Identifying the optimal conditioning intensity for stem cell transplantation in patients with myelodysplastic syndrome: a machine learning analysis

被引：5

作者：

Shimomura, Yoshimitsu ^{[1
,2
]}

Komukai, Sho ^{[3
]}

Kitamura, Tetsuhisa ^{[2
]}

Sobue, Tomotaka ^{[2
]}

Kurosawa, Shuhei ^{[4
]}

Doki, Noriko ^{[5
]}

Katayama, Yuta ^{[6
]}

Ozawa, Yukiyasu ^{[7
]}

Matsuoka, Ken-ichi ^{[8
]}

Tanaka, Takashi ^{[9
]}

Kako, Shinichi ^{[10
]}

Sawa, Masashi ^{[11
]}

Kanda, Yoshinobu ^{[12
]}

Nakamae, Hirohisa ^{[13
]}

Nakazawa, Hideyuki ^{[14
]}

Ueda, Yasunori ^{[15
,16
]}

Kanda, Junya ^{[17
]}

Fukuda, Takahiro ^{[9
]}

Atsuta, Yoshiko ^{[18
,19
]}

Ishiyama, Ken ^{[20
]}

机构：

[1] Kobe City Hosp Org, Kobe City Med Ctr, Gen Hosp, Dept Hematol, Minamimati 2-1-1,Chuo Ku, Kobe, Hyogo 6500047, Japan

[2] Osaka Univ, Grad Sch Med, Dept Environm Med & Populat Sci, 2-2 Yamadaoka, Suita, Osaka 5650871, Japan

[3] Osaka Univ, Dept Integrated Med, Grad Sch Med, Div Biomed Stat, 2-2 Yamadaoka, Suita, Osaka 5650871, Japan

[4] Univ Tokyo, Div Stem Cell & Mol Med, Inst Med Sci, 4-6-1 Shiroganedai,Minato Ku, Tokyo 1080071, Japan

[5] Komagome Hosp, Tokyo Metropolitan Canc & Infect Dis Ctr, Hematol Div, 3-18-22 Honkomagome,Bunkyo Ku, Tokyo 1138677, Japan

[6] Hiroshima Red Cross Hosp & Atom Bomb Survivors Ho, Dept Hematol, 1-9-6 Sendamachi,Naka Ku, Hiroshima 7308619, Japan

[7] Nagoya Daiichi Hosp, Dept Hematol, Japanese Red Cross Aichi Med Ctr, 3-35 Michishita Tyo,Nakamura Ku, Nagoya, Aichi 4538511, Japan

[8] Okayama Univ Hosp, Dept Hematol & Oncol, 2-5-1 Shikata Cho,Kita Ku, Okayama 7000914, Japan

[9] Natl Canc Ctr, Dept Hematopoiet Stem Cell Transplantat, 5-1-1 Tsukiji,Chuo Ku, Tokyo 1040045, Japan

[10] Jichi Med Univ, Div Hematol, Saitama Med Ctr, 1-847 Amanuma Cho,Omiya Ku, Saitama 3308503, Japan

[11] Anjo Kosei Hosp, Dept Hematol & Oncol, 28 Higashihirokute,Anjo Cho, Anjo, Aichi 4468602, Japan

[12] Jichi Med Univ, Div Hematol, 3311-1 Yaushiji, Shimotsuke, Tochigi 3290498, Japan

[13] Osaka City Univ, Grad Sch Med, Dept Hematol, 1-4-3 Asahi Machi,Abeno Ku, Osaka 5458585, Japan

[14] Shinshu Univ, Dept Hematol, Sch Med, 3-1-1 Asahi, Matsumoto, Nagano 3908621, Japan

[15] Kurashiki Cent Hosp, Dept Hematol Oncol & Transfus, I-1-1 Miwa, Kurashiki, Okayama 7108602, Japan

[16] Kurashiki Cent Hosp, Hemapheresis Ctr, 1-1-1 Miwa, Kurashiki, Okayama 7108602, Japan

[17] Kyoto Univ, Grad Sch Med, Dept Hematol & Oncol, Yoshida Konoe Cho,Sakyo Ku, Kyoto 6068501, Japan

[18] Japanese Data Ctr Hematopoiet Cell Transplantat, 1-1 Yazakokariata, Nagakute, Aichi 4801195, Japan

[19] Aichi Med Univ, Dept Registry Sci Transplant & Cellular Therapy, Sch Med, 1-1 Yazakokariata, Nagakute, Aichi 4801195, Japan

[20] Kanazawa Univ Hosp, Dept Hematol, 13-1 Takaramachi, Kanazawa, Ishikawa 9208641, Japan

来源：

BONE MARROW TRANSPLANTATION | 2023年 / 58卷 / 02期

关键词：

ACUTE MYELOID-LEUKEMIA; SUBGROUP IDENTIFICATION; HETEROGENEOUS TREATMENT; WORKING PARTY; IMPUTATION; REGIMEN; BLOOD;

D O I：

10.1038/s41409-022-01871-8

中图分类号：

Q6 [生物物理学];

学科分类号：

071011 ;

摘要：

A conditioning regimen is an essential prerequisite of allogeneic hematopoietic stem cell transplantation for patients with myelodysplastic syndrome (MDS). However, the optimal conditioning intensity for a patient may be difficult to establish. This study aimed to identify optimal conditioning intensity (reduced-intensity conditioning regimen [RIC] or myeloablative conditioning regimen [MAC]) for patients with MDS. Overall, 2567 patients with MDS who received their first HCT between 2009 and 2019 were retrospectively analyzed. They were divided into a training cohort and a validation cohort. Using a machine learning-based model, we developed a benefit score for RIC in the training cohort. The validation cohort was divided into a high-score and a low-score group, based on the median benefit score. The endpoint was progression-free survival (PFS). The benefit score for RIC was developed from nine baseline variables in the training cohort. In the validation cohort, the hazard ratios of the PFS in the RIC group compared to the MAC group were 0.65 (95% confidence interval [CI]: 0.48-0.90, P = 0.009) in the high-score group and 1.36 (95% CI: 1.06-1.75, P = 0.017) in the low-score group (P for interaction < 0.001). Machine-learning-based scoring can be useful for the identification of optimal conditioning regimens for patients with MDS.

引用

页码：186 / 194

页数：9

共 35 条

[1] Allogeneic haematopoietic cell transplantation with reduced-intensity conditioning for elderly patients with advanced myelodysplastic syndromes: a nationwide study [J].