Non-Communicable Diseases, such as heart disease, stroke, cancer, diabetes, and chronic lung disease, are the leading causes of death worldwide. These diseases do not have a one-to-one relationship between cause and effect, but are the result of the intertwining of various factors in multiple layers of daily life, such as diet, exercise, sleep, relationships, living environment, preferences, and work. However, it is not easy for the general public, excluding health-conscious people, to change their behavior toward their future health. Therefore, we propose a new concept of "street medical" as a starting point for the development of new intervention methods. "Street medical" is an attempt to expand the scope of medical care from "patients" to "consumers" and from "hospitals" to "places of daily life," and to incorporate the knowledge and know-how accumulated in the lifestyle and entertainment industries to update medical care in order to appeal to the happiness of people.

　In this paper, we introduce two examples of "street medical" that we have worked on so far: (1) "floor decoration design measures to promote fast walking and increase stride length" and (2) "digital games to promote early detection of mild cognitive impairment (MCI)," along with the results of their effectiveness verification, and share an image of "street medical" in practice. Furthermore, we will show the possibility that the "PERMA Model," a check frame for the Happiness factor, can be extremely effective in developing effective behavior change intervention methods.

　As the decrease of Helicobacter pylori (H.pylori) infection rate, the incidence of H.pylori-uninfected gastric cancer is gradually increasing, and it was revealed that there are various histopathological type of H.pylori-uninfected gastric cancers. Gastric foveolar-type adenocarcinoma, which appears reddish and protruded in H.pylori-uninfected gastric mucosa, is known as "raspberry-like Gastric foveolar-type adenocarcinoma". Whereas, other histopathological types of gastric lesions which resemble for raspberry in H.pylori-uninfected gastric mucosa have been also reported. We define gastric lesions which resemble for raspberry as RSGL (raspberry shaped gastric lesion). We describe endoscopic and clinicopathological features of each histopathological type of RSGLs, and endoscopic differential diagnoses. RSGLs are classified into five histopathological types: gastric adenocarcinoma of foveolar type (GA-FV), gastric adenocarcinoma of fundic-gland type (GA-FG), gastric adenocarcinoma of fundic-gland mucosa type (GA-FGM), hyperplastic polyp (HP), and proton pump inhibitor-related lesion (PPI-L). GA-FV lesions have homogenously reddish and exhibited only polygonal/curved marginal crypt epithelium (MCE) without a subepithelial lesion (SEL) shape. GA-FG lesions have heterogeneous reddish with a SEL shape. GA-FGM lesions have homogenous reddish with a SEL shape. HP and PPI-L have homogenous reddish and exhibited polygonal/curved and linear/dotted MCE without a SEL shape. The diagnostic algorithm for RSGLs based on these endoscopic features is useful for endoscopic differentiation of RSGLs.

　Endoscopic screening for gastric cancer started in the Itabashi Ward, Tokyo in 2019, which involved the participation of eight clinics and ten hospitals. The secondary interpretation is recommended as an accuracy control; however, improving the work efficiency of interpretation is necessary for increasing the number of screening facilities. Following the discussion with the Itabashi Medical Association and Itabashi ward office, a cloud-based secondary interpretation system (Fujifilm Medical) was introduced for endoscopic screening. The handling of personal information was a matter of concern while introducing this interpretation system. It was necessary to work closely with cloud operators, such as the development of personal computers (PCs) and internet environments at each facility along with the dissemination of operation methods to these facilities. The features of endoscopic screening included countermeasures against the leakage of personal information while using the cloud, such as deleting personal names including endoscopic images and setting rules related to PCs used for screening and the large proportion of hospitals. The cloud-based secondary interpretation system allows a secondary interpretation to be performed at one's own clinic or hospital, and there is no need to participate in a medical association hall. An advantage of the cloud -based secondary interpretation was observed in infection risk reduction, particularly during the coronavirus disease 2019 pandemic. However, it is a challenge to communicate with all doctors from different clinics and hospitals participating in the screening the important rules associated with this system, such as on-time reading, input of required items in cloud systems, and compliance with the manual of shooting order of endoscopy. Moreover, the importance of conducting workshops and creating easy-to-understand documents has been considered.

