Machine Learning-Based Prediction of Pulmonary Embolism to Reduce Unnecessary Computed Tomography Scans in Gastrointestinal Cancer Patients: A Retrospective Multicenter Study

doi:10.21203/rs.3.rs-3988494/v1

Download PDF

Article

Machine Learning-Based Prediction of Pulmonary Embolism to Reduce Unnecessary Computed Tomography Scans in Gastrointestinal Cancer Patients: A Retrospective Multicenter Study

https://doi.org/10.21203/rs.3.rs-3988494/v1

This work is licensed under a CC BY 4.0 License

Journal Publication

published 25 Oct, 2024

Read the published version in Scientific Reports →

You are reading this latest preprint version

Background

Pulmonary embolism (PE) is one of the most important complications in cancer patients. Gastrointestinal cancers entail an increased risk of PE. However, there were few researches on predicting pulmonary embolism using machine learning (ML) in cancer patients. The purpose of this study was to develop an ML based prediction model for PE in gastrointestinal cancer patients.

Methods

We conducted a retrospective, multicenter study in which ML model was developed and subsequently internally and externally validated. We reviewed gastrointestinal cancer patients who had undergone computed tomographic pulmonary angiography (CTPA) from 2010 to 2020. Demographic and predictor variables including the Wells score and D-dimer were investigated. The ML model was based on the random forest model. The area under receiver operating curve (AUROC) was used to evaluate the performance of ML model.

Results

446 patients in hospital A and 139 patients in hospital B were analyzed in this study. The training set comprised 356 patients in hospital A. The ML model was validated both internally (90 patients) and externally (139 patients). AUROC was 0.736 in hospital A and 0.669 in hospital B. The number of patients classified as requiring CTPA was significantly reduced according to the prediction with ML (hospital A; 100.0% vs 91.1%, P < 0.001, hospital B; 100.0% vs. 93.5%, P = 0.003).

Conclusion

Prediction model based on ML might have advantages in reducing the number of CTPA compared to the conventional diagnostic strategy for PE in patients with gastrointestinal cancer.

Health sciences/Diseases/Cancer/Gastrointestinal cancer

Health sciences/Oncology/Cancer/Gastrointestinal cancer

Health sciences/Diseases/Cardiovascular diseases/Vascular diseases/Embolism

Health sciences/Diseases/Cardiovascular diseases/Vascular diseases/Thromboembolism

Pulmonary embolism

machine learning

gastrointestinal cancer

computed tomographic pulmonary angiography

random forest model

Venous embolism (VTE) occurs in 15%-20% of cancer patients¹. In the cancer populations, VTE increases the risk of death^2–4. Epidemiological studies have reported the highest risk of VTE in intra-abdominal cancers, including gastrointestinal cancers^5–7. Among VTEs, pulmonary embolism (PE) is a clinically important disease that requires urgent management. Early detection is crucial because massive PE can lead to cardiac arrest or circulatory collapse, both associated with high mortality rates⁸.

Many studies have developed diagnostic strategies for PE. These strategies aim to identify low-risk patients for PE in whom imaging studies and anticoagulation therapy can be safely withheld⁹. Assessments of clinical pretest probability (C-PTP), such as the Wells score, are most often used in combination with the D-dimer test. It is well established that patients with low C-PTP and D-dimer levels of less than 500ng per milliliter are considered to have ruled out PE^9–11. However, these patients constitute only approximately 30% of outpatients¹².

Computed tomography pulmonary angiography (CTPA) is the method of choice for the evaluation of pulmonary vasculature in patients with suspected PE¹⁰. However, CTPA is associated with issues such as radiation exposure, potential side effects from contrast media, and cost. Efforts have been made to reduce unnecessary CTPA in patients with suspected PE. Several studies explored modifying the cut-off value of the D-dimer test^{12, 13}. More recently, there have been studies to improve the diagnosis of PE using artificial intelligence. In one study, machine learning (ML) was used to support clinical decision-making for CTPA in patients with moderate to high C-PTP¹⁴. Another study utilized ML for risk-stratification of deep vein thrombosis (DVT) using the Wells score and D-dimer¹⁵. However, there are few studies utilizing ML to aid in the decision-making for CTPA in cancer patients suspected of having PE.

