Breast cancer survival has steadily increased owing to screening programs and advancements in treatment. For example, in the United States, the 5-year survival rate increased from 85.5% in 1990 to 90.7% in 2013. On average, age-adjusted death rates have been falling by 1.4% each year, even after 2010 [1]. In Korea, the 5-year survival rate of breast cancer patients increased by 14% from 79.2% in 1993–1995 to 93.2% in 2013–2017 [2].

As the number of long-term cancer survivors increases and the quality of life of individuals with cancer becomes more important, the late effects of primary cancer treatment have become increasingly important. Excess cardiac and pulmonary morbidity associated with the use of radiation therapy (RT) in breast cancer has been extensively evaluated, and it has been clearly demonstrated that some of the benefits of RT diminish with respect to overall mortality [3, 4]. There is another concern regarding the potential for the development of hypothyroidism. Radiation damage to the thyroid gland can be less conspicuous, as hypothyroidism does not directly affect survival, such as in coronary artery disease or heart failure. Symptoms of hypothyroidism include fatigue, weight gain, myalgia, and depression. Untreated hypothyroidism can induce hypercholesterolemia, cognitive dysfunction, and impaired consciousness.

The European Organization for Research and Treatment of Cancer 22922/10925 and MA.20 study showed a significant reduction in mortality and recurrence of breast cancer by regional nodal irradiation in stage I–III disease [5, 6]. Based on these findings, the indication for regional nodal irradiation has expanded from patients with N2 disease to N1, resulting in an increase in the number of patients receiving RT to the supraclavicular area [7]. Studies have suggested an elevated risk of hypothyroidism in patients undergoing adjuvant breast RT, including in the supraclavicular region [8, 9]. However, only small-scale studies have been conducted, particularly in Asian women.

Therefore, the present study aimed to evaluate the patterns of hypothyroidism development among Korean patients undergoing breast cancer surgery. We sought to determine the risk of hypothyroidism in patients treated with and without radiation and the association of supraclavicular lymph node (SCL) RT with this risk. To the best of our knowledge, this is the first Korean population-based study.

Between 2007 and 2018, the HIRA database incorporated data from 939,775,946 claims from 305,058 patients diagnosed with breast cancer. Among them, 204,889 patients underwent breast surgery. Those with any thyroid disease diagnosis before surgery (n = 49,463) or multiple breast surgery codes (n = 38,291) were excluded, and 117,135 patients with breast cancer fulfilled the inclusion criteria (Fig 1).

The median follow-up time was 4.6 years (interquartile range, 2.1–7.6 years). Patient characteristics are listed in Table 1 for patients who received RT (n = 64,080) and those who did not (n = 53,055). The mean age at surgery was higher among patients not receiving RT (52.1 years) than among those receiving RT (50.5 years).

This study, derived from the HIRA database of the National Health Insurance Service in Korea, evaluated the incidence of hypothyroidism in patients who underwent adjuvant RT between 2007 and 2018. The incidence of hypothyroidism was higher in patients who received RT (HR = 1.081, 95% CI 1.013–1.134, p = 0.002).

In other countries, nationwide registry-based studies have been conducted to evaluate the risk of hypothyroidism in breast cancer survivors. The most recent publication was a Danish study, which included 44,574 breast cancer survivors and 203,306 matched controls. The risk of hypothyroidism was higher in breast cancer survivors than in controls (5-year cumulative incidence: 1.8% vs. 1.6%). Among the cancer treatments, RT to regional lymph nodes and chemotherapy showed the highest risks, with an HR of 1.74 (95% CI 1.50–2.02). In analyses restricted to the breast cancer cohort alone, nodal RT with or without chemotherapy was associated with an elevated risk of hypothyroidism compared to not receiving these therapies [12]. In a Canadian database study, changes in comorbidities before and after treatment were investigated in patients who received breast cancer treatment between 2005 and 2009, and this was compared with the matched cohort. The development of new comorbidities, such as ischemic heart disease, heart failure, depression, diabetes, osteoporosis, and hypothyroidism, was higher in women with breast cancer. The HR for hypothyroidism was 1.17 (95% CI 1.09–1.26) [13]. The long-term consequences of cancer treatment were assessed using a long-term British cancer survivor dataset. A total of 26,213 adults who survived for 5 years following breast, colorectal, or prostate cancer were matched with non-cancer controls. Breast cancer survivors had a marginally increased rate of hypothyroidism in multivariate models (HR, 1.26; 95% CI 1.02–1.56) [14]. Smith et al. specifically assessed this subject in the older population aged > 65 years from the Surveillance, Epidemiology, and End Results (SEER)Medicare cohort. The study included 38,255 patients with stage 0–3 breast cancer and 111,944 controls. The 1- and 5-year incidence rates of hypothyroidism were 4% and 14%, respectively. They compared the incidence of hypothyroidism among irradiated patients with 4+ positive lymph nodes (surrogate for supraclavicular RT) and no positive nodes (surrogate for no supraclavicular RT), non-irradiated patients, and controls. All patients, regardless of RT status, were more likely to be diagnosed with hypothyroidism than were cancer-free controls (hazard ratio [HR] = 1.21; 95% CI 1.17–1.25). However, supraclavicular irradiation did not appear to amplify risks, as the incidence of hypothyroidism did not increase in irradiated patients with 4+ LN versus 0 + LN (HR = 1.04; 95% CI 0.89–1.23) [9].

