Recent developments in machine learning modeling methods for hypertension treatment.

Hypertension is the leading cause of cardiovascular complications. This review focuses on the advancements in medical artificial intelligence (AI) models aimed at individualized treatment for hypertension, with particular emphasis on the approach to time-series big data on blood pressure and the development of interpretable medical AI models. The digitalization of daily blood pressure records and the downsizing of measurement devices enable the accumulation and utilization of time-series data. As mainstream blood pressure data shift from snapshots to time series, the clinical significance of blood pressure variability will be clarified. The time-series blood pressure prediction model demonstrated the capability to forecast blood pressure variabilities with a reasonable degree of accuracy for up to four weeks in advance. In recent years, various explainable AI techniques have been proposed for different purposes of model interpretation. It is essential to select the appropriate technique based on the clinical aspects; for example, actionable path-planning techniques can present individualized intervention plans to efficiently improve outcomes such as hypertension. Despite considerable progress in this field, challenges remain, such as the need for the prospective validation of AI-driven interventions and the development of comprehensive systems that integrate multiple AI methods. Future research should focus on addressing these challenges and refining the AI models to ensure their practical applicability in real-world clinical settings. Furthermore, the implementation of interdisciplinary collaborations among AI experts, clinicians, and healthcare providers are crucial to further optimizing and validate AI-driven solutions for hypertension management.

Consideration of the reference value and number of measurements of the urinary sodium-to-potassium ratio based on the prevalence of untreated home hypertension: TMM Cohort Study.

The sodium-to-potassium (Na/K) ratio is known to be associated with blood pressure (BP). However, no reference value has been established since the urinary Na/K (uNa/K) ratio is known to have diurnal and day-to-day variations. Therefore, we investigated the number of days required to yield a better association between the morning uNa/K ratio and home BP (HBP) and determined a morning uNa/K ratio value that can be used as a reference value in participants who are not taking antihypertensive medication. This was a cross-sectional study using data from the Tohoku Medical Megabank Project Cohort Study. A total of 3122 participants borrowed HBP and uNa/K ratio monitors for 10 consecutive days. We assessed the relationship between the morning uNa/K ratio from 1 day to 10 days and home hypertension (HBP ≥ 135/85 mmHg) using multiple logistic regression models. Although a 1-day measurement of the morning uNa/K ratio was positively associated with home hypertension, multiple measurements of the morning uNa/K ratio were strongly related to home hypertension. The average morning uNa/K ratio was relatively stable after 3 days (adjusted odds ratio of home hypertension per unit increase in the uNa/K ratio for more than 3 days: 1.19-1.23). In conclusion, there was no threshold for the uNa/K ratio, and the morning uNa/K ratio was linearly associated with home hypertension. The Na/K ratio 2.0 calculated from the Dietary Reference Intakes for Japanese might be a good indication. Regarding the stability of the association between the morning uNa/K ratio and BP, more than 3 days of measurements is desirable.

Future possibilities for artificial intelligence in the practical management of hypertension.

The use of artificial intelligence in numerous prediction and classification tasks, including clinical research and healthcare management, is becoming increasingly more common. This review describes the current status and a future possibility for artificial intelligence in blood pressure management, that is, the possibility of accurately predicting and estimating blood pressure using large-scale data, such as personal health records and electronic medical records. Individual blood pressure continuously changes because of lifestyle habits and the environment. This review focuses on two topics regarding controlling changing blood pressure: a novel blood pressure measurement system and blood pressure analysis using artificial intelligence. Regarding the novel blood pressure measurement system, we compare the conventional cuff-less method with the analysis of pulse waves using artificial intelligence for blood pressure estimation. Then, we describe the prediction of future blood pressure values using machine learning and deep learning. In addition, we summarize factor analysis using "explainable AI" to solve a black-box problem of artificial intelligence. Overall, we show that artificial intelligence is advantageous for hypertension management and can be used to establish clinical evidence for the practical management of hypertension.

Prediction of blood pressure variability using deep neural networks.