Applying the existing diagnostic methods for PE to cancer patients has limitations. This is primarily because cancer patients tend to have elevated D-dimer levels¹⁶. PE is relatively common in gastrointestinal cancers^5–7. Therefore, our objective was to improve the diagnostic strategy for PE in gastrointestinal cancer patients using ML, aiming to reduce unnecessary CTPA scans.

Study design and patients

This retrospective, multicenter study investigated the patients with gastrointestinal cancer who underwent CTPA between 2010 and 2020, using an electrical medical records database (Fig. 1). Data from Hospital A (Seoul National University Hospital, Seoul, Korea) were used for development and internal validation. Data from Hospital B (Seoul National University Bundang Hospital, Seongnam-si, Korea) were used for external validation. The diagnosis of gastrointestinal cancer was confirmed by the pathological results. Hepatocellular carcinoma diagnosed based on imaging without pathological confirmation was also included¹⁷. The patients with exclusion criteria were not included in the analysis. Exclusion criteria were as follow; suspected PE associated with causes other than cancer or other malignancy, no evidence of malignancy at the time of CTPA, ambiguous diagnosis of PE on CTPA, missing data. And we checked heart rate by electrocardiography, we excluded patients who did not have an electrocardiogram at the time of the CTPA. Diagnosis of PE was confirmed by trained experts based on CTPA.

This study was approved by the institutional review board (IRB) of the Seoul National University Hospital, Korea (IRB No.2009-146-1159) and the Seoul National University Bundang Hospital, Korea (IRB No.B-2111-721-401). The need for informed consent was waived by the IRB. The study was conducted in accordance with the Declaration of Helsinki.

Data collection and definition

Patient characteristics were retrospectively collected including age, sex, cancer diagnosis, the Wells score and components of the Wells score, and D-dimer. Gastrointestinal cancers were defined as cancers of gastrointestinal tract from esophagus to anus, cancers of liver and pancreatobiliary system¹⁸. The Wells score was calculated as previously used in patients suspected PE¹⁹. Components of the Wells score included signs and symptoms of VTE, alternative diagnosis less likely than pulmonary embolism, heart rate > 100 beats per minute, history of VTE, immobilization, malignancy, hemoptysis. Among them, we did not include malignancy because all of the subjects were diagnosed with cancer. History of VTE was defined as previous history of PE or DVT¹⁹. A low C-PTP was defined as a Wells score of 0 to 1.5, a moderate C-PTP was 2.0 to 6.0 and a high C-PTP was 6.5 or higher ¹⁹.

Study outcome measures

The primary outcome of this study was the area under the receiver operating characteristics curve (AUROC) and accuracy of ML model for diagnosis of PE in patients with gastrointestinal cancer.

As a secondary outcome, we compared the number of performed CTPA for PE in the ML model with the conventional diagnostic strategy. We also investigated feature importance of the ML model.

Statistical analysis

To compare the baseline characteristics, the Student’s t-test and Chi-square test were used for continuous and dichotomous variables, respectively. If any subgroups had less than four subjects, the Fisher’s exact test was used instead of a Chi-square test.

We utilized components of wells score and incorporated D-dimer as a continuous variable in machine learning training. D-dimer was used as a continuous variable. We evaluated our model using the hold-out test method. We performed a 5-fold cross validation on 80% of the subjects to find the optimal hyperparameters. Subsequently, we evaluated the model using the remaining 20% of the subjects. To evaluate this, we measured the performance of the model using the area under the receiver operating characteristics curve (AUROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). To determine the optimal cutoff, we identified the point at which sensitivity reached 1.0²⁰.

The random forest model showed good performance in regression and classification, especially in the healthcare field, where deep learning is not accessible due to the lack of data ^{21, 22}. Although PE is an important disease, the number is relatively small, so we used the random forest model²³. The random forest model can track which features the model mainly considered in the process of making decisions. This is a form of explainable artificial intelligence, which can solve the model reliability problem that most deep learning algorithms currently have. In this paper, we used SHAP (Shapley Additive exPlanations) algorithm²⁴. The SHAP values generated by the algorithm allowed us to interpret the relative importance of each feature in influencing the model's predictions. Consequently, using this SHAP values, we determined how each feature is influenced for classifying the data. In this paper, we used impurity-based feature importance²⁵.

