We recently reported on a late preterm infant born at 36 weeks' gestation with serious arrhythmia due to hyperkalemia associated with long-term maternal ritodrine administration. It is unknown whether ritodrine alone increases the risk of neonatal hyperkalemia in infants born at 34-36 weeks' gestation. This single-center, retrospective, cohort study enrolled late preterm infants (34-36 gestational weeks) born between 2004 and 2018. Cases with maternal magnesium sulfate use were not sufficient for statistical analysis and so were excluded from the study. Risk factors for the occurrence of hyperkalemia were determined based on clinical relevance and previous reports. In all, 212 late preterm infants with maternal ritodrine use and 400 infants without tocolysis were included in the study. Neonatal hyperkalemia occurred in 5.7% (12/212) in the ritodrine group and 1.8% (7/400) in the control group. The risk of neonatal hyperkalemia was significantly increased by maternal ritodrine administration with a crude odds ratio (OR) of 3.37 (95% confidence interval [CI]: 1.30-8.69; p < 0.01) and an adjusted OR of 3.71 (95% CI: 1.41-9.74; p < 0.01) on multivariable analysis. Long-term tocolysis (≥28 days) with ritodrine increased the risk of neonatal hyperkalemia with 9.3% (11/118) of infants developing hyperkalemia (adjusted OR 4.86; 95% CI: 1.59-14.83; p < 0.01). Neonatal hyperkalemia was not found within 2 weeks of ritodrine administration. This research suggests that late preterm infants born after long-term ritodrine administration are at risk of neonatal hyperkalemia and require special attention.
Masato Tagi, Mari Tajiri, Yasuhiro Hamada, Yoshifumi Wakata, Xiao Shan, Kazumi Ozaki, Masanori Kubota, Sosuke Amano, Hiroshi Sakaue, Yoshiko Suzuki and Jun Hirose : Accuracy of an Artificial Intelligence-Based Model for Estimating Leftover Liquid Food in Hospitals: Validation Study., JMIR Formative Research, Vol.6, No.5, e35991, 2022.
(要約)
An accurate evaluation of the nutritional status of malnourished hospitalized patients at a higher risk of complications, such as frailty or disability, is crucial. Visual methods of estimating food intake are popular for evaluating the nutritional status in clinical environments. However, from the perspective of accurate measurement, such methods are unreliable. The accuracy of estimating leftover liquid food in hospitals using an artificial intelligence (AI)-based model was compared to that of visual estimation. The accuracy of the AI-based model (AI estimation) was compared to that of the visual estimation method for thin rice gruel as staple food and fermented milk and peach juice as side dishes. A total of 576 images of liquid food (432 images of thin rice gruel, 72 of fermented milk, and 72 of peach juice) were used. The mean absolute error, root mean squared error, and coefficient of determination (R) were used as metrics for determining the accuracy of the evaluation process. Welch t test and the confusion matrix were used to examine the difference of mean absolute error between AI and visual estimation. The mean absolute errors obtained through the AI estimation approach were 0.63 for fermented milk, 0.25 for peach juice, and 0.85 for the total. These were significantly smaller than those obtained using the visual estimation approach, which were 1.40 (P<.001) for fermented milk, 0.90 (P<.001) for peach juice, and 1.03 (P=.009) for the total. By contrast, the mean absolute error for thin rice gruel obtained using the AI estimation method (0.99) did not differ significantly from that obtained using visual estimation (0.99). The confusion matrix for thin rice gruel showed variation in the distribution of errors, indicating that the errors in the AI estimation were biased toward the case of many leftovers. The mean squared error for all liquid foods tended to be smaller for the AI estimation than for the visual estimation. Additionally, the coefficient of determination (R) for fermented milk and peach juice tended to be larger for the AI estimation than for the visual estimation, and the R value for the total was equal in terms of accuracy between the AI and visual estimations. The AI estimation approach achieved a smaller mean absolute error and root mean squared error and a larger coefficient of determination (R) than the visual estimation approach for the side dishes. Additionally, the AI estimation approach achieved a smaller mean absolute error and root mean squared error compared to the visual estimation method, and the coefficient of determination (R) was similar to that of the visual estimation method for the total. AI estimation measures liquid food intake in hospitals more precisely than visual estimation, but its accuracy in estimating staple food leftovers requires improvement.
Kotaro Matsumoto, Yasunobu Nohara, Yoshifumi Wakata, Takanori Yamashita and Yukio Kozuma : Impact of a learning health system on acute care and medical complications after intracerebral hemorrhage, Learning Health Systems, 2020.
