MedSysB Hospital Assistant

🔮 Revenue Prediction — Next 90 Days (₹ Lakhs)

Predicted revenue for the next 90 days. Blue = actual, Orange = forecast. Shaded band = confidence range — wider means less certain.

💳 Advance Payment Collection (₹ Lakhs)

Advance payments collected from IP patients by year. Low collection = cash flow risk. High unused advances = refund liability.

💰 Monthly Revenue Trend — ₹ Cr

Monthly revenue over time. Look for seasonal dips (Dec–Jan holidays) and overall growth trajectory compared to prior years.

📈 Year-over-Year Growth (%)

Each month's revenue compared to the same month last year. Negative values mean revenue declined. Sustained negatives need management review.

🏛 Revenue by Department — Top 15

Top 15 revenue-generating departments. Bar color indicates department category (Ward, Billing, Pharmacy, etc). Use to identify which clinical areas drive hospital income.

📋 Revenue by Bill Type

Revenue breakdown by bill category (Ward, Pharmacy, Lab, etc). A high Ward share means strong inpatient (IPD) revenue. Hover for exact amounts.

💳 Payment Mode Distribution

How patients pay — Cash, Card, NEFT, Insurance, etc. Growing digital payments indicate modernisation. High cash dependency is a compliance risk.

📈 Net Revenue vs Discounts — Monthly

Net revenue (green) vs discounts given (amber) each month. If discount share exceeds 10% of gross, review discount approval policies.

🔮 Doctor Revenue Prediction (₹ Lakhs)

AI-predicted monthly doctor-attributed revenue. Blue = actual, Orange = forecast with 95% confidence band. Use for doctor incentive budgeting and capacity planning.

🤑 Top 15 Doctors by Revenue (₹ Lakhs)

Doctors generating the most billing revenue. Identifies key revenue contributors for incentive planning and workload balancing.

📈 Doctor Revenue Trend — Top 5 (₹ Lakhs)

Monthly revenue for top 5 revenue-generating doctors. Track consistency, seasonal variation, and growth per doctor.

🏥 IP vs OP Revenue Split

Revenue by category: Ward = Inpatient, Registration = Outpatient, Lab/Pharmacy/General = shared services. High Ward share = strong IPD revenue.

📈 IP vs OP Revenue Trend (₹ Lakhs)

Monthly IP (Ward) vs OP (Registration) vs shared services revenue. Rising IP share signals stronger bed utilisation and higher-value treatments.

🤑 Doctor-wise IP vs OP Revenue — Top 15 (₹ Lakhs)

Per-doctor revenue split: IP (Ward billing) vs OP+Other. Identify which doctors drive inpatient vs outpatient revenue for resource planning.

🚫 Bill Cancellations & Refunds (₹ Lakhs)

Monthly cancellation and refund amounts. Rising trends may indicate billing errors, patient dissatisfaction, or policy issues needing review.

💊 Pharmacy GST Breakdown (₹ Lakhs)

Yearly pharmacy billing with GST/tax component. Compare gross vs net to assess tax burden and discount policies on pharmacy revenue.

🔬 Lab Revenue Trend (₹ Lakhs)

Monthly lab-specific revenue from billing. Track lab contribution to total hospital revenue. Dips may indicate equipment downtime or reduced referrals.

🔮 Patient Footfall Prediction

Predicted daily patient visits through Dec 2026. Blue = actual visits, Orange = AI forecast. Use for staffing and capacity planning.

🔮 Bed Demand Prediction

Predicted daily bed admissions. Rising trend means more beds needed. Plan ward expansion or faster discharge protocols.

🔮 30-Day Readmission Rate (Predicted)

Percentage of patients readmitted within 30 days of discharge. Target: below 15%. Rising trend signals premature discharge or inadequate follow-up care.

📅 Daily Patient Census

Daily patient footfall (OPD + IPD). Peaks may indicate seasonal illness outbreaks or festival-related injuries. Dips on weekends/holidays are normal.

👥 Outpatient vs Inpatient Visits — Monthly

Monthly breakdown: Outpatient (OPD) vs Inpatient (IPD) visits. A rising IPD share may indicate increasing disease severity in the catchment area.