Our study provides one of the largest population-based data analyses regarding the long-term risk of hypothyroidism among Korean breast cancer patients, with an 8-year incidence in this patient population as high as 9%. Importantly, the adjusted risk for patients treated with RT exceeded that for those with breast cancer treated without RT (HR = 1.085, 95% CI 1.033–1.139, p = 0.001). In the subgroup analysis of patients who underwent mastectomy, the adjusted HR was 1.267 (95% CI, 0.991–1.620; p = 0.059). We confirmed that the cumulative incidence and relative effect estimates in Korean patients with breast cancer were similar to those observed in previous studies [9, 12–14].

The pathophysiology of hypothyroidism associated with breast cancer treatment has not yet been clearly established. Direct thyroid cell damage from radiation, as well as injury to small thyroid vessels and to the gland capsule, can cause RT-induced thyroid dysfunction. It has been suggested that late injury is mainly caused by vascular damage, whereas acute effects result from parenchymal cell damage [15]. There is also an explanation for the immune-mediated damage [16]. However, the contributions of other treatment modalities remain unclear. A few studies have evaluated the synergistic effects of chemotherapy, with conflicting results [12, 17, 18]. The possibility of an earlier diagnosis owing to frequent regular contact with healthcare services or symptoms of hormone therapies cannot be eliminated. As most clinical data are reported on populations treated for Hodgkin disease and head and neck cancer, the National Comprehensive Cancer Network guidelines recommend routine screening of thyroid-stimulating hormone levels, at least annually in these patients [19, 20]. In breast cancer, however, no guidelines exist on post-treatment thyroid function tests, including proper screening time [21]. Evidence indicates that antimicrosomal antibodies are elevated precociously after the end of local RT, and thyroid damage initially manifested within 6 months [16, 22]. Most reported that the events occurred within 5 years, with a median clinical latency of 8–27 months [23–27]. In our study, the effect of RT on cumulative incidence was evident immediately after treatment, and differences were observed for up to approximately 9 years. Notably, the incidence curve pattern was analogous to that of the Danish trial [12]. As symptoms are very nonspecific and are easily marked in cancer populations, it would be helpful to consider the possibility of RT-induced hypothyroidism in symptomatic patients and to consider laboratory tests for at least 5–8 years.

Intensity-modulated RT, as the most modern planning technique, usually minimizes incidental exposure to nontarget tissues and organs. However, IMRT may cause increased low-dose exposure to the thyroid gland, compared with 3D-CRT [28, 29]. The use of regional nodal irradiation, including IMRT, is expanding rapidly. Further experimental and clinical studies are required to determine the appropriate dose constraints for the thyroid gland.

In the general population, the prevalence of hypothyroidism increases with age [30]. In contrast, in the case of thyroid disorders after radiation with or without chemotherapy, susceptibility has been reported to be higher in younger patients [8, 31]. One possible hypothesis is that the upper limit of the SCL field is higher among younger women. Second, intense chemotherapy is often administered more frequently in younger patients.

Limitations of the current study include misclassification of the outcome of hypothyroidism, as it was based on diagnostic codes and did not reflect TSH elevation or levothyroxine prescription. Second, owing to data characteristics, analysis relating to the radiation dose or field, which is critical in radiation toxicity, was not performed. Third, it is possible that some patients with unclear mastectomy types were completely omitted from the subgroup analysis. Fourth, it is possible that hypothyroidism, which occurred during the interval between surgery and RT, was misclassified as an RT-induced disease, leading to immortal time bias. Fifth, some of the included patients might have undergone thyroid surgery owing to increased healthcare interactions, leading to the diagnosis of thyroid nodules or other thyroid diseases.

In conclusion, the use of RT in patients with breast cancer was associated with an increased risk of hypothyroidism, which lasted for several years. The SCL-RT-confined subgroup analysis revealed similar results.