Lung cancer in the emergency department

Investigating socioeconomic disparities in lung cancer diagnosis, treatment and mortality: an Italian cohort study

BACKGROUND

Lung cancer is one of the most lethal cancers worldwide and patient clinical outcomes seem influenced by their socioeconomic position (SEP). Since little has been investigated on this topic in the Italian context, our aim was to investigate the role of SEP in the care pathway of lung cancer patients in terms of diagnosis, treatment and mortality.

METHODS

This observational retrospective cohort study included patients discharged in the Lazio Region with a lung cancer diagnosis between 2014 and 2017. In the main analysis, educational level was used as SEP measure. Multivariate models, adjusted for demographic and clinical variables, were applied to evaluate the association between SEP and study outcomes, stratified for metastatic (M) and non-metastatic (NM) cancer. We defined a diagnosis as 'delayed' when patients received their initial cancer diagnosis after an emergency department admission. Access to advanced lung cancer treatments (high-cost, novel and innovative treatments) and mortality were investigated within the 24-month period post-diagnosis. Moreover, two additional indicators of SEP were examined in the sensitivity analysis: one focusing on area deprivation and the other on income-based exemption.

RESULTS

A total of 13,251 patients were identified (37.3% with metastasis). The majority were males (> 60%) and over half were older than 70 years. The distribution of SEP levels among patients was as follow: 31% low, 29% medium-low, 32% medium-high and 7% high. As SEP increased, the risks of receiving a delayed diagnosis ((high vs low: M: OR = 0.29 (0.23-0.38), NM: OR = 0.20 (0.16-0.25)) and of mortality ((high vs low M: OR = 0.77 (0.68-0.88) and NM: 0.61 (0.54-0.69)) decreased. Access to advanced lung cancer treatments increased in accordance with SEP only in the M cohort (high vs low: M: OR = 1.57 (1.18-2.09)). The primary findings were corroborated by sensitivity analysis.

CONCLUSIONS

Our study highlighted the need of public health preventive and educational programs in Italy, a country where the care pathway of lung cancer patients, especially in terms of diagnosis and mortality, appears to be negatively affected by SEP level.

Risk Prediction of Emergency Department Visits in Patients With Lung Cancer Using Machine Learning: Retrospective Observational Study

BACKGROUND

Patients with lung cancer are among the most frequent visitors to emergency departments due to cancer-related problems, and the prognosis for those who seek emergency care is dismal. Given that patients with lung cancer frequently visit health care facilities for treatment or follow-up, the ability to predict emergency department visits based on clinical information gleaned from their routine visits would enhance hospital resource utilization and patient outcomes.

OBJECTIVE

This study proposed a machine learning-based prediction model to identify risk factors for emergency department visits by patients with lung cancer.

METHODS

This was a retrospective observational study of patients with lung cancer diagnosed at Seoul National University Bundang Hospital, a tertiary general hospital in South Korea, between January 2010 and December 2017. The primary outcome was an emergency department visit within 30 days of an outpatient visit. This study developed a machine learning-based prediction model using a common data model. In addition, the importance of features that influenced the decision-making of the model output was analyzed to identify significant clinical factors.

RESULTS

The model with the best performance demonstrated an area under the receiver operating characteristic curve of 0.73 in its ability to predict the attendance of patients with lung cancer in emergency departments. The frequency of recent visits to the emergency department and several laboratory test results that are typically collected during cancer treatment follow-up visits were revealed as influencing factors for the model output.

CONCLUSIONS

This study developed a machine learning-based risk prediction model using a common data model and identified influencing factors for emergency department visits by patients with lung cancer. The predictive model contributes to the efficiency of resource utilization and health care service quality by facilitating the identification and early intervention of high-risk patients. This study demonstrated the possibility of collaborative research among different institutions using the common data model for precision medicine in lung cancer.

Time intervals and previous primary care consultations in the pathway to emergency cancer diagnosis

BACKGROUND

Time intervals and number of prior consultations in primary care (PC) are recognised metrics of diagnostic timeliness of cancer and are interrelated. However, whether and how the two measures correlate with each other in the emergency diagnostic pathway is unknown. We investigated the association between the number of prereferral consultations and the length of intervals from PC presentation to cancer diagnosis following emergency referral to hospital.

METHODS

Patients were eligible if they first consulted in PC and were diagnosed with cancer following emergency or nonemergency referral to hospital. We analysed for differences in PC and diagnostic intervals and number of consultations between emergency and nonemergency presenters and determined their associations by cancer type. Differences in presenting symptoms and stage at diagnosis between populations and according to number of consultations were also examined.

RESULTS

There were 796 emergency and 865 nonemergency presenters with comparable sociodemographic and comorbidity data. Correlation analysis in emergency presenters revealed a strong positive association between number of consultations and intervals for seven of 13 different cancers, including cancers characterised by high proportions of > 3 consultations and long intervals (pancreatic, lung, and colorectal cancer) and vice versa for others (e.g., endometrial, cervical, or oesophageal cancer). Additionally, emergency presenters with > 3 consultations were more likely than those with 1-2 to report nonspecific symptoms (60 vs. 40%, respectively) and to be diagnosed at a later stage.

CONCLUSION

System level interventions are needed to reduce unnecessary delays in the emergency diagnostic pathway, particularly in cancer patients with multiple prereferral consultations. The findings also suggest opportunities to reduce the proportion of emergency diagnoses by targeting symptomatic individuals pre-presentation.