Severe Hemodynamic Collapse During Humerus Stabilization with Photodynamic Implant: A Report of Two Cases.

CASE: We present 2 cases of severe hemodynamic collapse during prophylactic stabilization of impending pathologic humerus fractures using a photodynamic bone stabilization device. Both events occurred when the monomer was infused under pressure into a balloon catheter. CONCLUSION: We suspect that an increase in intramedullary pressure during balloon expansion may cause adverse systemic effects similar to fat embolism or bone cement implantation syndrome. Appropriate communication with the anesthesia team, invasive hemodynamic monitoring, and prophylactic vent hole creation may help mitigate or manage these adverse systemic effects.

Rare vertebral pathological fracture in primary amyloidosis.

Spinal involvement in primary amyloidosis is an exceedingly rare condition, presenting with typical pathological fracture symptoms that are often indistinguishable from other pathologies such as bone metastasis, metabolic disorders and infections. Histopathological studies for tissue diagnosis are the cornerstone of a definitive diagnosis, leading to successful treatment. Early diagnosis and intervention play a pivotal role in the care of patients with amyloidosis. Here, we present a unique case of a pathological fracture in the L4 vertebra following minor trauma. This fracture manifested with pain, instability and limitations in daily activities in a patient who had already been diagnosed with systemic amyloidosis and was undergoing chemotherapy. This case represents a distinct instance of vertebral involvement in amyloidosis and was managed with both chemotherapy and surgical intervention to address the spinal pathology, resulting in favourable outcomes.

Intravenous tranexamic acid reduces complications following surgical treatment of pathologic fractures of the lower extremity.

BACKGROUND AND OBJECTIVES: This study aimed to evaluate the postoperative complications associated with administering intravenous (IV) tranexamic acid (TXA) in patients undergoing surgical fixation for neoplastic pathologic fractures of the lower extremities. METHODS: Patients ≥18 years old who underwent surgical intervention for neoplastic pathologic lower extremity fractures from 2015 to 2021 were identified using the Premier Healthcare Database. This cohort was divided by TXA receipt on the index surgery day. Patient demographics, hospital factors, patient comorbidities, and 90-day complications were assessed and compared between the cohorts. RESULTS: From 2015 to 2021, 4497 patients met inclusion criteria (769 TXA[+] and 3728 TXA[-]). Following propensity score matching, patients who received TXA had a significantly shorter length of stay than those who did not (7.6 ± 7.3 days vs. 9.0 ± 15.2, p = 0.036). Between the two cohorts, there were no significant differences in comorbidities. Regarding differences in postoperative complications, TXA(+) patients had significantly decreased odds of deep vein thrombosis (DVT) (1.87% vs. 5.46%; odds ratio [OR]:0.33; 95% confidence interval: 0.17-0.62; p = 0.001). CONCLUSION: Administration of IV TXA may be associated with a decreased risk of postoperative DVT without an increased risk of other complications. Orthopedic surgeons should consider the utilization of IV TXA in patients treated surgically for neoplastic pathologic fractures of the lower extremity.

Impact of metastatic epidural spinal cord compression (MESCC) and pathological vertebral compression fracture (pVCF) in neurological and survival prognosis.