P-value lower than 0.05 indicated statistical significance. Statistical calculations were performed with SPSS and scikit-learn's random forest model. To measure the feature importance, the SHAP algorithm was used. When comparing prediction ROC curves between models, statistical analysis based on the Delong test was performed.

Baseline characteristics of the study population

In hospital A, 708 patients diagnosed with gastrointestinal cancer underwent CTPA and 262 were excluded because of the exclusion criteria thus, a total of 446 patients were analyzed. In hospital B, 388 patients diagnosed with gastrointestinal cancer underwent CTPA and 249 were excluded (Fig. 1). In training set, 103 (28.9%) patients were diagnosed with PE. Table 1 shows the comparison of baseline characteristics according to PE in the development dataset. Pancreatic cancer was the most common type of cancer in patients with PE (33.0%). Patients with PE had more high C-PTP (40.8% vs. 23.3%, P < 0.001). Patients suspected with DVT was higher in patients with PE (48.5% vs. 26.9%, P < 0.001). History of VTE (2.4% vs. 14.6%, P < 0.001) was more common in patients with PE. There was no significant difference between the two groups in other variables.

Table 1

Baseline characteristics of patients according to the presence of pulmonary embolism.
	All patients	Patients without PE	Patients with PE
	(n = 356)	(n = 253)	(n = 103)	P value
Age (mean)	66.5\(\pm\)11.1	66.8\(\pm\)10.9	65.5\(\pm\)11.6	0.318
Male (%)	243 (68.3)	177 (70.0)	66 (64.1)	0.339
Cancer (%)				< 0.001
Gastric cancer	70 (19.7)	58 (22.9)	12 (11.7)
Colon cancer	72 (20.2)	49 (19.4)	23 (22.3)
Hepatocellular carcinoma	81 (22.8)	65 (25.7)	16 (15.5)
Pancreatic cancer	71 (19.9)	37 (14.6)	34 (33.0)
Cholangiocarcinoma	40 (11.2)	26 (10.3)	14 (13.6)
Others	22 (6.2)	18 (7.1)	4 (3.9)
Components of Wells score (%)
Signs and symptoms of DVT	118 (33.1)	68 (26.9)	50 (48.5)	< 0.001
Alternative diagnosis less likely than PE	168 (47.2)	114 (45.1)	54 (52.4)	0.252
Heart rate > 100/min	160 (44.9)	113 (44.7)	47 (45.6)	0.961
Immobilization	136 (38.2)	91 (36.0)	45 (43.7)	0.215
History of VTE	21 (5.9)	6 (2.4)	15 (14.6)	< 0.001
Hemoptysis	3 (0.8)	1 (0.4)	2 (1.9)	0.202
Wells score (%)				0.001
Low to intermediate	225 (71.6)	194 (76.7)	61 (59.2)
High	101 (28.4)	59 (23.3)	42 (40.8)
D-dimer \(\ge\) 500 ng/mL (%)	348 (97.8)	246 (97.2)	102 (99.0)	0.447
DVT, deep vein thrombosis; PE, pulmonary embolism; VTE, venous embolism

Demographics were evaluated on the internal validation set and on the external validation set (Table 2). Patients of hospital B were older than patients of hospital A (65.6 ± 12.6 vs. 69.4 ± 10.9, P = 0.021). There were differences in the types of cancer among hospitals. Patients of hospital B had a higher incidence of pancreatic cancer (20.0% vs. 29.5%) and cholangiocarcinoma (6.7% vs. 12.2%), while colon cancer (22.2% vs. 16.5%) and hepatocellular carcinoma (27.8% vs. 12.2%) exhibited lower prevalence in hospital B. Patients of hospital A had higher C-PTP than hospital B (35.6% vs. 15.8%, P < 0.001). Patients suspected with DVT (36.7% vs. 13.7%, P < 0.001) and history of VTE (13.3% vs. 1.4%, P < 0.001) were higher in patients of hospital A.