　Aim: Endoscopic examination has been started since 2016 for the national gastric cancer surveillance program. The national gastric cancer surveillance program included 1^st and 2^nd endoscopic image reading. The aim of our study was to evaluate the effectiveness of artificial intelligence gastric cancer diagnosis in 2^nd endoscopic image reading.

　Methods: We retrospectively collected endoscopic images from endoscopic examinations performed in Nagasaki Prefecture. We analyzed these endoscopic images using our object detection AI model for detecting gastric cancer. Our AI model evaluated endoscopic images classified as anomaly or normal images. We evaluated sensitivity and specificity for gastric cancer detection per patient level and per image level, respectively.

　Results: A total of 65 patients were analyzed. The mean number of endoscopic images per patient was 66.7 images (standard deviation 9.4 images). The sensitivity and specificity for gastric cancer per patient level were 100% (6/6 patients) and 20.3% (12/59 patient), respectively. The sensitivity and specificity for gastric cancer per image level were 60.6% (54/89 images) and 95.7% (4,067/4,252 images), respectively. The mean number of ‘anomaly' images was 3.6 images (standard deviation 4.1 images). The mean number of ‘normal' images was 63.1 images (standard deviation 8.8 images).

　Conclusion: Our gastric cancer endoscopic diagnosis AI model may be useful for 2^nd reading in gastric cancer screening programs.

　Electrocardiography was invented more than 100 years ago by Einthoven et al. It is still in use today as an important medical examination. Attempts to use computers to automatically diagnose electrocardiograms began in the 1960s. In the 1970s, an automated diagnostic system consisting of an electrocardiograph, a minicomputer, and a teletypewriter was developed, and in the 1980s, automated diagnostic and printing functions were built into the body of a single electrocardiograph. Although the accuracy of automatic diagnosis has been high for normal waveforms since its early development, there are still many cases of difficulty in diagnosing complex or small waveforms. In order to study the problems related to automatic ECG diagnosis, a "The task force on automated diagnosis of the electrocardiogram in Japan." consisting of researchers, company engineers, and clinicians was formed, and discussions were held, and an expert consensus statement was issued on the unification of the names of findings and diagnoses in automatic diagnosis. Furthermore, the study of inappropriate cases showed that the accuracy of automated diagnosis is not only over- or under-diagnosis of myocardial ischemia, but also misdiagnosis of atrial fibrillation and missed pacing spikes, although these cases are less frequent. In considering the future of automated diagnosis, it is important to note that the widespread use of smartwatches, including the Apple Watch, has created a situation in which individuals record and own ECG waveforms using ECG functions. To improve the accuracy of the current automatic diagnosis, it is suggested that in addition to improving the conventional algorithm, a program using AI diagnostic theory could also be useful.

　The automatic analysis function in electrocardiographs can standardize diagnostic criteria by providing an objective double check in addition to the subjective diagnosis by physicians, and can provide reproducible results that are not affected by individual differences in physician interpretation. It is widely used in group medical examinations since it can easily obtain measurements such as the QRS electrical axis which require complicated calculations, and can analyze a large number of ECGs in a short amount of time.

However, the results of automated analysis are not perfect and misinterpretations may occur. If valid analysis results cannot be obtained, the results may be improved by reviewing the operating environment of the ECG device. In particular, reviewing the filter settings and applying other noise countermeasures have proven effective. Since automatic analysis is performed according to a predetermined process (algorithm), understanding the principles behind automatic analysis allows a deeper understanding of its results, which is considered to be effectively useful in daily clinical practice.

　Using the automatic analysis of Fukuda Denshi's 12-lead ECG as an example, we will explain measurement processing, the Minnesota Code, and algorithms for finding classification.

　In health checkup, an electrocardiograph with an automatic diagnostic function is often used, and the Minnesota code is output as its diagnosis. Q waves tend to appear in coronary artery disease, cardiomyopathy, etc., and are considered important in clinical practice, but there are rare in health checkup, and are more common with physiological or positional changes. In pathological cases, Q waves tend to appear in multiple related inductions in pathological cases. Since the Minnesota code is settled as a single induction finding, false positives are more common. There are limitations in assessing severity by code about Q waves. In this paper, the challenges of automatic electrocardiograph diagnosis in health checkup are discussed, especially the Q wave and the incompatible codes defined in the Minnesota code.

