WellCure Pitch Deck Notes
WellCure Pitch Deck Notes (Comprehensive Summary)
The clinical problem
- Postoperative period is a critical recovery phase with high risk for deterioration.
- Key statistics (source: Rowland BA, Motamedi V, Michard F, et al. Br J Anaesth. 2024;132:519–27):
- >50\% of fatalities could be avoided after surgery with better monitoring.
- Up to 30\% of surgical patients face serious complications.
- Clinicians currently rely on spot checks; there is no tool for continuous, real-time predictive monitoring.
- Early perioperative risk identification can prevent most serious adverse outcomes.
- Context: This problem is framed as a readiness/need for continuous monitoring with predictive capabilities.
The impact (market and human impact)
- Global/postoperative landscape:
- 50{,}000{,}000\,\text{patients} worldwide suffer serious post-surgical complications each year.
- Mortality risk linked to delayed detection:
- Up to 33\% increase in mortality with delayed detection of post-surgical deterioration.
- Economic impact in the United States:
- Annual cost of post-surgical complications: €43{,}000{,}000{,}000\$-range? or more clearly: \$43-\$73\,\text{B} per year.
- These figures underscore a large-scale opportunity for continuous monitoring and early intervention tools.
- Relevance to healthcare systems: significant potential savings in hospital stays and ICU utilization when deterioration is detected earlier.
The solution (WellCure / Callisia approach)
- Callisia’s solution aims to address the clinical problem with:
- Wireless continuous monitoring
- Predictive models for early risk detection
- Outcome focus: reduce time to detection, preempt crises, and minimize unnecessary ICU transfers.
Technology and product architecture
- Software layer:
- AI-based platform for predictive analytics and alerting.
- Source cited: Slight, Sarah P. et al. ROI study on continuous monitoring systems (Critical Care Medicine 2014) [context for ROI of continuous monitoring].
- Hardware layer:
- LEAF smartband equipped with biosensors.
- Provides continuous vital signs data capture to feed AI models.
- Data and systems integration:
- RAW high-frequency data to support AI algorithms.
- Data capture rates:
- ECG up to 500\,\text{Hz}
- PPG at 100\,\text{Hz}
- Health indicators monitored include:
- Cardiovascular health and autonomic nervous system activity
- Stress levels
- Respiratory and cardiovascular health
- Arrhythmia detection
- Blood volume variations and vascular health
- AI/ML capabilities:
- Real-time AI alerts for immediate anomaly detection
- Ability to identify trends and potential crises before symptoms appear
- AI-based personalized alerts tailored to each patient, as opposed to generic thresholds
- Data infrastructure:
- RAW data is ingested and stored; feature extraction performed upstream
- Streaming data pipelines: Apache Kafka (high-frequency data) and related processing
- User interface:
- Dashboard for clinicians (web/mobile/desktop)
- Graphical visualization of AI model outputs and patient risk
- In-house hardware development:
- Clinical-grade biosensor hardware with a personalized board
Predictive models and value proposition
- Predictive capabilities vs traditional monitoring:
- Continuous monitoring (24/7 vitals) vs periodic checks by staff
- Real-time AI alerts vs delayed manual intervention
- Early crisis prediction (trends before symptoms) vs reactive care
- Reduced ICU transfers through preemptive intervention vs late detection leading to ICU transfer
- AI-based personalized alerts vs generic thresholds
- Synthetic data and model development:
- Predictive models include synthetic data simulations inspired by research on patient deterioration to augment real data.
Comparative advantages (Callisia vs traditional monitoring)
- Real-time monitoring and alerts:
- Callisia: ✔ Continuous 24/7 tracking of patient vitals
- Traditional: ✖ Periodic checks by staff
- Immediate anomaly detection:
- Callisia: ✔ Real-time AI Alerts
- Traditional: ✖ Delayed detection
- Early crisis prediction:
- Callisia: ✔ Predicts crises early (before symptoms appear)
- Traditional: ✖ Reacts when symptoms worsen
- ICU transfer reductions:
- Callisia: ✔ Reduces ICU transfers via preemptive intervention
- Traditional: ✖ Late detection leads to ICU transfers
- Personalization of alerts:
- Callisia: ✔ AI-based personalized alerts
- Traditional: ✖ Generic thresholds for all patients
- Note: The comparison is framed as synthetic vs traditional monitoring, emphasizing proactive care enabled by AI.
Technology stack and data workflow (WellCure / