Importance:Rapid digitalization of health care and a dearth of digital health education for medical students and junior physicians worldwide means there is an imperative for more training in this dynamic and evolving field. Objective:To develop an evidence-informed, consensus-guided, adaptable digital health competencies framework for the design and development of digital health curricula in medical institutions globally. Evidence Review:A core group was assembled to oversee the development of the Digital Health Competencies in Medical Education (DECODE) framework. First, an initial list was created based on findings from a scoping review and expert consultations. A multidisciplinary and geographically diverse panel of 211 experts from 79 countries and territories was convened for a 2-round, modified Delphi survey conducted between December 2022 and July 2023, with an a priori consensus level of 70%. The framework structure, wordings, and learning outcomes with marginal percentage of agreement were discussed and determined in a consensus meeting organized on September 8, 2023, and subsequent postmeeting qualitative feedback. In total, 211 experts participated in round 1, 149 participated in round 2, 12 participated in the consensus meeting, and 58 participated in postmeeting feedback. Findings:The DECODE framework uses 3 main terminologies: domain, competency, and learning outcome. Competencies were grouped into 4 domains: professionalism in digital health, patient and population digital health, health information systems, and health data science. Each competency is accompanied by a set of learning outcomes that are either mandatory or discretionary. The final framework comprises 4 domains, 19 competencies, and 33 mandatory and 145 discretionary learning outcomes, with descriptions for each domain and competency. Six highlighted areas of considerations for medical educators are the variations in nomenclature, the distinctiveness of digital health, the concept of digital health literacy, curriculum space and implementation, the inclusion of discretionary learning outcomes, and socioeconomic inequities in digital health education. Conclusions and Relevance:This evidence-informed and consensus-guided framework will play an important role in enabling medical institutions to better prepare future physicians for the ongoing digital transformation in health care. Medical schools are encouraged to adopt and adapt this framework to align with their needs, resources, and circumstances.

KDD AIDSH 2024 aims to foster discussions and developments that push the boundaries of Artificial Intelligence (AI) and Data Science (DS) in healthcare, enhance diagnostic accuracy and promote human-centric approaches to healthcare, thus stimulating future interdisciplinary collaborations. This year's symposium will focus on expanding the application of AI/DS in healthcare/medicine and bridging existing gaps. The workshop invites submissions of full papers as well as work-in-progress on the application of AI/DS in healthcare. The workshop will feature three invited talks from eminent speakers, spanning academia, industry, and clinical researchers. In addition, selected papers will be invited to publish in Health Data Science, a Science Partner Journal. This summary provides a brief description of the half-day workshop to be held on August 26th, 2024. The webpage for the workshop can be found at https://aimel.ai/kdd2024aidsh.

Objective: To understand the status of autism spectrum disorder (ASD) cohort studies and explore the feasibility of constructing ASD disease-specific cohorts based on real-world data (RWD). Methods: ASD cohort studies published by December 2022 were collected by literature retrieval from major Chinese and English databases. And the characteristics of the cohort were summarized. Results: A total of 1 702 ASD cohort studies were included, and only 60 (3.53%) were from China. A total of 163 ASD-related cohorts were screened, of which 55.83% were birth cohorts, 28.22% were ASD-specific cohorts, and 4.91% were ASD high-risk cohorts. Most cohorts used RWD such as hospital registries or conducted community-based field surveys to obtain participant information and identified patients with ASD by scales or clinical diagnoses. The contents of the studies included ASD incidence and prognostic risk factors, ASD comorbidity patterns and the impact of ASD on self-health and their offspring's health. Conclusions: ASD cohort studies in developed countries have been in the advanced stage, while the Chinese studies are still in their infancy. RWD provides the data basis for ASD-specific cohort construction and offers new opportunities for research, but work such as case validation is still needed to ensure the scientific nature of cohort construction.