(キーワード)
learning health system / 口腔ケア (oral care) / pneumonia / stroke
Jun Hirose, Yoshifumi Wakata, Masato Tagi and Yuu Tamaki : The role of medical informatics in the management of medical information, The Journal of Medical Investigation : JMI, Vol.67, No.1,2, 27-29, 2020.
(要約)
With progress in information and communication technology, medical information has been converted to digital formats and stored and managed using computer systems. The construction, management, and operation of medical information systems and regional medical liaison systems are the main components of the clinical tasks of medical informatics departments. Research using medical information accumulated in these systems is also a task for medical informatics department. Recently, medical real-world data (RWD) accumulated in medical information systems has become a focus not only for primary use but also for secondary uses of medical information. However, there are many problems, such as standardization, collection, cleaning, and analysis of them. The internet of things and artificial intelligence are also being applied in the collection and analysis of RWD and in resolving the above problems. Using these new technologies, progress in medical care and clinical research is about to enter a new era. J. Med. Invest. 67 : 27-29, February, 2020.
Atsushi Kimura, Yoshihiro Matsumoto, Yoshifumi Wakata, Akiko Oyamada, Masanobu Ohishi, Toshifumi Fujiwara, Ko Ikuta, Kuniyoshi Tsuchiya, Naohisa Tayama, Shinji Tomari, Hisaaki Miyahara, Takao Mae, Toshihiko Hara, Taichi Saito, Takeshi Arizono, Kozo Kaji, Taro Mawatari, Masami Fujiwara, Riku Sakimura, Kunichika Shin, Kenichi Ninomiya, Kazutoshi Nakaie, Yasuaki Antoku, Shoji Tokunaga, Naoki Nakashima, Yukihide Iwamoto and Yasuharu Nakashima : Predictive factors of mortality of patients with fragility hip fractures at 1 year after discharge: A multicenter, retrospective study in the northern Kyushu district of Japan., Journal of Orthopaedic Surgery (Hong Kong), Vol.27, No.3, 2019.
(要約)
, TCCI 5, smoking history, LOS <14 days, and BI <30 were those for females. Decreased BI is one of the independent and preventable risk factors. A comprehensive therapeutic approach should be considered to prevent deterioration of activities of daily living and a higher risk of mortality.
Hiroaki Kurata, Masayuki Ochiai, Hirosuke Inoue, Takeshi Kusuda, Junko Fujiyoshi, Masako Ichiyama, Yoshifumi Wakata and Hidetoshi Takada : Inflammation in the neonatal period and intrauterine growth restriction aggravate bronchopulmonary dysplasia., Pediatrics and Neonatology, Vol.60, No.5, 496-503, 2019.
(要約)
This prospective observational study enrolled 73 BPD patients from a total of 331 infants with a birth weight of <1500 g from 2005 to 2013. The clinical severity of BPD was defined by the duration of oxygen supplementation and positive pressure ventilation (PPV) in line with the diagnostic criteria of BPD. The hematological status and cytokine levels were surveyed from blood samples at birth and at 2 and 4 weeks of life.
Rieko Izukura, Tadashi Kandabashi, Yoshifumi Wakata, Chinatsu Nojiri, Yasunobu Nohara, Takanori Yamashita, Atsushi Takada, Jinsang Park, Yoshiaki Uyama and Naoki Nakashima : The Development of an Electronic Phenotyping Algorithm for Identifying Rhabdomyolysis Patients in the MID-NET Database., Studies in Health Technology and Informatics, Vol.264, 1498-1499, 2019.
(要約)
We aimed to develop rhabdomyolysis (RB) phenotyping algorithms using machine learning techniques and to create subphenotyping algorithms to identify RB patients who lack RB diagnosis. Two pattern algorithms, one with a focus on improving predictive value and one focused on improving sensitivity, were finally created and had a high area under the curve value of 0.846. Although we were unable to create subphenotyping algorithms, an attempt to detect unknown RB patients is important for epidemiological studies.
(キーワード)
Algorithms / Databases, Factual / Electronic Health Records / Humans / Machine Learning / Rhabdomyolysis
Takanori Yamashita, Yoshifumi Wakata, Hideki Nakaguma, Yasunobu Nohara and Shinji Hato : Machine Learning for Classification of Postoperative Patient Status Using Standardized Medical Data, APAMI 2020, Nov. 2020.