Patients in this arm will use AI-enhanced point-of-care ECG device to monitor their serum potassium level every 3 days for 6 months in addition to their regular outpatients follow-up. If ECG device detected hyperkalemia was reported, more intensive monitoring, education on diet or offer of making outpatient appointment, as appropriate, will be provided.

Patients in this arm will just follow their regular outpatients care without additional intervention.

A mobile AI-enhanced electrocardiogram device will be used to help patients monitor hyperkalemia. The device, shaped like a stick of chewing gum, collects time-series data of electrocardiogram lead I through two electrodes. Deep convolutional neural network algorithm can read the data and generated categories of plasma potassium (<5 mmol/L, 5 - <5.5 mmol/L, 5.5 - <6.0 mmol/L and ≥ 6.0 mmol/L). Study participants receive the device after randomization. The staff establishes a WeChat group for each participant and reminds them to monitor plasma potassium every 3 days. When the detected plasma potassium category falls in 5 - <5.5 mmol/L, they will be reminded to watch diet and to verify plasma potassium again. More intensive reminding (once daily) will be sent if plasma potassium category falls in 5.5 - <6.0 mmol/L or ≥ 6.0 mmol/L. An extra outpatient appointment will also be made as soon as possible for the patients when their detected plasma potassium category is ≥ 6.0 mmol/L.

The serum potassium should be the laboratory measured one, which is obtained in the 3(±1) month and 6(±1) month follow-up in outpatients visit.

The serum potassium should be the laboratory measured one, which is obtained in the 3(±1) month and 6(±1) month follow-up in outpatients visit.

We collect incidence of serum potassium ≥ 5.0 mmol/L after the intervention period to see whether there is still a gap between the original intervention and control groups with the latter one having obtained the device.