　For further study to obtain a good diagnosis of breast disease in breast screening candidates suspected to have a breast abnormality, appropriate information about breast screening examination is inevitable. Mammography, ultrasound, in case, physical examination is prevalent for breast cancer screening in Japan. If a candidate is checked by any examinations, information about the type of abnormality, such as breast mass, calcification of mammary gland should be clearly stated. The laterality of the checked abnormal findings should be also noted. In addition, the probability of malignancy should be noted without exception! The information is correctly sent with a candidate introduced to a breast surgeon. The information will be used to select examinations of the next stage to diagnose the real character of the breast abnormality checked by screening modalities. Thus, the breast surgeon will be able to obtain a good diagnosis of the breast abnormalities without spending a long time.

　The information of breast cancer screening, especially DICOM-filed breast imaging data is important and should be used to get a correct and prompt diagnosis of the breast abnormal findings.

　There is concern about a decrease in opportunities for early cancer detection due to reluctance to undergo health checkups as a result of the COVID-19 pandemic. The total number of persons who underwent health checkups at our hospital before (FY 2019) and after (FY 2020, FY 2021) the COVID-19 pandemic and malignant diseases detected in health checkups were tabulated by site (breast, colon, lung, stomach, uterus, prostate, and others), and the proportion of early cancers was determined within the range that could be retrieved. Travel medical checkups were greatly affected by the COVID-19 pandemic, falling significantly from FY 2019 (134,906) to FY 2020 (95,745), and not reaching the level before the COVID-19 pandemic in FY 2021 (112,004). Outpatient medical checkups showed an increasing trend (29,144 in FY 2019, 35,087 in FY 2020, and 43,873 in FY 2021), partly due to the relocation of this hospital to the Minato Mirai area in April 2020, which increased the number of patients accepted. The total number of examinees did not recover to the level before the COVID-19 pandemic (FY 2019) in FY 2021, due to a large drop in traveling medical examinations. The number of cancers detected was not in proportion to the total number of examinees, but showed an increasing trend (177 cases in FY 2019, 200 cases in FY 2020, and 214 cases in FY 2021). The increase in the number of colorectal cancers detected in FY2020 was particularly marked (30 cases in FY2019 to 59 cases in FY2020), and reports of early-stage cancers increased; however, the proportion of early-stage cancers in the total number of cancers detected showed a downward trend (38.5% in FY2019, 36.2% in FY2020, 35.1% in FY2021). Even in the face of the COVID-19 pandemic, there is no change in the importance of health checkups and preventive medicine, and we will continue our health checkup services by thoroughly implementing infection control measures at health checkup sites and striving to improve accuracy control.

　Sysmex Corporation is a leading provider of analyzers, reagents, and quality-controlled samples for various fields of testing, including Hematology, Urinalysis, Hemostasis, Immunology, and Life Science. We also supply controls for Clinical Chemistry and Serology to laboratories that perform specimen examinations in Japan.

　In addition to our product offerings, we provide comprehensive services to support quality assurance in laboratories. These services include assistance with ISO 15189 certification, calibration of blood cell analyzers, and external quality assessments across all testing fields. By offering these services, we aim to instill confidence in laboratories and help them maintain and improve the quality of their specimen examinations.

　In this article, we will focus on two key efforts in our quality assurance services:

　External Quality Assessment Management: We utilize a network-based system to manage external quality assessments.

　Quality Management Systems (QMS) for quality assurance services: Our quality management systems for quality assurance services have been certified by three international standards; ISO/IEC 17043, ISO/IEC 17025, and ISO 15195.

　Through these initiatives, Sysmex Corporation is committed to supporting laboratories in maintaining high standards of quality assurance.

　Abdominal ultrasonography results should be collected on the appointed day in the 1-day health check-up. Participation of sonography specialist physicians caused only minor improvement of sonography examination retardation. Misdiagnoses were reliably reduced by triple check-up ultrasonography reporting system. We have continued weekly conference of correlation with sonography results and detailed examination results.