Singapore Health Sciences Authority (HSA) has granted approval for Respiree’s 1Bio AI-Acute toolbox, classifying it as a Class B software-as-a-medical device (SaMD).
The toolbox is intended to assist healthcare professionals in detecting acute inpatient deterioration through machine learning (ML) and AI models.
Go deeper with GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
Respiree noted that the toolbox is designed to deliver higher precision notifications for acute deterioration compared to existing standards of care.
This leads to fewer false alerts and clinical support for healthcare teams.
The system utilises vital signs such as respiratory rate, pulse rate, systolic blood pressure, and oxygen saturation, all recorded at the bedside.
These are used for the generation of a probability score, which helps clinicians to determine whether a patient may need additional monitoring.
US Tariffs are shifting - will you react or anticipate?
Don’t let policy changes catch you off guard. Stay proactive with real-time data and expert analysis.
By GlobalDataA higher probability score from the 1Bio AI-Acute toolbox indicates a greater likelihood that the patient could need further monitoring or intervention, providing clinicians with an indication of the general physiological state of the patient.
Healthcare professionals can access the 1Bio AI-Acute toolbox via the company’s 1Bio platform, which, along with the RS001 wearable device, has also secured regulatory approval.
With this development, the 1Bio AI-Acute toolbox, the 1Bio platform, and the RS001 wearable have all secured approval from the HSA.
Following this approval, Respiree is preparing to seek regulatory clearances for the 1Bio AI-Acute toolbox in other Asia-Pacific, Australia and New Zealand regions, along with the US, over the coming months.
Respiree founder and CEO Dr Gurpreet Singh said: “Current early-warning scores that rely on threshold-based methods often suffer from low precision, leading to a high number of alarms and notifications.
“Advanced AI-driven machine learning models have the potential to deliver significantly greater precision, reducing unnecessary alerts / notifications, thus enabling healthcare professionals to better focus their time on delivering quality patient care.”
