Unique ID issued by UMIN | UMIN000049686 |
---|---|
Receipt number | R000056591 |
Scientific Title | Multidisciplinary Observational Study with Artificial Intelligence on Diagnosis, Prognosis Prediction, and Treatment of Pneumonia for the Older Adults |
Date of disclosure of the study information | 2022/12/04 |
Last modified on | 2022/12/05 05:21:14 |
Multidisciplinary Observational Study with Artificial Intelligence on Diagnosis, Prognosis Prediction, and Treatment of Pneumonia for the Older Adults
Multidisciplinary Observational Study with Artificial Intelligence on Diagnosis, Prognosis Prediction, and Treatment of Pneumonia for the Older Adults
Multidisciplinary Observational Study with Artificial Intelligence on Diagnosis, Prognosis Prediction, and Treatment of Pneumonia for the Older Adults
Multidisciplinary Observational Study with Artificial Intelligence on Diagnosis, Prognosis Prediction, and Treatment of Pneumonia for the Older Adults
Japan |
pneumonia
Medicine in general | Pneumology | Geriatrics |
Rehabilitation medicine | Adult |
Others
NO
The primary objective of this study is to verify whether artificial intelligence analysis can predict life expectancy and optimize treatment for older patients with pneumonia (including COVID-19) based on the information collected in the electronic medical record (EMR) .
Others
The secondary objective of this study is to use artificial intelligence analysis to identify factors related to pneumonia treatment and physical and cognitive function prognosis in older patients with pneumonia (incl. COVID-19).
Severity (use of ventilator/noninvasive positive pressure ventilation with or without oxygen) and prognosis (survival and death of patients with pneumonia) 30 days after onset of pneumonia
(1) Clinical characteristics of causative organisms
(2) Clinical response to treatment according to the type of antimicrobial agent (body temperature chart and blood sample results to determine whether the patient is cured)
(3) Length of hospitalization (days)
(4) Functional prognosis (alternative nutrition, type of walking aids, cognitive symptoms, facility admission)
(5) Sarcopenia and osteoporosis (dual energy X-ray absorptiometry DEXA, bioimpedance method BIA)
(6) Agreement between artificial intelligence (AI) and physician prognosis (primary endpoint, functional prognosis)
(7) AI assisted diagnosis of chest X-ray
Observational
65 | years-old | <= |
120 | years-old | > |
Male and Female
Pneumonia group
(1) Patients with a history of pneumonia in the past
(2) Those who are 65 years of age or older at the time of onset of pneumonia.
(3) Those who goes to hospital regularly or day-care center.
Non-pneumonia group
(1) Those who have no history of pneumonia in the past.
(2) Patients who are 65 years old or older at the time of their last visit to a hospital or nursing care facility.
(3) Those who goes to hospital regularly or day-care center.
(1) Persons who refuse to participate in the research
9000
1st name | Naoto |
Middle name | |
Last name | Ozaki |
The Jikei University School of Medicine
Department of Rehabilitation Medicine
105-8471
3-19-18 Nishi-Shinbashi, Minato-ku, Tokyo
03-3433-1111
nozakiame@jikei.ac.jp
1st name | Naoto |
Middle name | |
Last name | Ozaki |
The Jikei University School of Medicine
Department of Rehabilitation Medicine
105-8471
3-19-18 Nishi-Shinbashi, Minato-ku, Tokyo
03-3433-1111
nozakiame@jikei.ac.jp
The Jikei University School of Medicine
Japan Agency for Medical Research and Development
Japanese Governmental office
The Jikei University School of Medicine
3-19-18 Nishi-Shinbashi, Minato-ku, Tokyo
03-3433-1111
rinri@jikei.ac.jp
NO
東京大学(東京都),キッコーマン総合病院(千葉県),国際医療福祉大学市川病院(千葉県), 小張総合病院(千葉県), 野田病院(千葉県), 横浜国立大学(神奈川県), 季美の森リハビリテーション病院(千葉県), 日本IBM(東京都)
2022 | Year | 12 | Month | 04 | Day |
Unpublished
Open public recruiting
2022 | Year | 10 | Month | 25 | Day |
2022 | Year | 10 | Month | 25 | Day |
2022 | Year | 10 | Month | 25 | Day |
2026 | Year | 07 | Month | 31 | Day |
This is a multi-institutional observational study to examine whether artificial intelligence analysis of medical records can predict life expectancy, severity of illness, functional prognosis, and appropriate treatment recommendations in older patients with pneumonia.
The following information is to be collected:
Clinical information and laboratory results of pneumonia patients will be obtained from the electronic medical records of participating institutions.
The clinical data will include basic information such as age, gender, height, weight, body temperature, race (place of birth of the patient and one's parents), community-acquired infection, nosocomial infection, past medical history, complications, length of hospitalization, blood data, therapeutic drugs, chest X-ray, CT, MRI, DEXA, BIA and other laboratory records, clinical response to treatment, vital sign(temperature, blood pressure, oxygenation, etc.) ,complications, severity of illness, whether or not a ventilator was used, invasive mechanical ventilation (with or without intubation), duration of intubation, frequency of use of vasopressors or renal replacement therapy, outcome (survival or death), presence of alternative nutrition (gastrostomy, central venous nutrition, etc.), duration of hospitalization, cognitive function assessment, muscle strength assessment (grip strength, knee extension muscle strength), gait function evaluation, long-term care insurance related records (attending physician's opinion, long-term care certification results), history of hospitalization for pneumonia, history of COVID-19, history of medical conditions (internal diseases, bone fracture, Parkinson's disease, cerebrovascular disease, dementia), number of hospitalizations, alternative nutrition, type of walking aid, whether the patient is institutionalized, etc.
2022 | Year | 12 | Month | 04 | Day |
2022 | Year | 12 | Month | 05 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000056591