To the Editor: Thymic malignancies refer to a group of malignant tumors that originated from the thymic gland, including thymoma, thymic carcinoma, thymic carcinoid, and malignancies from other uncommon histological origins. As a set of rare diseases, only a limited number of studies have reported incidences of malignancies in thymus. The estimated incidence of thymoma was 0.13–0.15 per 100,000 person-years, and the incidence of all thymic malignancies was 0.28–0.30 per 100,000 person-years in the United States.[1] The incidence of thymic epithelial tumors (thymoma and thymic carcinoma) was 0.32 per 100,000 person-years in the Netherlands.[2] A very recent study reported that the incidence of thymic carcinoma in Japan was 0.29 per 100,000.[3] A trend of an increase in thymic cancers over time has also been observed in these studies. Notably, based on a limited number of cases within the databases from the United States population, it has also been suggested that the incidence may be higher in Asian/Pacific Islanders.[1,4] In comparison, a subtly elevated incidence could be observed in the study from Japan. However, the incidence of thymic malignancies from other Asian countries, including China, is largely unknown. The Chinese Commercial Critical Illness Insurance (CCCII) database is constituted of all critical illness insurance claims from six top commercial insurance companies with a market share >80% in 2007.[5] [Supplementary Material and Table 1, https://links.lww.com/CM9/B164]. Here, we used the CCCII database and conducted a population-based, longitudinal study to estimate the incidence of thymic malignancies. We also described the demographic patterns of the disease in China. In the de-identified database, claims information was recorded between the date of the policy being issued to the date of the reimbursement or of that exceeding the validity period. Claim reimbursement was triggered by the diagnosis of the first critical illness listed in the corresponding policy. All diagnoses had been validated through chart review and were recorded as text records in the database. The CCCII database only included claims in adults (aged ≥18 years). The criteria for the approval of a cancer diagnosis in the chart review includes, (1) the diagnosis should be confirmed by the pathological examination, and (2) the clinical diagnosis codes should belong to the category of malignant tumor of the International Classification of Diseases-10th (ICD-10) of the World Health Organization. For thymic malignancies, the ICD-10 code of the clinical diagnosis should indicate the primary cancer site as thymus. After chart review, all cancers identified with a thymus origin were recorded as “thymic malignancies” in the database. We extracted thymic malignancies cases with variables including sex, age, year of diagnosis, city tier of residence (megacities, cities, and rural areas), and province. We further grouped cases according to their geographic regions (East, Middle, North, Northeast, Northwest, South, and Southwest). The study cohort was the insurants who were recorded in 2007 in the CCCII database. Incidence rates were calculated with the number of claims as the numerator and the cumulative follow-up person-years as the denominator in each year from 2007 to 2016. All incidence rates other than age-specific incidence rates were standardized to World Health Organization standard population, and were expressed as per 100,000 person-years at risk. Sex, age, region, and residence were used for subset analysis in this study.[6] Trends in age-standardized incidence rates from 2007 to 2016 were examined by fitting the joinpoint model using the Joinpoint Trend Analysis Software. The software was developed by the US National Cancer Institute. The annual percent change (APC) in rates and the average annual percent change were quantified, and the Monte Carlo permutation method was used to test if a difference exists from the null hypothesis of no change (0%); a P value of <0.05 was considered as statistically significant. The SAS software (version 9.4, SAS Institute Inc., Cary, NC, USA) and Joinpoint software (version 4, 6.0.0, National Cancer Institute, USA) were used in the study. This study was approved by the institutional review board of ethics committee of the Peking University First Hospital (Ethical approval number: 2019-020). Thirty-one million person-years of insurant were recorded in the database in 2007. Between 2007 and 2016, there were 1373 cases diagnosed with thymic