Pharmacy Analytics

When consumption and procurement drift apart, hospitals either tie up working capital in slow stock or face stock-outs on high-use items. Most teams reconcile the two in monthly meetings, long after the imbalance affected patient care or cash.

FireAI joins dispensing and purchase feeds so you see consumption versus procurement by drug, category, and store in one place. The system highlights variance bands, seasonality, and sudden shifts so procurement can align orders with real usage patterns instead of last year’s averages.

What FireAI tracks:

• Consumption units versus procured units by week and month
• Variance percentage by drug and therapeutic class
• Top over-procured and under-procured SKUs linked to departments
• Trend lines for high-cost injectables and chronic medications

How FireAI solves the problem: A 280-bed hospital in Ahmedabad used FireAI to compare antibiotic consumption with procurement for three months and found cephalosporin orders running 22% above dispensing in two wards while another class sat 15% under-procured. Adjusting the next purchase cycle and ward-level par levels freed roughly nine days of inventory cash without a single stock-out on tracked items.

What you can ask FireAI:

• "Show consumption versus procurement for antibiotics last 90 days"
• "Which drugs had the largest positive variance between purchased and dispensed units this month?"
• "Compare ICU procurement to actual consumption for high-cost injectables"

Formularies only work when prescribing and issuing stay aligned. In busy hospitals, off-formulary orders creep in through brand preference, emergency overrides, or outdated favorites. Without department-level visibility, pharmacy cannot target education or auto-alerts where they matter.

FireAI matches prescribed molecules and issued items to your approved formulary and computes formulary compliance by department, doctor group, and drug class. You see trends, outliers, and the financial impact of substitutions so clinical pharmacy can focus rounds and approvals where non-compliance clusters.

What FireAI tracks:

• Formulary compliance rate by department and rolling 30/90 days
• Off-formulary orders by molecule and cost impact
• Override reasons where captured in HIS
• Compliance trend after formulary updates or new NLEM cycles

How FireAI solves the problem: A teaching hospital in Pune used FireAI to segment formulary compliance by department and found Orthopaedics at 76% versus a hospital target of 90%. Drill-down showed concentrated off-formulary use in two NSAID brands. A combined EMR alert and one CME session lifted Orthopaedics to 88% in eight weeks and reduced equivalent drug spend in that segment by an estimated 11%.

What you can ask FireAI:

• "What is formulary compliance by department this quarter?"
• "List top off-formulary molecules in Cardiology by cost"
• "Show compliance trend after the July formulary revision"

Expiry losses are predictable if you see them early. Many hospitals still discover risk during physical stock counts, when near-expiry drug tracking is too late for transfer, return, or consumption campaigns. Write-offs then show up as a lump in finance with little operational feedback.

FireAI runs continuous drug expiry tracking on batch-level data from your pharmacy system. It surfaces near-expiry alerts by value and days-to-expiry, ties expected write-offs to departments or stores where slow movement started, and tracks actual write-off versus avoided loss after interventions.

What FireAI tracks:

• Stock value within 30, 60, and 90 days of expiry
• Near-expiry alerts by category and location
• Write-off value and trend month on month
• Recovery rate from returns, transfers, or usage drives

How FireAI solves the problem: A multi-site chain linked FireAI to central and satellite pharmacies and cut monthly write-offs from near-expiry stock by prioritizing inter-store transfers for batches flagged at 75 days. Pharmacy leads saw which department had ordered surplus and could approve transfers before local expiry, improving recovery on tracked lines by a double-digit percentage in two quarters.

What you can ask FireAI:

• "What is the value of stock expiring in the next 60 days by store?"
• "Show write-off trend for the last six months"
• "Which molecules drove near-expiry alerts in ICU last month?"

Inventory days for medicines vary widely by category: IV fluids turn fast while specialty injectables can sit for months. Without category-level inventory days, finance sees one stock figure and pharmacy cannot explain which buckets tie up capital or risk obsolescence.

FireAI calculates days of inventory by drug category using on-hand value and trailing consumption. You can compare categories, stores, and time periods, and slice by ABC class so procurement adjusts safety stock and reorder points with evidence.

What FireAI tracks:

• Inventory days by drug category and hospital store
• Trend lines for high-value and high-turn categories
• Days of cover versus target bands you define
• Correlation with expiry risk and slow-mover lists

How FireAI solves the problem: A corporate hospital group benchmarked inventory days by drug category across two cities and found oncology support drugs at 94 days at one site versus 58 days at a peer site with similar case mix. Consolidating ordering for that category and sharing a central buffer reduced days by 19 at the slower site within one quarter without affecting service levels.

What you can ask FireAI:

• "What are inventory days by drug category this month?"
• "Which categories exceed 60 days cover at main pharmacy?"
• "Show inventory days trend for high-cost injectables"