BACKGROUND: Metastatic epidural spinal cord compression (MESCC) and pathological vertebral compression fractures (pVCF) are the most serious debilitating morbidities of spine metastases (SpMs) causing devastating neurological damages. The respective impact of these two metastasis-spreading entities on survival and on neurological damage is debated. METHODS: A French prospective cohort study collected 279 consecutive patients presenting with SpMs between January 2017 and 2021. We compared 174 patients with MESCC and 105 patients with pVCF. RESULTS: The median Overall Survival (OS) for the MESCC group was 13.4 months (SD 1.5) vs 19.2 months (SD 2.3) for pVCF patients (p = 0.085). Sixty-five patients (23.3 %) were operated on: 49/65 (75.4 %) in the MESCC group and 16/65 (15.2 %) in the pVCF group, p < 0.0001. At 6 months FU, in the MESCC group, 21/44 (45.4 %) of non-ambulatory patients at onset improved to ambulatory status (Frankel D-E) vs 10/13 (76.9 %) in the pVCF group (p = 0.007). In multivariable analysis with the Cox proportional hazard model, good ECOG-PS and SINS Score 7-12 [HR: 6.755, 95 % CI 2.40-19.00; p = 0.001] were good prognostic factors for preserved ambulatory neurological status. However, SpMs diagnosed synchronously with the primary tumor [HR: 0.397, 95 % CI 0.185-0.853; p = 0.018] and MESCC [HR: 0.058, 95 % CI 0.107-0.456; p = 0.007] were independent risk factors for impaired neurological function. CONCLUSION: Contrary to pVCF, MESCC causes neurological damage. Nevertheless, neurological recovery remains possible. MESCC and pVCF have no impact on survival. The management of MESCC remains to be clarified and optimized to reduce neurological damage.

Comparison of Hounsfield units and vertebral bone quality score for the prediction of time to pathologic fracture in mobile spine metastases treated with radiotherapy.

OBJECTIVE: Spine metastases are commonly treated with radiotherapy for local tumor control; pathologic fracture is a potential complication of spinal radiotherapy. Both Hounsfield units (HUs) on CT and vertebral bone quality (VBQ) on MRI have been argued to predict stability as measured by odds of pathologic fracture, although it is unclear if there is a difference in the predictive power between the two methodologies. The objective of the present study was to examine whether one methodology is a better predictor of pathologic fracture following radiotherapy for mobile spine metastases. METHODS: Patients who underwent radiotherapy (conventional external-beam radiation therapy, stereotactic body radiation therapy, or intensity-modulated radiation therapy) for mobile spine (C1-L5) metastases at a tertiary care center were retrospectively identified. Details regarding underlying pathology, patient demographics, and tumor morphology were collected. Vertebral involvement was assessed using the Weinstein-Boriani-Biagini (WBB) system. Bone quality of the non-tumor-involved bone was assessed on both pretreatment CT and MRI. Univariable analyses were conducted to identify independent predictors of fracture, and Kaplan-Meier analyses were used to identify significant predictors of time to pathologic fracture. Stepwise Cox regression analysis was used to determine independent predictors of time to fracture. RESULTS: One hundred patients were included (mean age 62.7 ± 11.9 years; 61% male), of whom 35 experienced postradiotherapy pathologic fractures. The most common histologies were lung (22%), prostate (21%), breast (14%), and renal cell (13%). On univariable analysis, the mean HUs of the vertebrae adjacent to the fractured vertebra were significantly lower among those experiencing fracture; VBQ was not significantly associated with fracture odds. Survival analysis showed that average HUs ≤ 132, nonprostate pathology, involvement of ≥ 3 vertebral body segments on the WBB system, Spine Instability Neoplastic Score (SINS) ≥ 7, and the presence of axial pain all predicted increased odds of fracture (all p < 0.001). Cox regression found that HUs ≤ 132 (OR 2.533, 95% CI 1.257-5.103; p = 0.009), ≥ 3 WBB vertebral body segments involved (OR 2.376, 95% CI 1.132-4.987; p = 0.022), and axial pain (OR 2.036, 95% CI 0.916-4.526; p = 0.081) predicted increased fracture odds, while prostate pathology predicted decreased odds (OR 0.076, 95% CI 0.009-0.613; p = 0.016). Sensitivity analysis suggested that an HU threshold of ≤ 132 and a SINS of ≥ 7 identified patients at increased risk of fracture. CONCLUSIONS: The present results suggest that bone density surrogates as measured on CT, but not MRI, can be used to predict the risk of pathologic fracture following radiotherapy for mobile spine metastases. More extensive vertebral body involvement and the presence of mechanical axial pain additionally predict increased fracture odds.