👤 Age Distribution by Gender

Patient count by age group and gender. Use to plan specialty departments — high Pediatric counts justify a children's wing; high Senior counts need geriatric services.

👥 Gender Distribution

Male vs Female patient distribution. Significant gender skew may indicate gaps in gender-specific services (e.g., Gynecology, Urology).

🛏️ Bed Occupancy by Ward — Live

Current bed occupancy per ward. Red (>90%) = overcrowded, needs immediate discharge review. Amber (80-90%) = monitor closely. Green (<80%) = can accept transfers.

🌎 Where Patients Come From — Top 20 Cities

Where patients travel from — top 20 cities. High-volume distant cities indicate demand for satellite clinics. Nearby cities with low counts need outreach campaigns.

🔄 New vs Returning Patients

New patients (first visit ever) vs returning patients each month. Declining new patients may signal reputation issues or competition. Rising returning patients = good retention.

👥 Patient Segmentation

Patient groups by visit frequency. Frequent visitors may need chronic disease management programs. Single-visit patients may need follow-up reminders.

🛌 Length of Stay by Ward

Average length of stay (in days) per ward. Wards significantly above hospital average may have discharge bottlenecks or complex case mix. Target: reduce without readmission increase.

🔮 Lab Test Volume Prediction

Predicted daily lab test volume. Use for reagent stock planning, technician shift scheduling, and equipment maintenance windows.

🔬 Daily Lab Test Volume

Daily number of lab tests processed. Sudden drops may indicate analyser downtime or reagent stockouts. Spikes may coincide with outbreaks.

⏱ Turnaround Time by Sample Type

Average turnaround time (hours) from sample collection to result, by sample type. Samples exceeding 24h delay treatment decisions — escalate to lab manager.

🩺 Top Ordering Doctors — Lab

Doctors who order the most lab tests. Unusually high ordering may indicate over-investigation. Compare with diagnosis complexity before concluding.

📊 Lab Results by Department

Lab test results generated per department. Departments generating the most results need proportional lab technician allocation and faster TAT guarantees.

⏱ Sample Collection TAT Distribution

Distribution of time from blood draw to lab receipt. Samples delayed >2h may have degraded quality. Work with phlebotomy and transport teams to reduce delays.

🔮 Pharmacy Revenue Prediction (₹ Lakhs)

Predicted pharmacy revenue. Declining trend may signal formulary changes, generic substitution, or falling patient volumes. Align procurement accordingly.

📈 Expiry Value Projection

Projected value of medicines expiring each month. Peaks need advance planning — negotiate vendor returns, accelerate dispensing of near-expiry stock (FIFO).

🔮 Prescription Volume Prediction

Predicted daily prescription count. Use for dispensing counter staffing, pharmacist shift planning, and drug procurement pipeline scheduling.

📦 Stock Value by Department

Current stock value by department, split by status. Red (Out of Stock) = critical reorder needed. Amber (Below Reorder Level) = place order soon. Green (Adequate) = no action.

📊 Stock Status Distribution

Proportion of pharmacy items by stock status. Target: >80% in Adequate. If Out of Stock exceeds 10%, review procurement lead times and reorder points.

⚠️ Expiry Risk by Alert Level

URGENT = expiring <30 days. Prioritize FIFO dispensing or return-to-vendor.

🚚 Top 15 Vendors by Order Value

Top 15 vendors by total purchase order value. If top 3 vendors account for >50% of spending, supply chain is vulnerable to single-vendor disruptions. Diversify.

✅ Vendor Net Payments — Top 15 (₹ Lakhs)

Net payments made to top 15 vendors. Compare with order values to identify vendors with high discounts or credit notes. Use for vendor performance reviews.

🚚 Procurement Fulfillment — Top 15 Vendors

Vendor order fulfillment rate (% of ordered quantity received). Low fulfillment = supply chain risk. Compare with net value to assess vendor reliability.

🔮 Surgery Volume Prediction

Predicted monthly surgery count. Use for OT (Operation Theatre) scheduling, surgical supply procurement, and surgeon duty roster planning.

🔮 Birth Volume Prediction

Predicted monthly birth count. Rising births require more delivery rooms, neonatal equipment, and NICU beds. Coordinate with Obstetrics and Paediatrics.