malignancies [Table 1]. The average crude incidence rate of thymic malignancies was 0.42 per 100,000 person-years. After age-standardization, the incidence rate was 0.40 per 100,000 person-years. The age-standardized incidence of thymic malignancies was higher in men than in women (0.50 vs. 0.33 per 100,000 person-years). The age-specific incidence continually increased with age and peaked at 0.93 per 100,000 person-years in the age group ≥60 years [Table 1]. Table 1 - Incidence rates of thymic malignancies in China from 2007 to 2016. Variable Cases Source population (×100,000 person-years) Crude incidence rate (per 100,000 person-years) (95% CI) ASR (per 100,000 person-years) (95% CI) Overall 1373 3278.63 0.42 (0.40–0.44) 0.40 (0.37–0.43) By sex Male 734 1536.94 0.48 (0.44–0.51) 0.50 (0.45–0.55) Female 639 1741.69 0.37 (0.34–0.40) 0.33 (0.29–0.36) By age (years) 18–29 36 393.01 0.09 (0.07–0.13) – 30–39 128 720.36 0.18 (0.15–0.21) – 40–49 473 1192.00 0.40 (0.36–0.43) – 50–59 560 784.00 0.71 (0.66–0.78) – ≥60 176 189.27 0.93 (0.80–1.08) – By residence∗ , ‡ Megacities 379 782.91 0.48 (0.44–0.54) 0.49 (0.43–0.56) Cities 713 1601.27 0.45 (0.41–0.48) 0.43 (0.38–0.47) Rural areas 279 884.31 0.32 (0.28–0.35) 0.29 (0.24–0.33) By geographic location† , ‡ Northeast 211 406.17 0.52 (0.45–0.59) 0.54 (0.44–0.65) North 235 503.67 0.47 (0.41–0.53) 0.49 (0.40–0.58) East 522 1095.56 0.48 (0.44–0.52) 0.48 (0.42–0.53) South 85 209.21 0.41 (0.33–0.50) 0.38 (0.28–0.47) Middle 171 484.21 0.35 (0.30–0.41) 0.28 (0.23–0.33) Northwest 77 277.14 0.28 (0.22–0.35) 0.27 (0.20–0.35) Southwest 70 292.53 0.24 (0.19–0.30) 0.24 (0.17–0.30) Data are presented as N or n (95%CI). ASR: Age-standardized incidence rate. CCCII: Chinese Commercial Critical Illness Insurance.CI: Confidence interval.∗The city tiers were predefined in the CCCII database with a reference to the Mckinsey ClusterMap (McKinsey Consumer and Shopper Insights: 2010 Annual Chinese Consumer Study) and represented the economic status and city size of a resident location.†The cases were grouped into seven geographic locations based on the national administrative regions.‡The two cases without information on residence and geographic location were not included in the analysis. Compared to those living in rural areas, the age-standardized incidence rates were higher in more urbanized areas (0.49 per 100,000 person-years in megacities, 0.43 per 100,000 person-years in cities vs. 0.29 per 100,000 person-years in rural areas). Among all the geographic locations, the highest incidence was observed in Northeast China (0.54 per 100,000 person-years), and the lowest was in Southwest China (0.24 per 100,000 person-years). Overall, the Northern and Eastern parts of China have a higher incidence of the disease than the Southern and Western parts [Table 1]. Overall, an upward trend was observed in the age-standardized incidence of thymic malignancies, with an APC of 4.1% (P < 0.05) from 2007 to 2016 [Supplementary Figure 1, https://links.lww.com/CM9/B164; Supplementary Table 2, https://links.lww.com/CM9/B164]. For men, the incidence declined from 2007 to 2009, and then elevated with an APC of 8.1% (P < 0.05) between 2009 and 2016. However, for women, it did not change between 2007 and 2016, with an APC of 3.7% (P > 0.05). Based on a national commercial insurance claims database over a decade, we reported the incidence of thymic malignancies to be 0.40 per 100,000 in China, with an increasing trend and geographic variations. To the best of our knowledge, our study is the first epidemiological study of thymic malignancies in China and expanded upon previous evidence mainly from the developed countries. Furthermore, the present study indicated that commercial claims database with a large enough sample size could be a valuable resource to investigate rare cancer. The incidence of thymic malignancies in China is considerably higher than that reported in the Western counties.[1,2,4] Using the data from the Surveillance, Epidemiology, and End Results database, Engels et al[4] showed that the overall incidence of thymoma is 0.13–0.15 per 100,000 person-years in the United States. Of note, these studies included only pathologically proved invasive (“malignant”) thymomas. Although, with no further information on histological types, the CCCII database used in our study included all primary malignancies in the thymus. In a recent study, Hsu et al[1] analyzed data from the United States Cancer Statistics (USCS) database and found that the incidence for thymic cancers with all histologic types was 0.30 per 100,000 person-years in 2015 in the United States. With a similar disease spectrum to Hsu et al's,[1] the elevated incidence of thymic malignancies found in our study may be attributed to many factors. First, it has been suggested that genetic risk factors may play a role in thymic cancers. Engels found a higher incidence of thymoma in Asian/Pacific Islanders compared with Whites and Hispanics.