Progression toward Vertebral Collapse of Vertebral Metastases Treated with Percutaneous Vertebroplasty: Rate and Risk Factors.

PURPOSE: To evaluate of the rate of and risks for progression toward collapse in vertebral metastases (VMs) treated with percutaneous vertebroplasty (PV). MATERIALS AND METHODS: A total of 151 PVs were performed in 81 patients with vertebral metastases and were retrospectively analyzed. Follow-up imaging was performed at 12 months to measure vertebral body height and to report vertebral collapse at the level of the treated vertebrae. Vertebral characteristics (spine instability neoplastic score [SINS], number of lysed cortices, and prior radiotherapy) and procedural parameters (Saliou score, cortical contact with cement, and intradiscal cement leakage) were compared between the group of patients with and without collapse of the treated vertebrae. RESULTS: Of the vertebrae treated with PV, 41 of 151 (27%) progressed toward collapse. Vertebral collapse was influenced by a high SINS (odds ratio [OR] = 1.27, P = .004), SINS value > 9 (OR = 2.96, P = .004), intradiscal cement leakage (OR = 2.18, P = .048), pre-existing spinal deformity (OR = 2.65, P = .020), and pre-existing vertebral fracture (OR = 3.93, P = .045). A high Saliou score (OR = 0.82, P = .011), more than 3 cortices in contact with the cement (OR = 0.38, P = .014), and preserved spinal alignment (OR = 0.38, P = .020) were associated with a lower incidence of collapse. CONCLUSIONS: Rate of vertebral collapse despite PV was influenced by vertebra-specific characteristics and by cement injection quality. Vertebrae with a SINS of ≤9 and with homogeneous cement filling had a lower incidence of collapse.

Pathological fracture increases the risk of unsatisfactory functional results and avascular necrosis in children with proximal femur simple bone cysts.

INTRODUCTION: Proximal femur simple bone cysts (SBCs) are rare in children, but with a risk of pathological fractures and the associated poor outcomes. This study aimed to evaluate the functional and radiographic outcomes of children with proximal femur SBCs. PATIENTS AND METHODS: 38 children with proximal femur SBCs treated surgically at our department, West China hospital, were enrolled in the study. Patients were divided into two groups according to whether pathological fractures presented before treatment. The non-fracture group received treatment of open curettage, cavity electrocauterization, bone grafting, and fixation (proximal femoral plate, intramedullary nail or Kirschner wire). The pathological fracture group received the same procedures of curettage, electrocauterization, grafting, and fixation. Autogenous iliac bone grafting was done in all cases, and the artificial bone was used as a supplementary based on the size of the cavity. Postoperatively, all patients underwent hip spica or similar orthosis immobilization for six weeks and received the same rehabilitation program after the removal of hip spica. Patients were evaluated by two independent observers, including the functional results based on the Ratliff's criteria, avascular necrosis, healing rate based on the Neer scoring system, coxa vara, and premature physeal arrest. We described the good outcome in Ratliff's criteria as "Satisfactory results", and fair and poor outcomes as "Unsatisfactory results." Grade 1 and grade 2 Neer results were termed as failures in treatment, and grades 3 and 4 were considered successes and healing. RESULTS: 38 patients with 38 hips (18 on the left side and 20 on the right side) were evaluated, including 9 females and 29 males, with a mean age of 9.0±2.6 years old (range, 5 to 14 years). There was no significant difference between these two groups in the baseline data of gender, age, side, grafting, staging, and fixation methods. The rate of unsatisfactory functional results in the pathological fractures group was 56.3% (9/16), significantly higher than that in patients without fracture (22.7%, 5/22. p= 0.047). There was also a significant difference in avascular necrosis of the femoral head between the pathological fractures group (7/16) and the group without fracture (2/22, p=0.021). Thirty cases presented with healing, including 13 in the fractures group and 17 in the non-fracture group (p=1.000), and eight cases were graded as failures (2 cases of grade 1 and 6 cases of grade 2). There were also no significant differences between these two groups in premature physeal arrest (2 in fracture group and 1 in non-fracture group, P=0.562), and Coxa vara (3 in the fracture group and 0 in non-fracture group, P=0.066). CONCLUSIONS: Pathological fracture significantly increases the risk of unsatisfactory functional results and avascular necrosis of the femoral head in patients with femoral neck SBCs. Prophylactic treatment and fixation of SBCs in weight bearing proximal femur region is better to manage without complications than managing with pathological fractures.

