Prognostic factors in patients with metastatic spinal cord compression secondary to lung cancer: a systematic review of the literature

Establishment and validation of an interactive artificial intelligence platform to predict postoperative ambulatory status for patients with metastatic spinal disease: a multicenter analysis

BACKGROUND

Identification of patients with high-risk of experiencing inability to walk after surgery is important for surgeons to make therapeutic strategies for patients with metastatic spinal disease. However, there is a lack of clinical tool to assess postoperative ambulatory status for those patients. The emergence of artificial intelligence (AI) brings a promising opportunity to develop accurate prediction models.

METHODS

This study collected 455 patients with metastatic spinal disease who underwent posterior decompressive surgery at three tertiary medical institutions. Of these, 220 patients were collected from one medical institution to form the model derivation cohort, while 89 and 146 patients were collected from two other medical institutions to form the external validation cohorts 1 and 2, respectively. Patients in the model derivation cohort were used to develop and internally validate models. To establish the interactive AI platform, machine learning techniques were used to develop prediction models, including logistic regression (LR), decision tree (DT), random forest (RF), extreme gradient boosting machine (eXGBM), support vector machine (SVM), and neural network (NN). Furthermore, to enhance the resilience of the study's model, an ensemble machine learning approach was employed using a soft-voting method by combining the results of the above six algorithms. A scoring system incorporating 10 evaluation metrics was used to comprehensively assess the prediction performance of the developed models. The scoring system had a total score of 0 to 60, with higher scores denoting better prediction performance. An interactive AI platform was further deployed via Streamlit. The prediction performance was compared between medical experts and the AI platform in assessing the risk of experiencing postoperative inability to walk among patients with metastatic spinal disease.

RESULTS

Among all developed models, the ensemble model outperformed the six other models with the highest score of 57, followed by the eXGBM model (54), SVM model (50), and NN model (50). The ensemble model had the best performance in accuracy and calibration slope, and the second-best performance in precise, recall, specificity, area under the curve (AUC), Brier score, and log loss. The scores of the LR model, RF model, and DT model were 39, 46, and 26, respectively. External validation demonstrated that the ensemble model had an AUC value of 0.873 (95% CI: 0.809-0.936) in the external validation cohort 1 and 0.924 (95% CI: 0.890-0.959) in the external validation cohort 2. In the new ensemble machine learning model excluding the feature of the number of comorbidities, the AUC value was still as high as 0.916 (95% CI: 0.863-0.969). In addition, the AUC values of the new model were 0.880 (95% CI: 0.819-0.940) in the external validation cohort 1 and 0.922 (95% CI: 0.887-0.958) in the external validation cohort 2, indicating favorable generalization of the model. The interactive AI platform was further deployed online based on the final machine learning model, and it was available at https://postoperativeambulatory-izpdr6gsxxwhitr8fubutd.streamlit.app/ . By using the AI platform, researchers were able to obtain the individual predicted risk of postoperative inability to walk, gain insights into the key factors influencing the outcome, and find the stratified therapeutic recommendations. The AUC value obtained from the AI platform was significantly higher than the average AUC value achieved by the medical experts ( P <0.001), denoting that the AI platform obviously outperformed the individual medical experts.

CONCLUSIONS

The study successfully develops and validates an interactive AI platform for evaluating the risk of postoperative loss of ambulatory ability in patients with metastatic spinal disease. This AI platform has the potential to serve as a valuable model for guiding healthcare professionals in implementing surgical plans and ultimately enhancing patient outcomes.

Osteoblastic Bone Reaction Developing During Treatment With Sintilimab and Bevacizumab in a Patient With KRASG12V-Mutant Lung Adenocarcinoma

Osteoblastic bone reaction, the occurrence of new osteoblastic lesions, is a paradoxical phenomenon during the treatment of cancers and can be defined as disease progression or bone metastases. Osteoblastic bone reactions usually occur in patients who receive treatments such as chemotherapy or hormonal or targeted therapy; however, it is difficult to differentiate them from disease progression or an increase in osteoblastic activity in response to therapy. Although osteoblastic bone reaction in lung cancer has been described in a few reports, it has never been reported in patients with KRASG12V-mutant lung adenocarcinoma treated with immunotherapy and antiangiogenesis. Here, we describe a case of a 77-year-old male with KRASG12V-mutant lung adenocarcinoma whose osteoblastic bone response was found during treatment with sintilimab and bevacizumab. We showed the course of the disease as well as systematic imaging manifestations of lung cancer with osteoblastic bone reaction and discussed their mechanisms.