[4] Similar findings also were observed in Hsu et al's[1] study. Consistent with the prior studies, we found an elevated incidence of thymic malignancies in the Chinese population over a similar study period. Genetic polymorphism might lead to the predisposition to thymic malignancies, but further designed studies with more specific endpoints are necessary to evaluate the hypothesis. Alternatively, the elevated incidence in China might be attributable to other risk factors. It has been suggested that modifiable risk factors could explain 60% of cancer deaths in China.[7] An extremely high incidence of certain cancers was observed in high risk areas. In our study, we observed a difference in the incidence rates by geographic regions, with the highest in Northeast China, followed by North and East China. The incidence of thymic malignancies increased over the study period. In contrast to the consistent increasing trend in women, the incidence rates in men had a decline from 2006 to 2009 (APC −23.6, 95% CI −56.7 to 34.8), before the steady increase since 2009 (APC 8.1, 95% CI 3.3–13.2). However, the underlying reason is unknown. The overall increasing trend could, in part, reflect an effect of the increased prevalence of CT scanning and the advancement of the diagnosis.[1] The unequal distribution of health resources might further explain the relatively low incidence rate of thymic malignancies in rural residents found in our study. Further studies are necessary to examine these associations. Our study has the advantage of a national sample size with long term follow-up. Furthermore, the possibilities of both false negative and false positive are relatively low, due to the insurant's motivation to being reimbursed and the strict case verifying procedure of commercial insurance companies. Meanwhile, our study has limitations. First, the commercial health insurance database had a selection bias. Due to the insurance policy's age cap, the elderly population in the study cohort was relatively small in proportion, which might lead to an underestimation of the disease. Also, detailed information on pathology, treatments, comorbidities, and prognosis was not available, limiting potential further analyses. Third, only the first diagnosis of the predetermined critical illnesses was recorded, which might cause missing cases of the thymic malignancies if diagnosed subsequently. Furthermore, the fast implementation of advanced imagining machines in China might lead to a detection bias in the disease's increasing trend. In summary, the incidence of thymic malignancies appears to be higher in China than those in Western countries, with an increasing trend over time. There also are differences in the incidence by the geographic regions. Our findings suggest the further need to understand the potential roles of genetic and modifiable risk factors in the disease. In addition, our study used a critical illness insurance database to give insight into the incidence and trends in thymic malignancies, which could be a feasible model in using commercial claims databases in rare disease epidemiologic studies. Funding This study was supported by grants from the National Natural Science Foundation of China (No. 72125009), Peking University (No. BMU2022XTZ005), Beijing advanced discipline construction project (No. BMU2019GJJXK001), and Project 2019BD017, 2020BD004, 2020BD005 supported by PKU-Baidu Fund. Conflicts of interest None.

1.Introduction Clinician-scientists have a unique strength in translational research and medical advances that improve the quality of care and patient outcomes.As big data analytics and advanced tech-nologies such as artificial intelligence are being continuously applied in the healthcare scenario,it not only transforms patient care but also creates tremendous opportunities for data-driven discoveries.In a digital health era,clinician-scientists proficient in data science knowledge——that is clinician data scientists——are central to harnessing the power of big data analytics and advanced technologies in medicine.