Outcomes of Long Bones Treated With Carbon-Fiber Nails for Oncologic Indications: International Multi-institutional Study.

BACKGROUND: Intramedullary nail fixation is commonly used for prophylactic stabilization of impending and fixation of complete pathological fractures of the long bones. However, metallic artifacts complicate imaging evaluation for bone healing or tumor progression and postoperative radiation planning. Carbon-fiber implants have gained popularity as an alternative, given their radiolucency and superior axial bending. This study evaluates incidences of mechanical and nonmechanical complications. METHODS: Adult patients (age 18 years and older) treated with carbon-fiber nails for impending/complete pathological long bone fractures secondary to metastases from 2013 to 2020 were analyzed for incidences and risk factors of mechanical and nonmechanical complications. Mechanical complications included aseptic screw loosening and structural failures of host bone and carbon-fiber implants. Deep infection and tumor progression were considered nonmechanical. Other complications/adverse events were also reported. RESULTS: A total of 239 patients were included; 47% were male, and 53% were female, with a median age of 68 (IQR, 59 to 75) years. Most common secondary metastases were related to breast cancer (19%), lung cancer (19%), multiple myeloma (18%), and sarcoma (13%). In total, 17 of 30 patients with metastatic sarcoma received palliative intramedullary nail fixation for impending/complete pathological fractures, and 13 of 30 received prophylactic nail stabilization of bone radiated preoperatively to manage juxta-osseous soft-tissue sarcomas, where partial resection of the periosteum or bone was necessary for negative margin resection. 33 (14%) patients had complications. Mechanical failures included 4 (1.7%) structural host bone failures, 7 (2.9%) implant structural failures, and 1 (0.4%) aseptic loosening of distal locking screws. Nonmechanical failures included 8 (3.3%) peri-implant infections and 15 (6.3%) tumor progressions with implant contamination. The 90-day and 1-year mortalities were 28% (61/239) and 53% (53/102), respectively. The literature reported comparable failure and mortality rates with conventional titanium treatment. CONCLUSIONS: Carbon-fiber implants might be an alternative for treating impending and sustained pathological fractures secondary to metastatic bone disease. The seemingly comparable complication profile warrants further cohort studies comparing carbon-fiber and titanium nail complications.

Two Pathological Fractures in a Patient with Chronic Abnormalities in Serum Markers Following Two Liver Transplantations: A Case Report and Literature Review.

Bone disease is a common complication following liver transplantation, often overlooked in clinical practice. Clinical diagnosis of post-liver transplantation bone disease is challenging, and there have been few case report in the literature. This case report presents a patient who underwent two liver transplant surgeries, exhibited good daily activity, and did not display typical clinical symptoms such as fatigue, bone pain, or spinal deformities associated with prolonged sitting or standing. However, within the fifth year after the second liver transplant, the patient experienced two consecutive fractures. In March 2023, the patient underwent the first bone density test, which revealed osteoporosis. This case highlights the fact that severe fractures after liver transplantation may not necessarily be accompanied by typical symptoms of bone disease. Without timely examination and early prevention, serious consequences may arise. Therefore, this condition requires attention, proactive prevention, early detection, and timely treatment. Additionally, a retrospective analysis of the patient's previous laboratory data revealed persistent abnormalities in serum markers such as hypocalcemia and elevated alkaline phosphatase levels after liver transplantation, emphasizing the importance of monitoring these serum markers.

