1
|
Tang Y, Wang CH, Mitra P, Pai TW. Noninvasive Risk Prediction Models for Heart Failure Using Proportional Jaccard Indices and Comorbidity Patterns. Rev Cardiovasc Med 2024; 25:179. [PMID: 39076472 PMCID: PMC11267177 DOI: 10.31083/j.rcm2505179] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2024] [Revised: 03/04/2024] [Accepted: 03/12/2024] [Indexed: 07/31/2024] Open
Abstract
Background In the post-coronavirus disease 2019 (COVID-19) era, remote diagnosis and precision preventive medicine have emerged as pivotal clinical medicine applications. This study aims to develop a digital health-monitoring tool that utilizes electronic medical records (EMRs) as the foundation for performing a non-random correlation analysis among different comorbidity patterns for heart failure (HF). Methods Novel similarity indices, including proportional Jaccard index (PJI), multiplication of the odds ratio proportional Jaccard index (OPJI), and alpha proportional Jaccard index (APJI), provide a fundamental framework for constructing machine learning models to predict the risk conditions associated with HF. Results Our models were constructed for different age groups and sexes and yielded accurate predictions of high-risk HF across demographics. The results indicated that the optimal prediction model achieved a notable accuracy of 82.1% and an area under the curve (AUC) of 0.878. Conclusions Our noninvasive HF risk prediction system is based on historical EMRs and provides a practical approach. The proposed indices provided simple and straightforward comparative indicators of comorbidity pattern matching within individual EMRs. All source codes developed for our noninvasive prediction models can be retrieved from GitHub.
Collapse
Affiliation(s)
- Yueh Tang
- Department of Computer Science and Information Engineering, National Taipei University of Technology, 106344 Taipei, Taiwan
| | - Chao-Hung Wang
- Heart Failure Research Center, Division of Cardiology, Department of Internal Medicine, Chang Gung Memorial Hospital, 204201 Keelung, Taiwan
- College of Medicine, Chang Gung University, 333323 Taoyua, Taiwan
| | - Prasenjit Mitra
- L3S Research Center, 30167 Hannover, Germany
- College of Information Sciences and Technology, The Pennsylvania State University, University Park, PA 16802, USA
| | - Tun-Wen Pai
- Department of Computer Science and Information Engineering, National Taipei University of Technology, 106344 Taipei, Taiwan
- Department of Computer Science and Engineering, National Taiwan Ocean University, 202301 Keelun, Taiwan
| |
Collapse
|
2
|
Weigel S, Heindel W, Decker T, Weyer-Elberich V, Kerschke L, Gerß J, Hense HW. Digital Breast Tomosynthesis versus Digital Mammography for Detection of Early-Stage Cancers Stratified by Grade: A TOSYMA Subanalysis. Radiology 2023; 309:e231533. [PMID: 38051184 DOI: 10.1148/radiol.231533] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/07/2023]
Abstract
Background Breast cancer screening with digital breast tomosynthesis (DBT) plus synthesized mammography (SM) increases invasive tumor detection compared with digital mammography (DM). However, it is not known how the prognostic characteristics of the cancers detected with the two screening approaches differ. Purpose To compare invasive breast cancers detected with DBT plus SM (test arm) versus DM (control arm) screening with regard to tumor stage, histologic grade, patient age, and breast density. Materials and Methods This exploratory subanalysis of the Tomosynthesis plus Synthesized Mammography (TOSYMA) study, which is a multicenter randomized controlled trial embedded in the German mammography screening program, recruited women aged 50-70 years from July 2018 to December 2020. It compared invasive cancer detection rates (iCDRs), rate differences, and odds ratios (ORs) between the arms stratified by Union for International Cancer Control (UICC) stage (I vs II-IV), histologic grade (1 vs 2 or 3), age group (50-59 vs 60-70 years), and Breast Imaging Reporting and Data System categories of breast density (A or B vs C or D). Results In total, 49 462 (median age, 57 years [IQR, 53-62 years]) and 49 669 (median age, 57 years [IQR, 53-62 years]) participants were allocated to DBT plus SM and DM screening, respectively. The iCDR of stage I tumors with DBT plus SM was 51.6 per 10 000 women (255 of 49 462) and with DM it was 30.0 per 10 000 women (149 of 49 669). DBT plus SM depicted more stage I tumors with grade 2 or 3 (166 of 49 462, 33.7 per 10 000 women) than DM (106 of 49 669, 21.3 per 10 000 women; rate difference, +12.3 per 10 000 women [95% CI: 0.3, 24.9]; OR, 1.6 [95% CI: 0.9, 2.7]). DBT plus SM achieved the highest iCDR of stage I tumors with grade 2 or 3 among women aged 60-70 years with dense breasts (41 of 7364, 55.4 per 10 000 women; rate difference, +21.6 per 10 000 women [95% CI: -21.1, 64.3]; OR, 1.6 [95% CI: 0.6, 4.5]). Conclusion DBT plus SM screening appears to lead to higher detection of early-stage invasive breast cancers of grade 2 or 3 than DM screening, with the highest rate among women aged 60-70 years with dense breasts. Clinical trial registration no. NCT03377036 © RSNA, 2023 See also the editorial by Ha and Chang in this issue.
Collapse
Affiliation(s)
- Stefanie Weigel
- From the Clinic for Radiology and Reference Center for Mammography Münster (S.W., W.H., T.D.), Institute of Biostatistics and Clinical Research (V.W.E., L.K., J.G.), and Institute of Epidemiology and Social Medicine (H.W.H.), University of Münster and University Hospital Münster, Albert-Schweitzer-Campus 1, Building A1, D-48149 Münster, Germany
| | - Walter Heindel
- From the Clinic for Radiology and Reference Center for Mammography Münster (S.W., W.H., T.D.), Institute of Biostatistics and Clinical Research (V.W.E., L.K., J.G.), and Institute of Epidemiology and Social Medicine (H.W.H.), University of Münster and University Hospital Münster, Albert-Schweitzer-Campus 1, Building A1, D-48149 Münster, Germany
| | - Thomas Decker
- From the Clinic for Radiology and Reference Center for Mammography Münster (S.W., W.H., T.D.), Institute of Biostatistics and Clinical Research (V.W.E., L.K., J.G.), and Institute of Epidemiology and Social Medicine (H.W.H.), University of Münster and University Hospital Münster, Albert-Schweitzer-Campus 1, Building A1, D-48149 Münster, Germany
| | - Veronika Weyer-Elberich
- From the Clinic for Radiology and Reference Center for Mammography Münster (S.W., W.H., T.D.), Institute of Biostatistics and Clinical Research (V.W.E., L.K., J.G.), and Institute of Epidemiology and Social Medicine (H.W.H.), University of Münster and University Hospital Münster, Albert-Schweitzer-Campus 1, Building A1, D-48149 Münster, Germany
| | - Laura Kerschke
- From the Clinic for Radiology and Reference Center for Mammography Münster (S.W., W.H., T.D.), Institute of Biostatistics and Clinical Research (V.W.E., L.K., J.G.), and Institute of Epidemiology and Social Medicine (H.W.H.), University of Münster and University Hospital Münster, Albert-Schweitzer-Campus 1, Building A1, D-48149 Münster, Germany
| | - Joachim Gerß
- From the Clinic for Radiology and Reference Center for Mammography Münster (S.W., W.H., T.D.), Institute of Biostatistics and Clinical Research (V.W.E., L.K., J.G.), and Institute of Epidemiology and Social Medicine (H.W.H.), University of Münster and University Hospital Münster, Albert-Schweitzer-Campus 1, Building A1, D-48149 Münster, Germany
| | - Hans-Werner Hense
- From the Clinic for Radiology and Reference Center for Mammography Münster (S.W., W.H., T.D.), Institute of Biostatistics and Clinical Research (V.W.E., L.K., J.G.), and Institute of Epidemiology and Social Medicine (H.W.H.), University of Münster and University Hospital Münster, Albert-Schweitzer-Campus 1, Building A1, D-48149 Münster, Germany
| |
Collapse
|
3
|
Lin YS, Kuan CH, Lo C, Tsai LW, Wu CH, Huang CH, Yeong EK, Tai HC, Huang CS. Is Immediate Lymphatic Reconstruction on Breast Cancer Patients Oncologically Safe? A Preliminary Study. PLASTIC AND RECONSTRUCTIVE SURGERY-GLOBAL OPEN 2023; 11:e5385. [PMID: 37941816 PMCID: PMC10629743 DOI: 10.1097/gox.0000000000005385] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2023] [Accepted: 09/20/2023] [Indexed: 11/10/2023]
Abstract
Background In breast cancer patients receiving axillary lymph node dissection (ALND), immediate lymphatic reconstruction (ILR) with lymphovenous anastomosis is an emerging technique for reducing the risk of arm lymphedema. However, the oncologic safety of surgically diverting lymphatic ducts directly into venules in a node-positive axilla is still a concern of inadvertently inducing metastasis of remaining cancer cells. This study aimed to assess the oncologic safety of ILR. Methods From January 2020 to January 2022, 95 breast cancer patients received ALND, and 45 of them also received ILR. Patients with recurrent cancer, with follow-up less than 12 months, and with missed data were excluded. Variables were compared between ILR and non-ILR groups, and the outcome of interest was the rate of distant recurrence after follow-up for at least 1 year. Results Thirty-four patients in the ILR group and 32 patients in the non-ILR group fulfilled the inclusion criteria for analysis. No statistically significant difference was noted between groups in terms of age, body mass index, type of breast surgery, pathologic cancer staging, histologic type and grade of breast cancer, molecular subtypes, frequency of axillary lymph node metastasis, or adjuvant therapy. For the patients receiving follow-up for at least 1 year, no statistically significant difference was found in terms of distant recurrence rates between ILR and non-ILR groups (P = 0.44). Conclusion For breast cancer patients receiving ALND, ILR with lymphovenous anastomosis is oncologically safe, within an average follow-up period of 21 months.
