1
|
Okita J, Nakata T, Uchida H, Kudo A, Fukuda A, Ueno T, Tanigawa M, Sato N, Shibata H. Development and validation of a machine learning model to predict time to renal replacement therapy in patients with chronic kidney disease. BMC Nephrol 2024; 25:101. [PMID: 38493099 PMCID: PMC10943785 DOI: 10.1186/s12882-024-03527-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2023] [Accepted: 02/28/2024] [Indexed: 03/18/2024] Open
Abstract
BACKGROUND Predicting time to renal replacement therapy (RRT) is important in patients at high risk for end-stage kidney disease. We developed and validated machine learning models for predicting the time to RRT and compared its accuracy with conventional prediction methods that uses the rate of estimated glomerular filtration rate (eGFR) decline. METHODS Data of adult chronic kidney disease (CKD) patients who underwent hemodialysis at Oita University Hospital from April 2016 to March 2021 were extracted from electronic medical records (N = 135). A new machine learning predictor was compared with the established prediction method that uses the eGFR decline rate and the accuracy of the prediction models was determined using the coefficient of determination (R2). The data were preprocessed and split into training and validation datasets. We created multiple machine learning models using the training data and evaluated their accuracy using validation data. Furthermore, we predicted the time to RRT using a conventional prediction method that uses the eGFR decline rate for patients who had measured eGFR three or more times in two years and evaluated its accuracy. RESULTS The least absolute shrinkage and selection operator regression model exhibited moderate accuracy with an R2 of 0.60. By contrast, the conventional prediction method was found to be extremely low with an R2 of -17.1. CONCLUSIONS The significance of this study is that it shows that machine learning can predict time to RRT moderately well with continuous values from data at a single time point. This approach outperforms the conventional prediction method that uses eGFR time series data and presents new avenues for CKD treatment.
Collapse
Affiliation(s)
- Jun Okita
- Department of Endocrinology, Metabolism, Rheumatology and Nephrology, Faculty of Medicine, Oita University, 8795593, 1-1 idaigaoka Hasama-cho, Yufu-shi, Oita-ken, Japan
| | - Takeshi Nakata
- Department of Endocrinology, Metabolism, Rheumatology and Nephrology, Faculty of Medicine, Oita University, 8795593, 1-1 idaigaoka Hasama-cho, Yufu-shi, Oita-ken, Japan.
| | - Hiroki Uchida
- Department of Endocrinology, Metabolism, Rheumatology and Nephrology, Faculty of Medicine, Oita University, 8795593, 1-1 idaigaoka Hasama-cho, Yufu-shi, Oita-ken, Japan
| | - Akiko Kudo
- Department of Endocrinology, Metabolism, Rheumatology and Nephrology, Faculty of Medicine, Oita University, 8795593, 1-1 idaigaoka Hasama-cho, Yufu-shi, Oita-ken, Japan
| | - Akihiro Fukuda
- Department of Endocrinology, Metabolism, Rheumatology and Nephrology, Faculty of Medicine, Oita University, 8795593, 1-1 idaigaoka Hasama-cho, Yufu-shi, Oita-ken, Japan
| | - Tamio Ueno
- Department of Medical Technology and Sciences, School of Health Sciences at Fukuoka, International University of Health and Welfare, Okawa, Japan
| | - Masato Tanigawa
- Department of Biophysics, Faculty of Medicine, Oita University, Oita, Japan
| | - Noboru Sato
- Department of Healthcare AI Data Science, Faculty of Medicine, Oita University, Oita, Japan
| | - Hirotaka Shibata
- Department of Endocrinology, Metabolism, Rheumatology and Nephrology, Faculty of Medicine, Oita University, 8795593, 1-1 idaigaoka Hasama-cho, Yufu-shi, Oita-ken, Japan
| |
Collapse
|
2
|
Goto Y, Miura H. Evaluation of an Advanced Care Planning Training Program Incorporating Online Skills in Shared Decision Making: A Preintervention and Postintervention Comparative Study. Healthcare (Basel) 2023; 11:1356. [PMID: 37174898 PMCID: PMC10178132 DOI: 10.3390/healthcare11091356] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2023] [Revised: 03/20/2023] [Accepted: 05/06/2023] [Indexed: 05/15/2023] Open
Abstract