Long-Term Outcomes of Decompression and Grafting in Acute Pathological Proximal Femur Fractures in Children with Unicameral Bone Cysts: A Retrospective Study Utilizing a 120° Fixed-Angle Low-Contact Locking Pediatric Hip Plate.

BACKGROUND Unicameral bone cysts (UBCs) are benign tumor-like lesions that are the most common cause of pathological proximal femur fracture in children. This study aimed to present the outcomes of acute, unstable, pathological proximal femur fractures secondary to UBCs in children. MATERIAL AND METHODS We retrospectively reviewed data on 12 patients with a mean age of 9.3 years (7-12 years) who were initially treated with decompression and grafting, followed by stabilization using a 120° fixed-angle low-contact locking pediatric plate (LCLPP). The Musculoskeletal Tumor Society (MSTS) scores, Capanna classification of cyst repair, time to union, collodiaphyseal angle (CDA), and limb length discrepancy (LLD) were evaluated. RESULTS The mean follow-up was 33.1 months (range, 13-96 months). The mean union time was 9.5 weeks (8-14 weeks). The mean time for reparation of the cyst was 6.9 months (range 3-9 months). Four patients had Dormans type IB, while the remaining had type IIB fractures. According to the Capanna classification, repairs in 10 cases were grade I and in 2 cases grade II. At the last follow-up, the mean 120.8° of preoperative CDA was corrected to 140.9° (P<0.001) and there was no difference compared to the healthy side (P=0.214). The mean postoperative MSTS score was 97.1% (29.1 points). Two patients experienced LLD at the affected extremities, while the other 10 patients healed without any complications. CONCLUSIONS Fixation of acute unstable fractures secondary to UBCs with a 120° fixed-angle LCLPP is a reliable and successful option after decompression and grafting of the lesion.

Femoral neck fracture after femoral head necrosis: a case report and review of the literature.

INTRODUCTION: Pathological fractures of the femoral neck caused by necrosis of the femoral head are extremely rare. Here, we report a rare case of bilateral femoral head osteonecrosis extending to the femoral neck, with bilateral pathological fractures of the femoral neck occurring within a short period of time. CASE REPORT: A 65-year-old male with a 25-year history of daily consumption of 750 ml of liquor, presented with right hip pain after labor for 1 month. He subsequently sustained a right femoral neck fracture without trauma and underwent a right total hip arthroplasty. Two months later, he suffered a non-traumatic left femoral neck fracture and underwent a left total hip arthroplasty. Histopathological examination revealed osteonecrosis of the femoral head and neck, along with the presence of osteoclasts and granulomatous inflammation. Bone mineral density testing also showed osteoporosis. The bilateral femoral neck fractures were ruled out to be caused by any other pathological factors. DISCUSSION: This is the first report of pathological fractures of the bilateral femoral neck caused by femoral head necrosis. During the literature review process, we found that this case conforms to the histological characteristics of rapidly destructive hip disease and analyzed the etiology of femoral head necrosis and the pathogenesis of femoral neck fractures.

Femoral metastatic pathological fractures, impending and actual fractures - A patient survival study.

