-operative neurological status, ambulatory status, medical and surgical complications. Two Sample t-test/Mann Whitney U test were used for numerical variables and Pearson Chi-Squared or Fishers Exact test for categorical variables. Survival was presented with a Kaplan-Meier curve. P < .05 was significant. RESULTS: We identified 412 patients of which 29 (7.1%) patients were excluded due to loss to follow-up and previous surgical treatment. 79 (20.6%) were ≥70-yrs. Age ≥70-yrs patients had poorer ECOG scores (P = .0017) and Charlson Comorbidity Index (P < .001). No significant difference in modified Tokuhashi score (P = .393) was observed with significantly more ≥ prostate (P < .001) and liver (P = .029) cancer in ≥70-yrs. Improved or maintained normal neurological function (P = .934), independent ambulatory status (P = .171), and survival at 6 months (P = .119) and 12 months (P = .659) was not significantly different between both groups. Medical (P = .528) or surgical (P = .466) complication rates and readmission rates (P = .800) were similar. CONCLUSION: ≥70-yrs patients have comparable outcomes to <70-yr old patients with no significant increase in complication rates. Age should not be a determining factor in deciding surgical management of spinal metastases.

Epithelioid Sarcoma of the Spine: A Review of Literature and Case Report.

Epithelioid sarcoma is a rare malignant mesenchymal tumor that represents less than 1% of soft-tissue sarcomas. Despite its slow growth, the overall prognosis is poor with a high rate of local recurrence, lymph-node spread, and hematogenous metastasis. Primary epithelioid sarcoma arising from the spine is extremely rare, with limited data in the literature. We review the existing literature regarding spinal epithelioid sarcoma and report a case of epithelioid sarcoma arising from the spinal cord. A 54 year old male presented with a 1-month history of progressive left upper-limb weakness and numbness. Magnetic resonance imaging (MRI) of the spine showed an enhancing intramedullary mass at the level of T1 also involving the left T1 nerve root. Systemic radiological examination revealed no other lesion at presentation. Surgical excision of the mass was performed, and histology was consistent with epithelioid sarcoma of the spine. Despite adjuvant radiotherapy, there was aggressive local recurrence and development of intracranial metastatic spread. The patient died of the disease within 5 months from presentation. To the best of our knowledge, spinal epithelioid sarcoma arising from the spinal cord has not yet been reported. We review the challenges in diagnosis, surgical treatment, and oncologic outcome of this case.

Vacuum assisted closure and local drug delivery systems in spinal infections: A review of current evidence.

Background: Spinal infections are still showing increased incidence throughout the years as our surgical capabilities increase, coupled with an overall aging population with greater number of chronic comorbidities. The management of spinal infection is of utmost importance, due to high rates of morbidity and mortality, on top of the general difficulty in eradicating spinal infection due to the ease of hematogenous spread in the spine. We aim to summarize the utility of vacuum-assisted closure (VAC) and local drug delivery systems (LDDS) in the management of spinal infections. Methods: A narrative review was conducted. All studies that were related to the use of VAC and LDDS in Spinal Infections were included in the study. Results: A total of 62 studies were included in this review. We discussed the utility of VAC as a tool for the management of wounds requiring secondary closure, as well as how it is increasingly being used after primary closure as prophylaxis for surgical site infections in high-risk wounds of patients undergoing spinal surgery. The role of LDDS in spinal infections was also discussed, with preliminary studies showing good outcomes when patients were treated with various novel LDDS. Conclusions: We have summarized and given our recommendations for the use of VAC and LDDS for spinal infections. A treatment algorithm has also been established, to act as a guide for spine surgeons to follow when tackling various spinal infections in day-to-day clinical practice.

Unipedicular-Screw Index Vertebra Manipulation Technique for Minimally Invasive Short-Segment Thoracolumbar Fracture Fixation.