AIM This study evaluated an advanced care planning (ACP) training program incorporating online skills in shared decision making (SDM). METHOD The New World Kirkpatrick Model was employed to assess the efficacy of the training program at four levels: reaction, learning, behavior, and results. Reaction measured the participants' satisfaction and difficulty with the training program alongside the status of support received from workplaces engaging in ACP. Learning evaluated the changes in SDM skills. Behavior assessed the changes in the relationship between patients and healthcare professionals when the latter were involved in the SDM process. Results evaluated whether the participants were willing to participate in ACP educational programs as a facilitator and whether their motivation for continuous learning changed through throughout the training program. The relationships among patients, healthcare providers, and third-party roles were analyzed in SDM role-playing via structural equation modeling (SEM). RESULTS Between September 2020 and June 2022, 145 multidisciplinary participants completed the entirety of the training program. The most common responses to the training were "satisfied", "slightly difficult", and "I received some support from my workplace". The SDM skills significantly improved from the first to the third workshop, evaluated using the Wilcoxon rank-sum test. In the first workshop, SDM was primarily performed by healthcare providers; however, in the third workshop, patient-centered SDM was adopted. Of the participants who completed the program, 63% intended to participate in future ACP educational programs as ACP education facilitators. CONCLUSION This study ascertained the validity of this training.
Collapse
Affiliation(s)
- Yuko Goto
- Department of Home Care and Regional Liaison Promotion, Hospital, National Center for Geriatrics and Gerontology, Obu 474-8511, Aichi, Japan
| | | |
Collapse
|
3
|
Goto Y, Miura H. Validation of the Novel Interprofessional Shared Decision-Making Questionnaire to Facilitate Multidisciplinary Team Building in Patient-Centered Care. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:15349. [PMID: 36430068 PMCID: PMC9690800 DOI: 10.3390/ijerph192215349] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/09/2022] [Accepted: 11/15/2022] [Indexed: 06/16/2023]
Abstract
To support patients in making complex and difficult decisions, it is necessary to form a team that comprises different specialists, the patient, and family members who have detailed information about the latter. Shared decision-making (SDM) is the foundation of patient-centered care; however, its structure in the context of multidisciplinary teams remains unclear. This cross-sectional study aimed to validate the novel interprofessional SDM measure ("Group's SDM measure"). We used data of 175 participants who attended SDM Workshops for Advance Care Planning. The Group's SDM measure included 10 Japanese items that could be used by small groups of multidisciplinary professionals, and the responses were rated using a 6-point Likert scale. The index exhibited a single-factor structure and high goodness of fit with residual correlation via factor analysis. We calculated Cronbach's α (α = 0.948) and McDonald's ω (ω = 0.948) and verified high internal consistency. The Group's SDM measure can be used when evaluating the SDM process where multidisciplinary professionals are involved. We hope that in the future, it will lead to the promotion of interprofessional SDM through training with the use of this measure.
Collapse
Affiliation(s)
- Yuko Goto
- Correspondence: ; Tel.: +81-562-46-2311
| | | |
Collapse
|
4
|
Okada K. Consensus-based proposal for forgoing dialysis therapy in Japan. RENAL REPLACEMENT THERAPY 2022. [DOI: 10.1186/s41100-022-00437-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022] Open
Abstract
AbstractThe Japanese Society for Dialysis Therapy published a proposal in 2014 and revised it to Shared Decision Making for the Initiation and Continuation of Dialysis: A Proposal from the Japanese Society for Dialysis Therapy in 2020 to strictly adhere to guidelines of the Ministry of Health, Labour and Welfare, because forgoing life-sustaining treatment to respect the will of patients in end-of-life care is not stipulated by law in Japan. The revised proposal describes the process of providing information about renal replacement therapy, the natural course of end-stage kidney disease, and conservative kidney management (CKM), the conditions when providing CKM information to be considered by healthcare teams, the process of providing information about CKM if patients with decision-making capacity or families of patients without decision-making capacity wish to make the decision to forgo dialysis, the process of shared decision making for choosing CKM, and the importance of performing advance care planning (ACP) with patients and their families for making advance directives, etc. We need to promote ACP and to establish the content and practice of palliative care for patients after choosing CKM in collaboration with home-cased care doctors.