🔮 Doctor Workload Prediction

Average patient visits per doctor per month. Rising workload without new hires = doctor burnout and patient safety risk. Target: <1500 visits/doctor/month.

🔮 Emergency Surgery Ratio (Predicted)

Percentage of surgeries that are emergency (unplanned). Rising emergency ratio signals gaps in early diagnosis or preventive care. Target: below 40%.

🔮 Surgery Volume by Specialty

Surgery volume by specialty (Obstetrics, General, Ortho, etc). Solid lines = actual, Dashed = forecast. Diverging trends help allocate OT time and specialist hiring.

🔩 Surgery Volume Trend — Monthly

Total surgeries performed each month. Dips may indicate scheduled OT maintenance, surgeon leave, or seasonal patterns. Compare with patient admission trends.

👶 C-Section Rate Trend (%)

Monthly C-Section rate as % of all deliveries. WHO recommends 10–15%. Rates above 20% warrant clinical audit to rule out unnecessary interventions.

🩹 Top 20 Diagnoses

Most common diagnoses across all patients. Use to plan specialist hiring, equipment procurement, and clinical protocol development for high-burden conditions.

🩺 Doctor Performance — Top 20

Top 20 doctors by patient visit count. Extremely high volumes indicate potential burnout risk. Consider redistribution, hiring support staff, or adjusting schedules.

✅ Discharge Compliance Trend (%)

Monthly discharge summary completion rate. Target: 95%+. Gaps indicate documentation bottlenecks — consider discharge summary templates or dedicated documentation staff.

👶 Birth Rate Trend — Delivery Modes

Monthly deliveries by mode: Normal (FTND), LSCS (C-Section), Forceps. 33K+ birth records. Rising LSCS share warrants clinical audit per WHO guidelines.

📈 Daily Scan Volume

Daily ultrasound/scanning volume over time. Track seasonal patterns and growth in imaging demand for equipment procurement and radiologist staffing.

📡 Scan Type Distribution

Breakdown by scan type: Pelvic Ultrasound, Fetal Heart, TIFFA Anomaly, Doppler, etc. High-volume types need dedicated equipment and trained sonographers.

🩺 Top Scanning Doctors

Doctors performing the most scans, by scan type. Use for workload balancing, quality audits, and identifying training needs for new scan modalities.

🔮 Scan Volume Forecast — AI

AI-predicted daily scan demand through Dec 2026. Plan equipment procurement, sonographer hiring, and appointment scheduling. Confidence band shows prediction uncertainty.

✅ Scanning Data Active: 91,635 scan records across 25 types (2013–2026) from 34 bronze source tables. AI Forecast loads in background (1–3 min).

🔮 30-Day Readmission Rate Forecast

AI-predicted readmission rate trend. Blue = actual, Orange = forecast. Target: below 15%.

👥 Risk by Age Group

Readmission risk % by age group. Seniors and neonates typically have higher rates.

📊 Risk by Patient Segment

Patient count by segment (Loyal, At-Risk, New, etc). Higher visits = higher risk.

🏫 Readmission by Department

Departments with highest readmission %. Focus retention efforts here.

⚤ Risk by Gender

Gender distribution among high-risk patients.

🤖 ML Readmission Predictions

Top 30 patients scored by ML model. Risk score 0-1 (higher = more likely to readmit within 30 days).

📊 LOS Distribution

Visit count and average bill by length of stay range. Longer stays drive higher costs.

📈 Average LOS Trend by Year

How average and median LOS have changed over the years.

🏫 LOS by Department (Top 15)

Departments with longest average stays. Target: reduce without affecting outcomes.

👥 LOS by Age Group

Average stay duration by patient age group.

💰 LOS vs Average Bill

How bill amount scales with length of stay.

🤖 ML LOS Predictions

Recent patients with predicted vs actual length of stay from ML model.

Loading Executive Briefing...

💰 Revenue Recommendations ai_gen

👥 Patient Flow Alerts ai_gen

💊 Pharmacy & Inventory Alerts ai_gen

🩸 Clinical Quality Alerts ai_gen

Smart Functions

🎯 Department Risk Tiers ai_classify

🧑 Diagnosis Intelligence ai_sentiment + ai_similarity

Hospital Assistant

Chat History

MedSysB AI Assistant