BACKGROUND: Minimally invasive spine surgery (MIS) has revolutionized fixation of thoracolumbar fractures with burst elements. Recent studies have proven that percutaneous pedicle screw instrumentation is as effective as open instrumentation but with reduced intraoperative blood loss and operative duration. Techniques such as short-segment pedicle screw fixation including the fractured vertebra have shown satisfactory radiological correction and functional outcomes, avoiding the need for extensile posterior constructs. OBJECTIVE: In the present study, the authors our technique utilizing unipedicular index vertebra fixation and manipulation in MIS for thoracolumbar fractures with burst elements. To our knowledge, this technique is not well described in literature as open approaches are often adopted for the above. The authors sought to highlight the 2-year radiological and functional outcomes of 20 consecutive patients who underwent this technique. METHODS: A retrospective review of prospectively collected data was conducted on 20 patients with thoracolumbar fractures with burst elements who underwent fixation using our technique. Patient data collected included demographic characteristics, mechanism of injury, associated injuries, neurological deficit at the time of admission, pre- and postoperative neurological evaluation, and length of hospital stay. Radiological investigations included plain radiographs, computed tomography of the spine with reconstruction, and magnetic resonance imaging of the spine, which provided data for radiological fracture classifications such as AO Spine and derivation of Thoracolumbar Injury Classification and Severity Score, as well as preoperative planning. Radiological investigations in the postoperative period were carried out by standing radiographs or EOS whole spine at each postoperative follow-up for up to 2 years. Radiological parameters-vertebral wedge angle, regional kyphosis angle, coronal Cobb angle, and anterior and posterior vertebral body heights-were recorded at preoperative, intraoperative, postoperative, and up to 2-year follow-up. Clinical outcome scores (visual analog score [VAS] and Oswestry Disability Index [ODI]) were also recorded at similar timepoints. RESULTS: Radiological outcomes reflect significant lordotic corrections of the vertebral wedge angles up to 2-year follow-up when compared with preoperative values (intraoperative: P = 0.06; postoperative: P = 0.001; 3 months: P = 0.002; 6 months: P = 0.004; 1 year: P = 0.011; 2 years: P = 0.016). Additionally, significant lordotic corrections of regional kyphosis angles (intraoperative: P = 0.00; postoperative: P = 0.00; 3 months: P = 0.031; 6 months: P = 0.039) and increases in anterior vertebral body heights (postoperative: P = 0.001; 3 months: P = 0.010; 6 months: P = 0.020) at up to 6-month follow-up were found. Preoperatively, median VAS of 85 (range 30-100) and ODI of 90 (range 40-98) were recorded. Statistically significant improvements in VAS and ODI were found across all timepoints when compared with preoperative values, with a mean VAS of 11.5 (SD 4.8) and ODI of 9.9 (SD 4.5) at 2-year follow-up. CONCLUSION: Surgical management of thoracolumbar fractures with or without neurological deficit has a role in reducing nursing requirements and postoperative morbidity in patients with polytrauma and other associated injuries. Our approach in treating thoracolumbar fractures with burst elements using MIS short-segment fixation and unipedicular screw manipulation technique shows satisfactory radiological correction and high rates of fracture union while reducing approach-related morbidity and improving functional outcomes.

Intraoperative cell-salvaged autologous blood transfusion is safe in metastatic spine tumour surgery: early outcomes of prospective clinical study.