PURPOSE: The purpose of our study was to predict blood pressure variability from time-series data of blood pressure measured at home and data obtained through medical examination at a hospital. Previous studies have reported the blood pressure variability is a significant independent risk factor for cardiovascular disease. METHODS: We adopted standard deviation for a certain period and predicted variabilities and mean values of blood pressure for 4 weeks using multi-input multi-output deep neural networks. In designing the prediction model, we prepared a dataset from a clinical study. The dataset included past time-series data for blood pressure and medical examination data such as gender, age, and others. As evaluation metrics, we used the standard deviation ratio (SR) and the root-mean-square error (RMSE). Moreover, we used cross-validation as the evaluation method. RESULTS: The prediction performances of blood pressure variability and mean value after 1-4 weeks showed the SRs were "0.67" to "0.70", the RMSEs were "5.04" to "6.65" mmHg, respectively. Additionally, our models were able to work for a participant with high variability in blood pressure values due to its multi-output nature. CONCLUSION: The results of this study show that our models can predict blood pressure over 4 weeks. Our models work for an individual with high variability of blood pressure. Therefore, we consider that our prediction models are valuable for blood pressure management.

Multiple measurements of the urinary sodium-to-potassium ratio strongly related home hypertension: TMM Cohort Study.

Previous studies have reported a positive association between the urinary sodium-to-potassium (Na/K) ratio and hypertension, and multiple measurements of the casual urinary Na/K ratio are more strongly correlated with the 24-h urinary Na/K ratio than a single measurement. Multiple measurements of the urinary Na/K ratio might be more strongly associated with hypertension. We aimed to determine the association between multiple measurements of the casual urinary Na/K ratio and home hypertension compared with a single measurement. A population-based cross-sectional study was performed in Miyagi Prefecture, Japan. Subjects were over 20 years old and participated in the Tohoku Medical Megabank Project Cohort Study. We targeted 3273 subjects who borrowed home blood pressure (HBP) monitors and urinary Na/K ratio monitors for 10 consecutive days. The association between the urinary Na/K ratio and home hypertension (HBP ≥ 135/85 mmHg or under treatment for hypertension) was examined using multiple logistic regression models. To compare the prediction of home hypertension using multiple measurements with that using a single measurement, we calculated the area under the receiver operating characteristic curve (AUROC). Multiple measurements of the urinary Na/K ratio strongly related to home hypertension were better than 1 or 2 days of measurement (adjusted odds ratio of home hypertension per unit increase in urinary Na/K ratio over 6 days: 1.13-1.15). The AUROC of the urinary Na/K ratio measurement for home hypertension was stable after 5 days (AUROC = 0.779). In conclusion, multiple measurements of the urinary Na/K ratio are strongly related to home hypertension. This finding suggests that multiple measurements of the urinary Na/K ratio are useful for evaluating home hypertension.

Blood pressure monitor with a position sensor for wrist placement to eliminate hydrostatic pressure effect on blood pressure measurement.

Accurate measurement of blood pressure at wrist requires the heart and wrist to be kept at the same level to avoid the effects of hydrostatic pressure. Although a blood pressure monitor with a position sensor that guides appropriate forearm angle without use of a chair and desk has already been proposed, a similar functioning device for measuring upper arm blood pressure with a chair and desk is needed. In this study, a calculation model was first used to explore design of such a system. The findings were then implemented into design of a new blood pressure monitor. Results of various methods were compared. The calculation model of the wrist level from arthrosis angles and interarticulars lengths was developed and considered using published anthropometric dimensions. It is compared with 33 volunteer persons' experimental results. The calculated difference of level was -4.1 to 7.9 (cm) with a fixed chair and desk. The experimental result was -3.0 to 5.5 (cm) at left wrist and -2.1 to 6.3(cm) at right wrist. The absolute difference level equals ±4.8 (mmHg) of blood pressure readings according to the calculated result. This meets the AAMI requirements for a blood pressure monitor. In the conclusion, the calculation model is able to effectively evaluate the difference between the heart and wrist level. Improving the method for maintaining wrist to heart level will improve wrist blood pressure measurement accuracy when also sitting in the chair at a desk. The leading angle of user's forearm using a position sensor is shown to work for this purpose.