INTRODUCTION: The skeleton is a common site for metastases. Prostate, breast, lung, renal and thyroid carcinomas account for 80 % of the original cancers, with the femur being the most affected long bone. With improved oncological treatments, prolonged patient survival leads to an increased prevalence of osseous metastases. This study examines the impact of preventive surgery for impending femoral pathological fracture (IFF), versus treatment of pathological femur fracture (PFF) on patient mortality and morbidity. METHODS: Retrospective cohort of 174 patients undergoing surgery due to femoral metastases (2004-2015). Eighty-two patients were with PFF, and 92 were with IFF based on the Mirels' score. The followed-up period was until 2016. Demographic data, oncological, pathological, radiation, surgical reports, outpatient clinical records, and imaging studies were examined. Exclusion criteria included primary tumours and Multiple Myeloma. RESULTS: The mean age was 64.8 ± 13.3 and 60.2 ± 11.9 years (p = 0.02) in the PFF and the IFF cohorts, with 62.1 % women and 57 % men. The breast was the most common source of femoral metastases. The average Mirels' score was 10 ± 1.2. There was an association between tumour origin and survival. Carcinoma of the lung had the worst survival, while the prostate had the most prolonged survival. Survival rates differed between IFF and PFF (p = 0.03). Postoperative complications occurred in 26 % of the patient, with no difference between IFF & PFF. CONCLUSION: Breast and lung are the most common tumours to metastasize the femur. Our study revalidates that pathological femoral fractures impede patient survival compared to impending fractures and should undergo preventive surgery. Postoperative complications do not differ between IFF and PFF but remain relatively high. Overall, patients with proximal femoral metastatic disease survive longer than previously published, probably due to improved treatment modalities.

Orthopaedic surgeons' ability to detect pathologic hip fractures: review of 1484 fractures reported to the Norwegian Hip Fracture Register.

BACKGROUND: The proximal femur is the most common location of metastases in the appendicular skeleton. Data on pathologic hip fractures, however, are sparse despite it is the most frequently operated pathologic fracture. The aim of this study was to investigate the ability of orthopaedic surgeons to identify pathologic hip fractures in an acute setting and secondly to validate the underlying cause of the pathologic fractures reported to Norwegian Hip Fracture Register (NHFR). METHODS: In the NHFR dataset between 2005 and 2019, we identified 1484 fractures reported to be pathologic possibly secondary to a malignancy. These fractures were thoroughly validated by reviewing X-rays, the patient journal, the operation description for date, side, why there had been suspicion of pathologic fracture, and implant choice. Pathology reports were reviewed once a biopsy had been performed. Based on this validation, information in the NHFR was corrected, whenever necessary. RESULTS: Of the 1484 fractures possible secondary to malignancy, 485 (32.7%) were not a pathologic fracture. When reviewing the 999 validated pathologic fractures, 15 patients had a pathologic fracture secondary to a benign lesion. The remaining 984 patients had a pathologic fracture secondary to malignancy. The underlying diagnosis reported was corrected in 442 of the 999 patients. The true rate of pathologic hip fractures secondary to malignancy in our material was 0.8%, and most patients had underlying prostate (30%), breast (20%), or lung (17%) cancer. CONCLUSION: Orthopaedic surgeons in Norway failed to report correct data on pathologic fractures and the corresponding cancer diagnosis in an acute setting in many patients. The corrected data on pathologic fractures in the NHFR from 2005 to 2019 can now be a valid resource for further studies on the subject.

Myeloid sarcoma and pathological fracture: a case report and review of literature.

Myeloid sarcoma is a rare clinical entity that presents as an isolated proliferation of leukemic cells, concurrently with or at relapse of acute myeloid leukemia (AML), myelodysplastic syndromes/neoplasms (MDS), chronic myeloid leukemia (CML), and myeloproliferative neoplasm (MPN). Myeloid sarcoma disrupts the normal architecture of its surrounding tissues. When it forms in long bones, it can cause their pathological fracture. We recently experienced a rare case of MDS presenting with myeloid sarcoma in the femur that eventually resulted in its pathological fracture. Detailed chromosomal analysis of the bone marrow cells suggested emergence of myeloid sarcoma during the fast-paced progression of MDS just after acquiring trisomy 22. A comprehensive review of previous cases of myeloid sarcoma-associated pathological fracture indicated possible involvement of structural rearrangements of chromosomes 9 and 22. Management of myeloid sarcoma should continue to improve, and clinicians should note that myeloid sarcoma with specific chromosomal alterations needs extra medical attention to prevent pathological fracture.