Table 2

Baseline characteristics for internal and external validation datasets
	All patients	Hospital A	Hospital B
	(n = 229)	(n = 90)	(n = 139)	P value
Age (mean)	67.9\(\pm\)11.7	65.6\(\pm\)12.6	69.4\(\pm\)10.9	0.021
Male (%)	143 (62.4)	63 (70.0)	80 (57.6)	0.078
PE (%)	72 (31.4)	31 (34.4)	41 (29.5)	0.521
Cancer (%)				0.018
Gastric cancer	48 (21.0)	18 (20.0)	30 (21.6)
Colon cancer	43 (18.8)	20 (22.2)	23 (16.5)
Hepatocellular carcinoma	42 (18.3)	25 (27.8)	17.(12.2)
Pancreatic cancer	59 (25.8)	18 (20.0)	41 (29.5)
Cholangiocarcinoma	23 (10.0)	6 (6.7)	17 (12.2)
Others	14 (6.1)	3 (3.3)	11 (7.9)
Components of Wells score (%)
Signs and symptoms of DVT	52 (22.7)	33 (36.7)	19 (13.7)	< 0.001
Alternative diagnosis less likely than PE	99 (43.2)	46 (51.1)	53 (38.1)	0.072
Heart rate > 100/min	120 (52.4)	47 (52.2)	73 (52.5)	1.000
Immobilization	79 (34.5)	35 (38.9)	44 (31.7)	0.326
History of VTE	14 (6.1)	12 (13.3)	2 (1.4)	0.001
Hemoptysis	2 (0.9)	2 (2.2)	0 (0)	0.153
Wells score (%)				0.001
Low to intermediate	175 (76.4)	58 (64.4)	117 (84.2)
High	54 (23.6)	32 (35.6)	22 (15.8)
D-dimer \(\ge\) 500 ng/mL (%)	228 (99.6)	89 (98.9)	139 (100.0)	0.393
DVT, deep vein thrombosis; PE, pulmonary embolism; VTE, venous embolism

Primary study outcomes

We have trained the data using several machine learning models. Among them, we employed the random forest model with the highest AUROC (Supplemental Table 1). The performance of ML model was summarized in Table 3 and Fig. 2. AUROC and accuracy of the ML model during internal validation were 0.736 and 0.433, respectively. In external validation, AUROC and accuracy of the ML model were 0.669 and 0.345, respectively. We validated this model at an operating point with high sensitivity (1.000) for use as screening tool, and external validation showed a sensitivity of 0.976.

Table 3

Performance of machine learning model for predicting PE
	Hospital A	Hospital B
Features	WC + D-dimer	WC + D-dimer
AUROC	0.736	0.669
Accuracy	0.433	0.345
Sensitivity	1.000	0.976
NPV	1.000	0.889
Specificity	0.136	0.082
PPV	0.378	0.308
PE, pulmonary embolism; WC, components of Wells score; AUROC, area under reciever operating curve; NPV, negative predictive value; PPV, positive predictive value

Secondary study outcomes

Figure 3 shows the feature importance of the ML model. D-dimer emerged as the most important variable in predicting PE, followed by Suspect DVT.

Figure 4 indicates that the number of patients classified as requiring CTPA during the diagnosis of PE was significantly reduced after applying ML model in hospital A (100.0% vs. 91.1%, P < 0.001) and hospital B (100.0% vs. 93.5%, P = 0.003).

In gastrointestinal cancer patients, PE is one of the most critical complications that necessitates early diagnosis and treatment. However, the current diagnostic strategy for PE exhibited the unsatisfactory performance in ruling out PE, leading to unnecessary CT scans in cancer patients. This study showed that the ML model enhances the performance of ruling out PE and reduces the unnecessary CTPA scans.