PURPOSE: Allogeneic blood transfusion (ABT) is current standard of blood replenishment despite known complications. Salvaged blood transfusion (SBT) addresses majority of such complications. Surgeons remain reluctant to employ SBT in metastatic spine tumour surgery (MSTS), despite ample laboratory evidence. This prompted us to conduct a prospective clinical study to ascertain safety of intraoperative cell salvage (IOCS), in MSTS. METHODS: Our prospective study included 73 patients who underwent MSTS from 2014 to 2017. Demographics, tumour histology and burden, clinical findings, modified Tokuhashi score, operative and blood transfusion (BT) details were recorded. Patients were divided based on BT type: no blood transfusion (NBT) and SBT/ABT. Primary outcomes assessed were overall survival (OS), and tumour progression was evaluated using RECIST (v1.1) employing follow-up radiological investigations at 6, 12 and 24 months, classifying patients with non-progressive and progressive disease. RESULTS: Seventy-three patients [39:34(M/F)] had mean age of 61 years. Overall median follow-up and survival were 26 and 12 months, respectively. All three groups were comparable for demographics and tumour characteristics. Overall median blood loss was 500 mL, and BT was 1000 mL. Twenty-six (35.6%) patients received SBT, 27 (37.0%) ABT and 20 (27.4%) NBT. Females had lower OS and higher risk of tumour progression. SBT had better OS and reduced risk of tumour progression than ABT group. Total blood loss was not associated with tumour progression. Infective complications other than SSI were significantly (p = 0.027) higher in ABT than NBT/SBT groups. CONCLUSIONS: Patients of SBT had OS and tumour progression better than ABT/NBT groups. This is the first prospective study to report of SBT in comparison with control groups in MSTS.

Deep learning assessment compared to radiologist reporting for metastatic spinal cord compression on CT.

Introduction: Metastatic spinal cord compression (MSCC) is a disastrous complication of advanced malignancy. A deep learning (DL) algorithm for MSCC classification on CT could expedite timely diagnosis. In this study, we externally test a DL algorithm for MSCC classification on CT and compare with radiologist assessment. Methods: Retrospective collection of CT and corresponding MRI from patients with suspected MSCC was conducted from September 2007 to September 2020. Exclusion criteria were scans with instrumentation, no intravenous contrast, motion artefacts and non-thoracic coverage. Internal CT dataset split was 84% for training/validation and 16% for testing. An external test set was also utilised. Internal training/validation sets were labelled by radiologists with spine imaging specialization (6 and 11-years post-board certification) and were used to further develop a DL algorithm for MSCC classification. The spine imaging specialist (11-years expertise) labelled the test sets (reference standard). For evaluation of DL algorithm performance, internal and external test data were independently reviewed by four radiologists: two spine specialists (Rad1 and Rad2, 7 and 5-years post-board certification, respectively) and two oncological imaging specialists (Rad3 and Rad4, 3 and 5-years post-board certification, respectively). DL model performance was also compared against the CT report issued by the radiologist in a real clinical setting. Inter-rater agreement (Gwet's kappa) and sensitivity/specificity/AUCs were calculated. Results: Overall, 420 CT scans were evaluated (225 patients, mean age=60 ± 11.9[SD]); 354(84%) CTs for training/validation and 66(16%) CTs for internal testing. The DL algorithm showed high inter-rater agreement for three-class MSCC grading with kappas of 0.872 (p<0.001) and 0.844 (p<0.001) on internal and external testing, respectively. On internal testing DL algorithm inter-rater agreement (κ=0.872) was superior to Rad 2 (κ=0.795) and Rad 3 (κ=0.724) (both p<0.001). DL algorithm kappa of 0.844 on external testing was superior to Rad 3 (κ=0.721) (p<0.001). CT report classification of high-grade MSCC disease was poor with only slight inter-rater agreement (κ=0.027) and low sensitivity (44.0), relative to the DL algorithm with almost-perfect inter-rater agreement (κ=0.813) and high sensitivity (94.0) (p<0.001). Conclusion: Deep learning algorithm for metastatic spinal cord compression on CT showed superior performance to the CT report issued by experienced radiologists and could aid earlier diagnosis.

A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT.