Intramedullary nailing versus cemented plate for treating metastatic pathological fracture of the proximal humerus: a comparison study and literature review.

BACKGROUND: Pathological fracture of the humerus causes severe pain, limited use of the hand, and decreased quality of life. This study aimed to compare the outcomes of intramedullary nailing and locking plate in treating metastatic pathological fractures of the proximal humerus. METHODS: This retrospective comparison study included 45 patients (22 male, 23 female) with proximal humerus metastatic pathological fractures who underwent surgical treatment between 2011 and 2022. All data were collected from medical records and were analyzed retrospectively. Seventeen cases underwent intramedullary nailing plus cement augmentation, and 28 cases underwent locking plate plus cement augmentation. The main outcomes were pain relief, function scores, and complications. RESULTS: Among 45 patients with mean age 61.7 ± 9.7 years, 23 (51.1%) had multiple bone metastases, and 28 (62.2%) were diagnosed with impending fractures. The nailing group had significantly lower blood loss [100 (60-200) versus 500 (350-600) ml, p < 0.001] and shorter hospital stay (8.4 ± 2.6 versus 12.3 ± 4.3 days, p < 0.001) than the plating group. Average follow-up time of the nailing group was 12 months and 16.5 months for the plating group. The nailing group had higher visual analog scale (VAS) scores than the plating group, indicating greater pain relief with nailing [7 (6-8) versus 6 (5-7), p = 0.01]. Musculoskeletal Tumor Society functional scores [28 (27-29) versus 27 (26.5-28.5), p = 0.23] were comparable between groups. No complications, local recurrence, or revision surgery were reported until the last follow-up in either group. However, one case in the plating group had a humeral head collapse and fragmentation without needing revision surgery. CONCLUSIONS: Intramedullary nailing with cement augmentation is a viable option for treating proximal humerus metastatic pathological fracture, providing rigid fixation and better pain relief resulting in earlier mobility to optimize functional outcomes. Less invasive procedure with less blood loss and shorter hospital stay also benefits patients. Level of evidence Level II. Trial registration statement Not applicable.

Development and Validation of a Convolutional Neural Network Model to Predict a Pathologic Fracture in the Proximal Femur Using Abdomen and Pelvis CT Images of Patients With Advanced Cancer.