Collapse
|
5
|
Ookawara S, Ito K, Sasabuchi Y, Miyahara M, Miyashita T, Takemi N, Nagamine C, Nakahara S, Horiuchi Y, Inose N, Shiina M, Murakoshi M, Sanayama H, Hirai K, Morishita Y. Cerebral oxygenation and body mass index association with cognitive function in chronic kidney disease patients without dialysis: a longitudinal study. Sci Rep 2022; 12:10809. [PMID: 35752646 PMCID: PMC9233691 DOI: 10.1038/s41598-022-15129-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2021] [Accepted: 06/20/2022] [Indexed: 12/30/2022] Open
Abstract
In chronic kidney disease (CKD) patients, the prevalence of cognitive impairment increases with CKD progression; however, longitudinal changes in cognitive performance remain controversial. Few reports have examined the association of cerebral oxygenation with cognitive function in longitudinal studies. In this study, 68 CKD patients were included. Cerebral regional oxygen saturation (rSO2) was monitored. Cognitive function was evaluated using mini-mental state examination (MMSE) score. Clinical assessments were performed at study initiation and 1 year later. MMSE score was higher at second measurement than at study initiation (p = 0.022). Multivariable linear regression analysis showed that changes in MMSE were independently associated with changes in body mass index (BMI, standardized coefficient: 0.260) and cerebral rSO2 (standardized coefficient: 0.345). This was based on clinical factors with p < 0.05 (changes in BMI, cerebral rSO2, and serum albumin level) and the following confounding factors: changes in estimated glomerular filtration rate, hemoglobin level, proteinuria, salt and energy intake, age, presence of diabetes mellitus, history of comorbid cerebrovascular disease, and use of renin–angiotensin system blocker. Further studies with a larger sample size and longer observational period are needed to clarify whether maintaining BMI and cerebral oxygenation improve or prevent the deterioration of cognitive function.
Collapse
Affiliation(s)
- Susumu Ookawara
- Division of Nephrology, First Department of Integrated Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma-cho, Omiya-ku, Saitama, Saitama, 330-8503, Japan. .,Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan.
| | - Kiyonori Ito
- Division of Nephrology, First Department of Integrated Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma-cho, Omiya-ku, Saitama, Saitama, 330-8503, Japan.,Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | | | - Mayako Miyahara
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Tomoka Miyashita
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Nana Takemi
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Chieko Nagamine
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Shinobu Nakahara
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Yuko Horiuchi
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Nagisa Inose
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Michiko Shiina
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Miho Murakoshi
- Department of Nutrition, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Hidenori Sanayama
- Division of Neurology, First Department of Integrated Medicine, Saitama Medical Center, Jichi Medical University, Saitama, Japan
| | - Keiji Hirai
- Division of Nephrology, First Department of Integrated Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma-cho, Omiya-ku, Saitama, Saitama, 330-8503, Japan
| | - Yoshiyuki Morishita
- Division of Nephrology, First Department of Integrated Medicine, Saitama Medical Center, Jichi Medical University, 1-847 Amanuma-cho, Omiya-ku, Saitama, Saitama, 330-8503, Japan
| |
Collapse
|
6
|
Challenges in promoting shared decision-making: Towards a breakthrough in Japan. ZEITSCHRIFT FUR EVIDENZ, FORTBILDUNG UND QUALITAT IM GESUNDHEITSWESEN 2022; 171:84-88. [PMID: 35610133 DOI: 10.1016/j.zefq.2022.04.007] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Revised: 04/11/2022] [Accepted: 04/12/2022] [Indexed: 11/21/2022]
Abstract
In Japan, shared decision-making (SDM) is still in its infancy, and there are many challenges and missions in promoting SDM. Older people account for approximately 30% of the population of Japan and they experience several challenges in deciding about the treatment and care for themselves. The importance of specific decision support and patient involvement is yet to be recognized widely for difficult decisions. However, in clinical settings, to support patients in decision-making, continuous activities by healthcare professionals are under development. With several policy guidelines and academic society proposals focusing on SDM, the number of people recognizing the importance of decision-making support is expected to increase. It is important to establish sites dedicated to teaching SDM, improveaccess to them, and managethese training activities continuously. Patients and healthcare providers in Japan will surely benefit from such activities.
Collapse
|