PURPOSE: To develop a deep learning (DL) model for epidural spinal cord compression (ESCC) on CT, which will aid earlier ESCC diagnosis for less experienced clinicians. METHODS: We retrospectively collected CT and MRI data from adult patients with suspected ESCC at a tertiary referral institute from 2007 till 2020. A total of 183 patients were used for training/validation of the DL model. A separate test set of 40 patients was used for DL model evaluation and comprised 60 staging CT and matched MRI scans performed with an interval of up to 2 months. DL model performance was compared to eight readers: one musculoskeletal radiologist, two body radiologists, one spine surgeon, and four trainee spine surgeons. Diagnostic performance was evaluated using inter-rater agreement, sensitivity, specificity and AUC. RESULTS: Overall, 3115 axial CT slices were assessed. The DL model showed high kappa of 0.872 for normal, low and high-grade ESCC (trichotomous), which was superior compared to a body radiologist (R4, κ = 0.667) and all four trainee spine surgeons (κ range = 0.625-0.838)(all p < 0.001). In addition, for dichotomous normal versus any grade of ESCC detection, the DL model showed high kappa (κ = 0.879), sensitivity (91.82), specificity (92.01) and AUC (0.919), with the latter AUC superior to all readers (AUC range = 0.732-0.859, all p < 0.001). CONCLUSION: A deep learning model for the objective assessment of ESCC on CT had comparable or superior performance to radiologists and spine surgeons. Earlier diagnosis of ESCC on CT could reduce treatment delays, which are associated with poor outcomes, increased costs, and reduced survival.

Application of Machine Learning for Differentiating Bone Malignancy on Imaging: A Systematic Review.

An accurate diagnosis of bone tumours on imaging is crucial for appropriate and successful treatment. The advent of Artificial intelligence (AI) and machine learning methods to characterize and assess bone tumours on various imaging modalities may assist in the diagnostic workflow. The purpose of this review article is to summarise the most recent evidence for AI techniques using imaging for differentiating benign from malignant lesions, the characterization of various malignant bone lesions, and their potential clinical application. A systematic search through electronic databases (PubMed, MEDLINE, Web of Science, and clinicaltrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 34 articles were retrieved from the databases and the key findings were compiled and summarised. A total of 34 articles reported the use of AI techniques to distinguish between benign vs. malignant bone lesions, of which 12 (35.3%) focused on radiographs, 12 (35.3%) on MRI, 5 (14.7%) on CT and 5 (14.7%) on PET/CT. The overall reported accuracy, sensitivity, and specificity of AI in distinguishing between benign vs. malignant bone lesions ranges from 0.44-0.99, 0.63-1.00, and 0.73-0.96, respectively, with AUCs of 0.73-0.96. In conclusion, the use of AI to discriminate bone lesions on imaging has achieved a relatively good performance in various imaging modalities, with high sensitivity, specificity, and accuracy for distinguishing between benign vs. malignant lesions in several cohort studies. However, further research is necessary to test the clinical performance of these algorithms before they can be facilitated and integrated into routine clinical practice.

Prevalence and Risk Factors of Degenerative Spondylolisthesis and Retrolisthesis in the Thoracolumbar and Lumbar Spine - An EOS Study Using Updated Radiographic Parameters.

STUDY DESIGN: Single centre, cross-sectional study. OBJECTIVES: The objective is to report the prevalence of spondylolisthesis and retrolisthesis, analyse both conditions in terms of the affected levels and severity, as well as identify their risk factors. METHODS: A review of clinical data and radiographic images of consecutive spine patients seen in outpatient clinics over a 1-month period is performed. Images are obtained using the EOS® technology under standardised protocol, and radiographic measurements were performed by 2 independent, blinded spine surgeons. The prevalence of both conditions were shown and categorised based on the spinal level involvement and severity. Associated risk factors were identified. RESULTS: A total of 256 subjects (46.1% males) with 2304 discs from T9/10 to L5/S1 were studied. Their mean age was 52.2(± 18.7) years. The overall prevalence of spondylolisthesis and retrolisthesis was 25.9% and 17.1% respectively. Spondylolisthesis occurs frequently at L4/5(16.3%), and retrolisthesis at L3/4(6.8%). Majority of the patients with spondylolisthesis had a Grade I slip (84.3%), while those with retrolisthesis had a Grade I slip. The presence of spondylolisthesis was found associated with increased age (P < .001), female gender (OR: 2.310; P = .005), predominantly sitting occupations (OR:2.421; P = .008), higher American Society of Anaesthesiology grades (P = .001), and lower limb radiculopathy (OR: 2.175; P = .007). Patients with spondylolisthesis had larger Pelvic Incidence (P < .001), Pelvic Tilt (P < .001) and Knee alignment angle (P = .011), but smaller Thoracolumbar junctional angle (P = .008), Spinocoxa angle (P = .007). Retrolisthesis was associated with a larger Thoracolumbar junctional angle (P =.039). CONCLUSION: This is the first study that details the prevalence of spondylolisthesis and retrolisthesis simultaneously, using the EOS technology and updated sagittal radiographic parameters. It allows better understanding of both conditions, their mutual relationship, and associated clinical and radiographic risk factors.