Several studies have reported that ML model can enhance diagnostic strategies for pulmonary embolism. One study demonstrated that the neural network model utilizing raw structured electronic medical record(EMR) data can predict the risk of PE¹⁴. They developed a predictive model specifically for moderate to high C-PTP patients. Willian et al. showed that ML model can better exclude deep vein thrombosis compared to existing risk assessment scores¹⁵. Humberto et al. reported that ML model outperformed traditional risk scores such as Wells score combined with D-dimer, revised Geneva score, the pulmonary embolism rule-out criteria score (PERC)²⁶. This study is distinct from previous studies because we investigated patients with gastrointestinal cancer.

Among patients diagnosed with cancer in South Korea in 2018, gastric cancer and colorectal cancer were the most common, with gastrointestinal cancer accounting for 36% of all cancer cases²⁷. Based on this study, the ML model has the potential to reduce unnecessary CTPA scans in thousands of gastrointestinal cancer patients per year in South Korea. Considering that a CTPA scan costs approximately 400 US dollars in South Korea, this could result in significant cost savings in healthcare expenses. Additionally, it can also decrease the medical burden by reducing complications associated with contrast media, such as nephropathy and anaphylaxis.

In this study, pancreatic cancer was the most common type of cancer in patients with PE. Previous studies reported that pancreatic cancer carries the highest risk of VTE among all cancer types^{7, 28}. Signs and symptoms of DVT, history of VTE are factors known to be associated with PE, as indicated in previous studies^{10, 19, 29}. While immobilization is a strong risk factor for PE¹⁹, there was no significant difference in immobilization according to PE in this study. This could be attributed to the fact that this study focused on cancer patients. Cancer itself is a risk factor for PE¹⁹, and it can also influence the performance status of patients.

Many studies have attempted to improve diagnostic rate by altering the cut-off value of D-dimer. One study enhanced the diagnostic rate by adjusting the D-dimer cutoff value based on age³⁰. Another study ruled out more patients suspected of having PE by raising the D-dimer cut-off value to 1000 ng per milliliter in the low probability group according to the Wells score¹². Based on these results, modifying the cut-off value of the D-dimer test have the potential to enhance the diagnostic rate for PE, particularly in cancer patients who exhibit elevated D-dimer levels. In this study, we did not employ the previously established D-dimer cutoff value; instead, we allowed the ML model to adjust the cutoff values based on other variables. As a result, the ML model reduced the number of CTPA scans required. D-dimer was also shown to be an important factor in feature importance.

This study has several limitations. First, being a retrospective study, it may potentially entail unexpected bias. Since our analysis focused on patients who had undergone CTPA scans, there could be inherent selective bias in the sample. Second, AUROC of the ML model are relatively lower when compared to other studies^{14, 30}. This discrepancy arises from the fact that the subjects of this study were cancer patients, who typically exhibit higher D-dimer levels than non-cancer patients¹⁶. We employed ML to address these D-dimer-related limitations. However, as most artificial intelligence, including ML, operates as a black-box model, the precise cutoff value for D-dimer within the ML model remains unknown. Nevertheless, we underscored the significance of D-dimer using feature importance, an explainable artificial intelligence technique. Third, the study’s sample size is relatively small. PE is a relatively rare disease, with an annual incidence of approximately 0.1%²³. Nevertheless, previous studies have successfully developed ML models with robust performance despite the smaller sample sizes^{31, 32}. Fourth, we compared the ML model with the Wells score combined with D-dimer. However, aside from the Wells score, other assessment tools such as the revised Geneva score and PERC are also employed for pulmonary embolism risk assessment³³. Further research is warranted to make comparisons between these scoring systems with ML model.

Despite these limitations, this study has several strengths. To the best of our knowledge, this study is the first to develop the ML model to predict PE in gastrointestinal cancer patients. We applied ML to the simplified model that has already been demonstrated. So it is more easily accessible in the emergent department. And since the weight of each variable in the Wells score and the cut-off value of D-dimer are adjusted in the ML model, the limitations of the existing diagnostic system can be overcome. Therefore, a large prospective study in the future would be warranted to verify these results.

In conclusion, this ML model for predicting PE might improve diagnostic strategies for PE and reduce the number of unnecessary CTPA during the diagnostic process of PE in gastrointestinal cancer patients.

Data availability

The anonymized datasets generated and analyzed during the current study are available from the corresponding author upon reasonable request.