Multiple Myeloma Rather Than Metastatic Lung Cancer: An Unexpected Cause of Spinal Cord Compression

Spinal cord compression caused by cancer metastasis is a medical emergency that should be managed positively. Both multiple myeloma and lung cancer can lead to metastatic deposits in the spinal column to induce compression of the spinal cord. However, co-occurring multiple myeloma and lung cancer in a single patient causing spinal cord compression are rarely reported in the literature. We describe a case of a 61-year-old female with multiple myeloma and lung cancer whose radiologic characteristics of spinal cord compression mimicked those of metastatic lung cancer. Finally, the diagnosis was multiple myeloma. We showed the systematic imaging manifestations of metastatic multiple myeloma and discussed their therapeutic management.

Prognostic Factors in Patients with Metastatic Spinal Cord Compression Secondary to Lung Cancer-A Retrospective UK Single-Centre Study

PURPOSE

Metastatic spinal cord compression (MSCC) is a severe complication of cancer that can lead to irreversible neurological impairment, necessitating prompt recognition and intervention. This retrospective, single-centre study aimed to determine the prognostic factors and survival rates among patients presenting with MSCC secondary to lung cancer.

METHODS AND MATERIALS

We identified 74 patients with epidural metastases-related spinal cord compression and a history of lung cancer through the electronic database of Medway Maritime Hospital in the United Kingdom (UK), spanning the period from April 2016 to September 2021. Among them, 39 were below 55 years old, while 35 were aged 55 years or older; 24 patients were diagnosed with small cell lung cancer (SCLC), and 50 patients had non-small cell lung cancer (NSCLC).

RESULTS

The median overall survival (OS) was 5.5 months, with 52 out of 74 patients dying within 6 months of diagnosis with MSCC. For the entire cohort, the statistically significant variables on multi-variate analysis were cancer type (NSCLC had improved OS), the number of involved vertebrae (one to two vertebrae involvement had improved OS), and the time taken to develop motor deficits (≤10 days to develop motor deficits had worsened OS). For the NSCLC cohort, the statistically significant variables on multivariate analysis were molecular alterations (patients with epidermal growth factor receptor (EGFR) mutation), pre-treatment ambulatory status, Eastern Cooperative Oncology Group (ECOG) performance status, and the time taken to develop motor deficits.

CONCLUSIONS

Within the entire cohort, patients diagnosed with NSCLC and spinal metastases affecting one to two vertebrae exhibited enhanced OS. Within the NSCLC subgroup, those with EGFR mutations who were ambulatory and possessed an ECOG performance status of 1-2 demonstrated improved OS. In both the entire cohort and the NSCLC subgroup, the development of motor deficits within a period of ≤10 days was associated with poor OS.

Prognostic factors and outcomes of surgical intervention for patients with spinal metastases secondary to lung cancer: an update systematic review and meta analysis

PURPOSE

Lung cancer is one of the most common malignant tumors. Most patients develop spinal metastases during the course of cancer and suffer skeletal-related events. Currently, no consensus has been reached on the prognostic factors in patients undergoing surgeries. This study aimed to answer two questions: (1) what are the effects of surgical intervention, and (2) what are the factors associated with postoperative survival.

METHODS

Searches were performed on electronic databases including PubMed, Ovid/MEDLINE, Cochrane, and Scopus for articles published before February of 2022, involving the survival factors of patients with spinal metastasis. Multiple data items were considered, such as baseline demographics, surgical details, clinical outcome, and prognostic factors. The analysis was performed in Review Manager (RevMan) 5.5. The prognostic factors of survival were analyzed with univariate and multivariate cox regression analysis.

RESULTS

Finally, 14 studies with 813 patients were identified. Their 6, 12, and 24 months survival rates ranged from 18 to 58%, 18 to 22.4%, and 0 to 58.5%, respectively. The pooled hazard ratio of preoperative ambulatory status and the number of involved vertebrae demonstrated statistical significance, while no significant prognostic effect on the overall survival was found for targeted therapy, visceral metastases, chemotherapy, radiotherapy, or postoperative ambulatory status.

CONCLUSION

Overall, surgical intervention could achieve significant pain relief and neurological function improvements. For patients receiving surgery for spinal metastasis from lung cancer, preoperative ambulatory status and the number of involved vertebrae were significant prognostic factors associated with their survival.