Epidemiology and estimated economic impact of musculoskeletal injuries in polytrauma patients in a level one trauma centre in Singapore.

Introduction: Musculoskeletal injuries are the most common reason for surgical intervention in polytrauma patients. Methods: This is a retrospective cohort study of 560 polytrauma patients (injury severity score [ISS] >17) who suffered musculoskeletal injuries (ISS >2) from 2011 to 2015 in National University Hospital, Singapore. Results: 560 patients (444 [79.3%] male and 116 [20.7%] female) were identified. The mean age was 44 (range 3-90) years, with 45.4% aged 21-40 years. 39.3% of the patients were foreign migrant workers. Motorcyclists were involved in 63% of road traffic accidents. The mean length of hospital stay was 18.8 (range 0-273) days and the mean duration of intensive care unit (ICU) stay was 5.7 (range 0-253) days. Patient mortality rate was 19.8%. A Glasgow Coma Scale (GCS) score <12 and need for blood transfusion were predictive of patient mortality (p < 0.05); lower limb injuries, road traffic accidents, GCS score <8 and need for transfusion were predictive of extended hospital stay (p < 0.05); and reduced GCS score, need for blood transfusion and upper limb musculoskeletal injuries were predictive of extended ICU stay. Inpatient costs were significantly higher for foreign workers and greatly exceeded the minimum insurance coverage currently required. Conclusion: Musculoskeletal injuries in polytrauma remain a significant cause of morbidity and mortality, and occur predominantly in economically productive male patients injured in road traffic accidents and falls from height. Increasing insurance coverage for foreign workers in high-risk jobs should be evaluated.

Does concomitant gout in septic arthritis affect surgical outcomes?

BACKGROUND: We aim to review and describe the proportion of patients with co-existing gout amongst patients with surgical treated septic arthritis, characterize their clinical presentation, outcomes and complications compared to patients with native joint septic arthritis. METHODS: Sixty-one patients with surgically treated primary joint septic arthritis were identified from the period of January 2011 to December 2016. There were 13 (21.3%) patients with co-existing septic arthritis and crystal proven gout. Pertinent details such as demographics, comorbidities, clinical features on presentation, infection markers, number of surgeries, length of stay (LOS) in general and individual LOS in supportive care units, limb amputations, readmissions and mortality were reviewed. Multiple linear and logistic regression models were used to control for confounders during analysis. RESULTS: The average age of patients was 60.8 years (range: 23-87 years). The patients with gout are associated with comorbidities such as being hypertensive, hyperlipidemia and renal impaired. They tend to present with ankle joint involvement (46.2% vs 8.3%; p = 0.004) while septic arthritis patients without gout tend to present with knee joint involvement (75% vs 46.2%; p = 0.046). In terms of complications, up to two thirds of them require supportive care in the High Dependency Unit and/or Intensive Care Unit during treatment (61.5% vs 29.2%; p = 0.031) and having gout with septic arthritis independently predicted a significant increase in LOS by an additional 12.6 days on average (95% CI: 2.11 - 23.03; p = 0.019). They are also more likely to end up with limb amputation (23.1% vs 0%; p = 0.008) on univariate analysis. CONCLUSION: Gout accompanying septic arthritis in the same joint is potentially associated with major systemic and joint related sequela, complications in terms of prolonged hospital stay, need for complex care and risk for limb amputation. Our findings further indicate the value and need for well-designed prospective controlled cohort studies to explore the relationship between gout and septic arthritis.

