Combination therapy is often used for these infections, but selecting the right mix of antibiotics can be difficult because the effectiveness of combinations varies widely between bacterial strains. Instead of relying on empirical or anecdotal treatment choices, iACT tests potential combinations directly against the patient’s bacterial isolate to determine which regimen works best.

Screening up to 180 antibiotic combinations

One of the distinctive features of the iACT approach is its large testing panel. Laboratory experiments can evaluate up to 180 unique antibiotic combinations at clinically relevant concentrations against the patient’s bacteria.

These tests measure how effectively each combination kills or suppresses the bacteria. Because different antibiotics can interact in synergistic, additive, or antagonistic ways, examining many combinations increases the chance of finding a regimen that works against highly resistant strains.

The testing workflow aims to generate actionable results quickly—typically within about 48 hours—so clinicians can adjust treatment while the infection is still actively being managed.

The role of AI and data analysis

Public descriptions of iACT refer to the platform as AI‑powered, reflecting the use of computational analysis to interpret large sets of experimental results and help identify optimal antibiotic combinations.

However, available public sources provide limited detail about the exact algorithms used. What is clear is that the system combines laboratory testing with data analysis to support clinicians in selecting individualized treatment regimens rather than relying solely on standard antibiotic susceptibility tests.

Why personalised antibiotic combinations matter

Multidrug‑resistant infections are difficult to treat because the number of effective antibiotics is shrinking. In many cases, doctors must combine multiple drugs to overcome resistance mechanisms.

Research shows that the success of antibiotic combinations is often highly strain‑specific, meaning a regimen that works for one patient’s infection may fail for another.

By directly testing combinations against the patient’s pathogen, iACT aims to:

• Identify the most effective antibiotic regimen for that specific infection
• Avoid ineffective or unnecessarily toxic combinations
• Improve treatment success in severe drug‑resistant infections

This personalized approach aligns with broader antimicrobial‑stewardship goals—using antibiotics more precisely to preserve their effectiveness over time.

SGH–A*STAR collaboration and commercialization plans

To move the technology beyond research laboratories, Singapore General Hospital and A*STAR’s Diagnostics Development Hub have formed a partnership to translate innovations such as iACT into deployable medical diagnostics.

The collaboration focuses on turning promising clinical research into scalable and licensable diagnostic technologies that can be adopted in Singapore’s healthcare system and potentially by hospitals overseas.

Government announcements note that the partnership aims to convert these innovations into real‑world patient impact, with the iACT platform highlighted as one of the early technologies supported under the initiative.

Why this approach could matter for antimicrobial resistance

Antimicrobial resistance is widely considered one of the major global health threats of the coming decades. As existing antibiotics lose effectiveness, improving how existing drugs are used becomes increasingly important.

Technologies like iACT could help address this challenge by enabling precision antibiotic therapy—matching the right combination of drugs to the exact pathogen causing the infection. If successful and widely adopted, this approach may improve outcomes for patients with resistant infections while reducing reliance on trial‑and‑error prescribing.

While more clinical data and real‑world deployment will determine its long‑term impact, the iACT platform represents a promising example of how laboratory diagnostics, data analysis, and precision medicine can be combined to tackle the growing problem of drug‑resistant bacteria.

Combination therapy is often used for these infections, but selecting the right mix of antibiotics can be difficult because the effectiveness of combinations varies widely between bacterial strains. Instead of relying on empirical or anecdotal treatment choices, iACT tests potential combinations directly against the patient’s bacterial isolate to determine which regimen works best.

Screening up to 180 antibiotic combinations

One of the distinctive features of the iACT approach is its large testing panel. Laboratory experiments can evaluate up to 180 unique antibiotic combinations at clinically relevant concentrations against the patient’s bacteria.

These tests measure how effectively each combination kills or suppresses the bacteria. Because different antibiotics can interact in synergistic, additive, or antagonistic ways, examining many combinations increases the chance of finding a regimen that works against highly resistant strains.

The testing workflow aims to generate actionable results quickly—typically within about 48 hours—so clinicians can adjust treatment while the infection is still actively being managed.

The role of AI and data analysis

Public descriptions of iACT refer to the platform as AI‑powered, reflecting the use of computational analysis to interpret large sets of experimental results and help identify optimal antibiotic combinations.

However, available public sources provide limited detail about the exact algorithms used. What is clear is that the system combines laboratory testing with data analysis to support clinicians in selecting individualized treatment regimens rather than relying solely on standard antibiotic susceptibility tests.

Why personalised antibiotic combinations matter

Multidrug‑resistant infections are difficult to treat because the number of effective antibiotics is shrinking. In many cases, doctors must combine multiple drugs to overcome resistance mechanisms.

Research shows that the success of antibiotic combinations is often highly strain‑specific, meaning a regimen that works for one patient’s infection may fail for another.

By directly testing combinations against the patient’s pathogen, iACT aims to:

• Identify the most effective antibiotic regimen for that specific infection
• Avoid ineffective or unnecessarily toxic combinations
• Improve treatment success in severe drug‑resistant infections

This personalized approach aligns with broader antimicrobial‑stewardship goals—using antibiotics more precisely to preserve their effectiveness over time.

SGH–A*STAR collaboration and commercialization plans

To move the technology beyond research laboratories, Singapore General Hospital and A*STAR’s Diagnostics Development Hub have formed a partnership to translate innovations such as iACT into deployable medical diagnostics.

The collaboration focuses on turning promising clinical research into scalable and licensable diagnostic technologies that can be adopted in Singapore’s healthcare system and potentially by hospitals overseas.

Government announcements note that the partnership aims to convert these innovations into real‑world patient impact, with the iACT platform highlighted as one of the early technologies supported under the initiative.

Why this approach could matter for antimicrobial resistance

Antimicrobial resistance is widely considered one of the major global health threats of the coming decades. As existing antibiotics lose effectiveness, improving how existing drugs are used becomes increasingly important.

Technologies like iACT could help address this challenge by enabling precision antibiotic therapy—matching the right combination of drugs to the exact pathogen causing the infection. If successful and widely adopted, this approach may improve outcomes for patients with resistant infections while reducing reliance on trial‑and‑error prescribing.

While more clinical data and real‑world deployment will determine its long‑term impact, the iACT platform represents a promising example of how laboratory diagnostics, data analysis, and precision medicine can be combined to tackle the growing problem of drug‑resistant bacteria.