National trends in the surgical management of metastatic lung cancer to the spine using the national inpatient sample database from 2005 to 2014

Optimal management of metastatic lung cancer to the spine (MLCS) incorporates a multidisciplinary approach. With improvements in lung cancer screening andnonsurgical treatment, the role for surgerymay be affected. The objective of this study is to assess trends in the surgical management of MLCS using the National Inpatient Sample (NIS) database. The NIS was queried for patients with MLCS who underwent surgery from 2005 to 2014. The frequencies of spinal decompression alone, spinal stabilization with or without (+/-) decompression, and vertebral augmentation were calculated. Statistical analysis was performed to analyze the effect of patient characteristics on outcomes. The most common procedure performed was vertebral augmentation (10719, 44.3%), followed by spinal stabilization +/- decompression (8634, 35.7%) and then decompression alone (4824, 20.0%). The total number of surgeries remained stable, while the rate of spinal stabilizations increased throughout the study period (p < 0.001). Invasive procedures such as stabilization and decompression were associated with greater costs, length of stay,complications and mortality. Increasingcomorbidity was associated with increased odds of complication, especially in patients undergoing more invasive procedures. In patients with lowpre-operative comorbidity, the type of procedure did not influence the odds of complication. Graded increases in length of stay, cost and mortality were seen with increasing complication rate.The rate of spinal stabilizations increased, which may be due to either increased early detection of disease facilitating use of outpatient vertebral augmentation procedures and/or the recognition that surgical decompression and stabilization are necessary for optimal outcome in the setting of MLCS with neurological deficit.

Predictors of overall survival in non-small-cell lung cancer patients with metastatic spinal cord compression treated with short-course radiotherapy

Metastatic spinal cord compression (MSCC) is a condition that impacts directly on the patient's prognosis.

OBJECTIVE

The study purpose was to identify predictors of overall survival in non-small-cell lung cancer (NSCLC) patients with MSCC.

METHODS

A cohort study involving NSCLC patients enrolled between 2008 and 2017 was performed. Sixty-four patients treated with short-course radiotherapy were included. Clinical and socio-demographic data were extracted from medical records. Data were analysed using survival analysis and Cox proportional hazard regression analysis.

RESULTS

The median survival time was 2.5 months (95% CI: 1.6-3.5). Patients >60 years had shorter survival than younger patients (HR 1.85; 95% CI 1.06-3.24; p = 0.02), and patients with performance status (PS) >2 had shorter survival than those with PS≤2 (HR 1.93; 95% CI 1.12-3.33; p = 0.01).

CONCLUSION

This study found worse PS and higher age are independent predictors of overall survival in NSCLC patients with MSCC treated with short-course radiotherapy after adjusting the potential confounding factors (PS, age and target therapy).

Is Open Surgery for Metastatic Spinal Cord Compression Secondary to Lung Cancer Really Beneficial? A Systematic Review

OBJECTIVE

Spinal cord compression secondary to metastatic epidural lung cancer generally has a worse prognosis when compared with other metastatic tumors. The purpose of this study was to determine the impact of open surgery on the survival time, ambulation status, and associated prognostic variables of these patients over the past 2 decades.

METHODS

We searched the PubMed, MEDLINE, and CENTRAL databases to identify patients with spinal cord compression secondary to metastatic lung cancer. We assessed the role of the following factors on survival outcome and ambulation recovery: Karnofsky Performance Scale, number of extraspinal bone metastases, number of metastases in the vertebrae, major internal organs involvement, vertebral location of spinal metastases, and neurologic status.

RESULTS

Our initial search yielded 367 articles, from which 11 studies met the eligibility criteria for a total of 395 patients. Significant correlations with the survival period and the recovery in ambulation were found in the prognostic score for the number of metastases in vertebrae (R = 0.74 and 0.88, respectively), and in the prognostic score for metastases to major internal organs (R = 0.82 and 0.81, respectively). A significant correlation with survival period was found in the numbers of extraspinal bone metastases (R = -0.82). The rates of major complications were comparable with those for open surgery for metastatic tumors of other origin.

CONCLUSIONS

Fewer vertebral metastases and less major internal organ involvement were associated with longer survival periods and greater ambulation recovery in patients undergoing open surgery for spinal cord compression secondary to metastatic lung cancer.

Predictive Analytics in Spine Oncology Research: First Steps, Limitations, and Future Directions

The potential of big data analytics to improve the quality of care for patients with spine tumors is significant. At this moment, the application of big data analytics to oncology and spine surgery is at a nascent stage. As such, efforts are underway to advance data-driven oncologic care, improve patient outcomes, and guide clinical decision making. This is both relevant and critical in the practice of spine oncology as clinical decision making is often made in isolation looking at select variables deemed relevant by the physician. With rapidly evolving therapeutics in surgery, radiation, interventional radiology, and oncology, there is a need to better develop decision-making algorithms utilizing the vast data available for each patient. The challenges and limitations inherent to big data analyses are presented with an eye towards future directions.