Diagnostic Accuracy of CT for Metastatic Epidural Spinal Cord Compression.

BACKGROUND: Early diagnosis of metastatic epidural spinal cord compression (MESCC) is vital to expedite therapy and prevent paralysis. Staging CT is performed routinely in cancer patients and presents an opportunity for earlier diagnosis. METHODS: This retrospective study included 123 CT scans from 101 patients who underwent spine MRI within 30 days, excluding 549 CT scans from 216 patients due to CT performed post-MRI, non-contrast CT, or a gap greater than 30 days between modalities. Reference standard MESCC gradings on CT were provided in consensus via two spine radiologists (11 and 7 years of experience) analyzing the MRI scans. CT scans were labeled using the original reports and by three radiologists (3, 13, and 14 years of experience) using dedicated CT windowing. RESULTS: For normal/none versus low/high-grade MESCC per CT scan, all radiologists demonstrated almost perfect agreement with kappa values ranging from 0.866 (95% CI 0.787-0.945) to 0.947 (95% CI 0.899-0.995), compared to slight agreement for the reports (kappa = 0.095, 95%CI -0.098-0.287). Radiologists also showed high sensitivities ranging from 91.51 (95% CI 84.49-96.04) to 98.11 (95% CI 93.35-99.77), compared to 44.34 (95% CI 34.69-54.31) for the reports. CONCLUSION: Dedicated radiologist review for MESCC on CT showed high interobserver agreement and sensitivity compared to the current standard of care.

Application of Artificial Intelligence Methods for Imaging of Spinal Metastasis.

Spinal metastasis is the most common malignant disease of the spine. Recently, major advances in machine learning and artificial intelligence technology have led to their increased use in oncological imaging. The purpose of this study is to review and summarise the present evidence for artificial intelligence applications in the detection, classification and management of spinal metastasis, along with their potential integration into clinical practice. A systematic, detailed search of the main electronic medical databases was undertaken in concordance with the PRISMA guidelines. A total of 30 articles were retrieved from the database and reviewed. Key findings of current AI applications were compiled and summarised. The main clinical applications of AI techniques include image processing, diagnosis, decision support, treatment assistance and prognostic outcomes. In the realm of spinal oncology, artificial intelligence technologies have achieved relatively good performance and hold immense potential to aid clinicians, including enhancing work efficiency and reducing adverse events. Further research is required to validate the clinical performance of the AI tools and facilitate their integration into routine clinical practice.

Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT.

Background: Metastatic epidural spinal cord compression (MESCC) is a disastrous complication of advanced malignancy. Deep learning (DL) models for automatic MESCC classification on staging CT were developed to aid earlier diagnosis. Methods: This retrospective study included 444 CT staging studies from 185 patients with suspected MESCC who underwent MRI spine studies within 60 days of the CT studies. The DL model training/validation dataset consisted of 316/358 (88%) and the test set of 42/358 (12%) CT studies. Training/validation and test datasets were labeled in consensus by two subspecialized radiologists (6 and 11-years-experience) using the MRI studies as the reference standard. Test sets were labeled by the developed DL models and four radiologists (2−7 years of experience) for comparison. Results: DL models showed almost-perfect interobserver agreement for classification of CT spine images into normal, low, and high-grade MESCC, with kappas ranging from 0.873−0.911 (p < 0.001). The DL models (lowest κ = 0.873, 95% CI 0.858−0.887) also showed superior interobserver agreement compared to two of the four radiologists for three-class classification, including a specialist (κ = 0.820, 95% CI 0.803−0.837) and general radiologist (κ = 0.726, 95% CI 0.706−0.747), both p < 0.001. Conclusion: DL models for the MESCC classification on a CT showed comparable to superior interobserver agreement to radiologists and could be used to aid earlier diagnosis.