Competing interests

The authors declare that they have no competing interests.

Funding

This study was supported by Seoul National University Hospital Research Fund (Grant Number 0420212090).

Authors’ contributions

J.S.K., S.H.L. and S-B.L. devised and designed the study. D.K., M.W.L., N.P., J.H.C. and E.S.J. collected data and analyzed data. J.S.K., D.K. and K.K. wrote the manuscript. K.K., E.S.J., I.R.C., W.H.P, J.K.L., J.K.R. and Y-T.K. edited the manuscript. S.H.L. takes full responsibility for the study. All authors have read and approved the manuscript.

Acknowledgment

Not applicable

Blom JW, et al. Incidence of venous thrombosis in a large cohort of 66,329 cancer patients: results of a record linkage study. Journal of thrombosis and haemostasis: JTH. 2006.4,529 – 35.
Gross CP, Galusha DH, Krumholz HM. The impact of venous embolism on risk of death or hemorrhage in older cancer patients. Journal of general internal medicine. 2007.22,321–6.
Sørensen HT, Mellemkjaer L, Olsen JH, Baron JA. Prognosis of cancers associated with venous embolism. The New England journal of medicine. 2000.343,1846–50.
Kim JS, et al. Clinical Significance of Venous Embolism in Patients with Advanced Cholangiocarcinoma. Gut and liver. 2023.
Ohashi Y, et al. Venous embolism in cancer patients: report of baseline data from the multicentre, prospective Cancer-VTE Registry. Japanese journal of clinical oncology. 2020.50,1246–53.
Mulder FI, et al. Venous embolism in cancer patients: a population-based cohort study. Blood. 2021.137,1959-69.
Cohen AT, Katholing A, Rietbrock S, Bamber L, Martinez C. Epidemiology of first and recurrent venous embolism in patients with active cancer. A population-based cohort study. Thrombosis and haemostasis. 2017.117,57–65.
Mukai M, Oka T. Mechanism and management of cancer-associated thrombosis. J Cardiol. 2018.72,89–93.
van Es N, et al. Wells Rule and d-Dimer Testing to Rule Out Pulmonary Embolism: A Systematic Review and Individual-Patient Data Meta-analysis. Annals of internal medicine. 2016.165,253 – 61.
Konstantinides SV, et al. 2019 ESC Guidelines for the diagnosis and management of acute pulmonary embolism developed in collaboration with the European Respiratory Society (ERS): The Task Force for the diagnosis and management of acute pulmonary embolism of the European Society of Cardiology (ESC). The European respiratory journal. 2019.54.
Hendriksen JM, et al. Diagnostic prediction models for suspected pulmonary embolism: systematic review and independent external validation in primary care. BMJ (Clinical research ed). 2015.351,h4438.
Kearon C, et al. Diagnosis of Pulmonary Embolism with d-Dimer Adjusted to Clinical Probability. The New England journal of medicine. 2019.381,2125–34.
Takach Lapner S, Julian JA, Linkins LA, Bates S, Kearon C. Comparison of clinical probability-adjusted D-dimer and age-adjusted D-dimer interpretation to exclude venous embolism. Thrombosis and haemostasis. 2017.117,1937-43.
Banerjee I, et al. Development and Performance of the Pulmonary Embolism Result Forecast Model (PERFORM) for Computed Tomography Clinical Decision Support. JAMA network open. 2019.2,e198719.
Willan J, Katz H, Keeling D. The use of artificial neural network analysis can improve the risk-stratification of patients presenting with suspected deep vein thrombosis. British journal of haematology. 2019.185,289 – 96.
Crawford F, et al. D-dimer test for excluding the diagnosis of pulmonary embolism. The Cochrane database of systematic reviews. 2016.2016,Cd010864.
Bruix J, Sherman M. Management of hepatocellular carcinoma: an update. Hepatology (Baltimore, Md). 2011.53,1020–2.
Lee K, et al. Oral health and gastrointestinal cancer: A nationwide cohort study. Journal of clinical periodontology. 2020.47,796–808.
Di Nisio M, van Es N, Büller HR. Deep vein thrombosis and pulmonary embolism. Lancet (London, England). 2016.388,3060–73.
Kline JA, et al. Prospective multicenter evaluation of the pulmonary embolism rule-out criteria. Journal of thrombosis and haemostasis: JTH. 2008.6,772 – 80.
Pourghasemi HR, et al. Spatial modeling, risk mapping, change detection, and outbreak trend analysis of coronavirus (COVID-19) in Iran (days between February 19 and June 14, 2020). International Journal of Infectious Diseases. 2020.98,90–108.
Kaur P, Kumar R, Kumar M. A healthcare monitoring system using random forest and internet of things (IoT). Multimedia Tools and Applications. 2019.78,19905–16.
Keller K, et al. Trends in thrombolytic treatment and outcomes of acute pulmonary embolism in Germany. European heart journal. 2020.41,522–9.
Lundberg SM, Lee S-IJAinips. A unified approach to interpreting model predictions. 2017.30.
Nembrini S, König IR, Wright MN. The revival of the Gini importance? Bioinformatics (Oxford, England). 2018.34,3711–8.
Villacorta H, et al. Machine learning with D-dimer in the risk stratification for pulmonary embolism: a derivation and internal validation study. European heart journal Acute cardiovascular care. 2022.11,13 – 9.
Korea Central Cancer Registry NCC. Annual report of cancer statistics in Korea in 2018. Ministry of Health and Welfare. 2020.
Frere C, et al. Incidence of Venous Embolism in Patients With Newly Diagnosed Pancreatic Cancer and Factors Associated With Outcomes. Gastroenterology. 2020.158,1346-58.e4.
Wells PS, et al. Derivation of a simple clinical model to categorize patients probability of pulmonary embolism: increasing the models utility with the SimpliRED D-dimer. Thrombosis and haemostasis. 2000.83,416 – 20.
Nagel SN, Steffen IG, Schwartz S, Hamm B, Elgeti T. Age-dependent diagnostic accuracy of clinical scoring systems and D-dimer levels in the diagnosis of pulmonary embolism with computed tomography pulmonary angiography (CTPA). European radiology. 2019.29,4563–71.
Lu Z, et al. Prediction of immune checkpoint inhibition with immune oncology-related gene expression in gastrointestinal cancer using a machine learning classifier. Journal for immunotherapy of cancer. 2020.8.
Yokoyama S, et al. Predicted Prognosis of Patients with Pancreatic Cancer by Machine Learning. Clinical cancer research: an official journal of the American Association for Cancer Research. 2020.26,2411–21.
Freund Y, Cohen-Aubart F, Bloom B. Acute Pulmonary Embolism: A Review. Jama. 2022.328,1336–45.