Prognostic factors in patients with metastatic spinal cord compression secondary to melanoma: a systematic review

Melanoma is one of the most common primary tumours associated with metastatic spinal cord compression (MSCC). The aim of this review is to identify prognostic factors specifically for MSCC secondary to melanoma. A systematic search of literature was performed in MEDLINE, Embase and the Cochrane Library to identify studies reporting prognostic factors for patients with MSCC secondary to melanoma. Two studies, involving a total of 39 patients, fulfilled the inclusion criteria. The variables associated with increased survival were receiving postoperative radiotherapy, receiving chemotherapy, perioperative lactate dehydrogenase level less than or equal to 8.0 µkat/l, preoperative haemoglobin level more than 11.5 mg/dl, an interval of 4 or more years between melanoma diagnosis and skeletal metastasis, absence of further skeletal metastases, absence of visceral metastases, Eastern Cooperative Oncology Group Performance Status of 2 or less, two or fewer involved vertebrae, being ambulatory preradiotherapy and an interval of more than 7 days between developing motor deficits and radiotherapy. The variables associated with good functional outcome were slow development of motor dysfunction, good performance status and being ambulatory before radiotherapy. The most important prognostic factors for survival are Eastern Cooperative Oncology Group Performance Status of 2 or less and absence of visceral metastases. There is a lack of studies looking specifically at prognostic factors for patients with MSCC secondary to melanoma, and the number of patients involved in the existing studies is small.

[Clinical Features of Intradural Extramedullary Spinal Cord Metastases in Primary Lung Cancer]

背景与目的

肺癌硬膜下脊髓外转移罕见, 可导致严重的神经损害, 本研究旨在阐明其临床特征。

方法

2013年5月-2016年5月, 北京协和医院8例确诊硬膜下脊髓外转移肺癌患者纳入该研究, 系统回顾分析临床资料。

结果

7例非小细胞肺癌及1例小细胞肺癌合并硬膜下脊髓外转移。马尾综合征是最常见的临床表现。行腰椎穿刺的5例(100%)患者脑脊液找到肿瘤细胞。脊髓增强核磁(magnetic resonance imaging, MRI)发现, 3例软脊膜弥漫线样增强, 4例硬膜下脊髓外多发结节, 1例具有上述两种表现。4例接受靶向治疗和/或放疗患者神经系统症状改善或稳定。中位生存时间是5.8个月。

结论

硬膜下脊髓外转移需依靠神经系统症状及增强MRI影像学检查诊断。靶向治疗和/或放疗可能有效。

Results of a multicenter study investigating the potential impact of the overall treatment time on outcomes of radiation therapy alone with 5×4 Gy for metastatic epidural spinal cord compression

PURPOSE/OBJECTIVE

A 5×4 Gy program is commonly used for metastatic epidural spinal cord compression (MESCC). It is unclear whether an overall treatment time (OTT) of 5 days (5 consecutive fractions) results in better outcomes than an OTT of 7 days (ie, no irradiation during the weekend).

METHODS AND MATERIALS

A total of 111 patients who received 5×4 Gy over 5 consecutive days were retrospectively compared with 277 patients treated with 5×4 Gy over 7 days (no irradiation during the weekend) for effect on motor function, local control of MESCC, and overall survival (OS). Ten further characteristics were evaluated: age, gender, interval tumor diagnosis to MESCC, visceral metastases, other bone metastases, primary tumor type, time developing motor deficits, walking ability, vertebrae involved, and performance status.

RESULTS

On multivariate analysis regarding post-radiation therapy motor function, primary tumor type (P = .011) and time developing motor weakness (P < .001) were significant, whereas the OTT did not even achieve significance on univariate analysis (P = .99). On multivariate analysis of local control, visceral metastases (P = .006) were significant. Again, the OTT was not even significant on univariate analysis (P = .81). On multivariate analysis of OS, interval tumor diagnosis to MESCC (P = .015), visceral metastases (P .001), tumor type (P = .003), walking ability (P < .001), and Eastern Cooperative Oncology Group performance score (P < .001) achieved significance. Even on univariate analysis, OTT did not have an effect on OS (P = .79).

CONCLUSIONS

Longer OTT did not impair outcomes of irradiation with 5×4 Gy for MESCC; thus, no compensation (for example an additional radiation fraction) is necessary if the radiation treatment is not continued during the weekend.