Health Science Authority (HSA) released a reference draft guideline on the risk classification of Standalone Medical Mobile Applications and the Qualification of CDSS. This is taken from the IMDRF’s Framework for SaMD. The guideline shows the HSA’s current policy stance and practice and should not be confused as a new regulatory control on SaMD and CDSS.

The risk classification framework must take the following into consideration:

• - The significance of the information provided by the standalone mobile application,
• - The state of the patient’s healthcare situation or condition, and
• - GN – 13 Guidance on Risk Classification

Risk Classification of Standalone Medical Mobile Applications 

SaMDs will be assessed to decide whether to treat or to diagnose the condition. They can also be used to aid in the treatment/diagnosis, triage, or identify early signs of a condition. Moreover, they can also be used to inform the patients of the options to treat, diagnose, or prevent the condition. However, in cases wherein the condition is critical, the SaMD information will only be considered if the type of condition is life-threatening, the target population is fragile, and is intended for specialized trained users. This also includes serious (however, the target population is not fragile compared to critical), and non – serious conditions. Below is the summary of the risk classification for such:

State of Healthcare Situation or Condition	Significance of Information provided by SaMD to Healthcare Decision
	Treat or Diagnose	Drive Clinical/Patient Management	Inform Clinical/Patient Management
Critical	Class C	Class C	Class B
Serious	Class C	Class B	Class A
Non – Serious	Class B	Class A	Class A

SaMDs will be classified as Class B if their intended use is to measure, image, or monitor a physiological process.

Below are some examples of risk classification of some MDs using the table above as a guide:

Medical Device Intended Use	Significance of Information	State of Healthcare Situation or Condition	Risk Class
Detection of early signs of sleep apnoea	Drive management	Non – serious	Class B
Identification of irregular moles that indicate increased risk of melanoma	Drive management	Serious	Class B
Diagnosis of heart arrhythmias	Drive management	Serious	Class B
Therapy for patients with substance use disorder	Drive management	Serious	Class B
Used for analysis of skin lesion images in the classification of malignant and benign lesions	Drive management	Serious	Class B
Used for analysis of vital signs readings to triage Major Adverse Cardiac Event (MACE)	Drive management	Critical	Class C

Risk Classification of Clinical Decision Support Software (CDSS)

CDSS is standalone software that can perform a variety of functions in order to support clinical practice and patient management. However, not all CDSS in the market are MDs and this document intends to clarify the qualification and identification of such devices.

As with any other MDs, the intended use of the CDSS must be taken into account. If it meets the definition of the intended use of MDs as per the First Schedule of the Health Products Act (HPA), then it should be regulated by the HSA. They will also be regulated if they are intended for medical purposes, such as investigation, detection, diagnosis, prevention, monitoring, treatment, or management of any medical condition. They will not be regulated if the intended use does not meet the definition in the First Schedule of HPA, or if the CDSS is intended solely for the display or printing of medical information.   

CDSS will be classified as Class A if they meet all the criteria below:

• - It is intended to analyze medical information
• - It is not intended to acquire, process, or analyze a medical image
• - It is intended only to support healthcare professionals in making clinical decisions
• - It is not intended to replace the clinical judgment of a healthcare professional

Examples of Class A CDSS are:

• - Analysis of patient’s symptoms and test results against accepted clinical guidelines and to recommend most appropriate surgical action
• - Analysis of patient’s DNA sequence
• - Aid in the interpretation of variants of genomic profiling

Examples of Non – MD CDSS are:

• - Patient appointment and surgery schedule management
• - Patient billing
• - Simple medical information calculator
• - Laboratory Information Management System (LIMS)/Laboratory Information System (LIS)
• - Clinical decision flow with no analysis
• - Information that displays about healthcare products
• - Tracking of end users’ diet
• - Diary function
• - Electronic Health Record
• - Medical information
• - Teleconsultation/telecollaboration
• - Survey or chat-based triaging
• - General wellness
• - Calendar tools for menstrual cycles and IVF treatment cycles
• - Drug dosage calculator
• - Library function

Other examples of CDSS are:

• - Analysis of raw DNA sequencing data

Reference:

Consultation on Regulatory Guidelines for Classification of Standalone Medical Mobile Applications (SaMD) and Qualification of Clinical Decision Support Software (CDSS)

Guidelines on Risk Classification of Standalone Medical Mobile Applications (SaMD) and Qualification of Clinical Decision Support Software (CDSS)