Collapse
Affiliation(s)
- Ying-Sheng Lin
- From the Division of Plastic Surgery, Department of Surgery, National Taiwan University Hospital Yunlin Branch, Yunlin County, Taiwan
| | - Chen-Hsiang Kuan
- Division of Plastic Surgery, Department of Surgery, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
| | - Chiao Lo
- Division of General Surgery, Department of Surgery, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
- Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University, Taipei, Taiwan
| | - Li-Wei Tsai
- Division of General Surgery, Department of Surgery, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
- Department of Surgical Oncology, National Taiwan University Cancer Center, Taipei, Taiwan
| | - Chien-Hui Wu
- Division of General Surgery, Department of Surgery, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
| | - Chieh-Huei Huang
- Division of Plastic Surgery, Department of Surgery, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
| | - Eng-Kean Yeong
- Division of Plastic Surgery, Department of Surgery, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
| | - Hao-Chih Tai
- From the Division of Plastic Surgery, Department of Surgery, National Taiwan University Hospital Yunlin Branch, Yunlin County, Taiwan
- Division of Plastic Surgery, Department of Surgery, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
| | - Chiun-Sheng Huang
- From the Division of Plastic Surgery, Department of Surgery, National Taiwan University Hospital Yunlin Branch, Yunlin County, Taiwan
- Division of General Surgery, Department of Surgery, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
| |
Collapse
|
4
|
Screening mammography mitigates breast cancer disparities through early detection of triple negative breast cancer. Clin Imaging 2021; 80:430-437. [PMID: 34543867 DOI: 10.1016/j.clinimag.2021.08.013] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2021] [Accepted: 08/12/2021] [Indexed: 12/14/2022]
Abstract
PURPOSE Screening mammography improves breast cancer survival through early detection, but Triple Negative Breast Cancer (TNBC) is more difficult to detect on mammography and has lower survival compared to non-TNBC, even when detected at early stages. TNBC is twice as common among African American (AA) compared to White American (WA) women, thereby contributing to the 40% higher breast cancer mortality rates observed in AA women. The role of screening mammography in addressing breast cancer disparities is therefore worthy of study. METHODS Outcomes were evaluated for TNBC patients treated in the prospectively-maintained databases of academic cancer programs in two metropolitan cities of the Northeast and Midwest, 1998-2018. RESULTS Of 756 TNBC cases, 301 (39.8%) were mammographically screen-detected. 46% of 189 AA and 38.5% of 460 WA patients had screen-detected TNBC (p = 0.16). 25.3% of 257 TNBC cases ≤50 years old had screen-detected disease compared to 47.3% of 499 TNBC cases >50 years old (p < 0.0001). 220/301 (73.1%) screen-detected TNBC cases were T1 lesions versus 118/359 (32.9%) non-screen-detected cases (p < 0.0001). Screen-detected TNBC was more likely to be node-negative (51.9% v. 40.4%; p < 0.0001). Five-year overall survival was better in screen-detected TNBC compared to nonscreen-detected TNBC (92.8% v. 81.5%; p < 0.0001) in the entire cohort. The magnitude of this effect was most significant among AA patients (Fig. 1). Screening-related survival patterns were similar among AA and WA patients in both cities. CONCLUSION Data from two different cities demonstrates the value of screening mammography to mitigate breast cancer disparities in AA women through the early detection of TNBC.
Collapse
|