BACKGROUND: Improvement in survival in patients with advanced cancer is accompanied by an increased probability of bone metastasis and related pathologic fractures (especially in the proximal femur). The few systems proposed and used to diagnose impending fractures owing to metastasis and to ultimately prevent future fractures have practical limitations; thus, novel screening tools are essential. A CT scan of the abdomen and pelvis is a standard modality for staging and follow-up in patients with cancer, and radiologic assessments of the proximal femur are possible with CT-based digitally reconstructed radiographs. Deep-learning models, such as convolutional neural networks (CNNs), may be able to predict pathologic fractures from digitally reconstructed radiographs, but to our knowledge, they have not been tested for this application. QUESTIONS/PURPOSES: (1) How accurate is a CNN model for predicting a pathologic fracture in a proximal femur with metastasis using digitally reconstructed radiographs of the abdomen and pelvis CT images in patients with advanced cancer? (2) Do CNN models perform better than clinicians with varying backgrounds and experience levels in predicting a pathologic fracture on abdomen and pelvis CT images without any knowledge of the patients' histories, except for metastasis in the proximal femur? METHODS: A total of 392 patients received radiation treatment of the proximal femur at three hospitals from January 2011 to December 2021. The patients had 2945 CT scans of the abdomen and pelvis for systemic evaluation and follow-up in relation to their primary cancer. In 33% of the CT scans (974), it was impossible to identify whether a pathologic fracture developed within 3 months after each CT image was acquired, and these were excluded. Finally, 1971 cases with a mean age of 59 ± 12 years were included in this study. Pathologic fractures developed within 3 months after CT in 3% (60 of 1971) of cases. A total of 47% (936 of 1971) were women. Sixty cases had an established pathologic fracture within 3 months after each CT scan, and another group of 1911 cases had no established pathologic fracture within 3 months after CT scan. The mean age of the cases in the former and latter groups was 64 ± 11 years and 59 ± 12 years, respectively, and 32% (19 of 60) and 53% (1016 of 1911) of cases, respectively, were female. Digitally reconstructed radiographs were generated with perspective projections of three-dimensional CT volumes onto two-dimensional planes. Then, 1557 images from one hospital were used for a training set. To verify that the deep-learning models could consistently operate even in hospitals with a different medical environment, 414 images from other hospitals were used for external validation. The number of images in the groups with and without a pathologic fracture within 3 months after each CT scan increased from 1911 to 22,932 and from 60 to 720, respectively, using data augmentation methods that are known to be an effective way to boost the performance of deep-learning models. Three CNNs (VGG16, ResNet50, and DenseNet121) were fine-tuned using digitally reconstructed radiographs. For performance measures, the area under the receiver operating characteristic curve, accuracy, sensitivity, specificity, precision, and F1 score were determined. The area under the receiver operating characteristic curve was used to evaluate three CNN models mainly, and the optimal accuracy, sensitivity, and specificity were calculated using the Youden J statistic. Accuracy refers to the proportion of fractures in the groups with and without a pathologic fracture within 3 months after each CT scan that were accurately predicted by the CNN model. Sensitivity and specificity represent the proportion of accurately predicted fractures among those with and without a pathologic fracture within 3 months after each CT scan, respectively. Precision is a measure of how few false-positives the model produces. The F1 score is a harmonic mean of sensitivity and precision, which have a tradeoff relationship. Gradient-weighted class activation mapping images were created to check whether the CNN model correctly focused on potential pathologic fracture regions. The CNN model with the best performance was compared with the performance of clinicians. RESULTS: DenseNet121 showed the best performance in identifying pathologic fractures; the area under the receiver operating characteristic curve for DenseNet121 was larger than those for VGG16 (0.77 ± 0.07 [95% CI 0.75 to 0.79] versus 0.71 ± 0.08 [95% CI 0.69 to 0.73]; p = 0.001) and ResNet50 (0.77 ± 0.07 [95% CI 0.75 to 0.79] versus 0.72 ± 0.09 [95% CI 0.69 to 0.74]; p = 0.001). Specifically, DenseNet121 scored the highest in sensitivity (0.22 ± 0.07 [95% CI 0.20 to 0.24]), precision (0.72 ± 0.19 [95% CI 0.67 to 0.77]), and F1 score (0.34 ± 0.10 [95% CI 0.31 to 0.37]), and it focused accurately on the region with the expected pathologic fracture. Further, DenseNet121 was less likely than clinicians to mispredict cases in which there was no pathologic fracture than cases in which there was a fracture; the performance of DenseNet121 was better than clinician performance in terms of specificity (0.98 ± 0.01 [95% CI 0.98 to 0.99] versus 0.86 ± 0.09 [95% CI 0.81 to 0.91]; p = 0.01), precision (0.72 ± 0.19 [95% CI 0.67 to 0.77] versus 0.11 ± 0.10 [95% CI 0.05 to 0.17]; p = 0.0001), and F1 score (0.34 ± 0.10 [95% CI 0.31 to 0.37] versus 0.17 ± 0.15 [95% CI 0.08 to 0.26]; p = 0.0001). CONCLUSION: CNN models may be able to accurately predict impending pathologic fractures from digitally reconstructed radiographs of the abdomen and pelvis CT images that clinicians may not anticipate; this can assist medical, radiation, and orthopaedic oncologists clinically. To achieve better performance, ensemble-learning models using knowledge of the patients' histories should be developed and validated. The code for our model is publicly available online at https://github.com/taehoonko/CNN_path_fx_prediction . LEVEL OF EVIDENCE: Level III, diagnostic study.