No competing interests reported.

SupplementalTable1.docx

Download PDF

Journal Publication

published 25 Oct, 2024

Read the published version in Scientific Reports →

Editorial decision: Revision requested
11 May, 2024
Reviews received at journal
30 Apr, 2024
Reviewers agreed at journal
19 Apr, 2024
Reviews received at journal
17 Apr, 2024
Reviewers agreed at journal
17 Apr, 2024
Reviews received at journal
23 Mar, 2024
Reviewers agreed at journal
13 Mar, 2024
Reviewers agreed at journal
13 Mar, 2024
Reviewers invited by journal
13 Mar, 2024
Editor assigned by journal
13 Mar, 2024
Editor invited by journal
13 Mar, 2024
Submission checks completed at journal
13 Mar, 2024
First submitted to journal
25 Feb, 2024

You are reading this latest preprint version

Machine Learning-Based Prediction of Pulmonary Embolism to Reduce Unnecessary Computed Tomography Scans in Gastrointestinal Cancer Patients: A Retrospective Multicenter Study

Status:

Journal Publication

Version 1

Abstract

Background

Methods

Results

Conclusion

Figures

Introduction

Methods

Study design and patients

Data collection and definition

Study outcome measures

Statistical analysis

Results

Baseline characteristics of the study population

Primary study outcomes

Secondary study outcomes

Discussion

Declarations

References

Additional Declarations

Supplementary Files

Status:

Journal Publication

Version 1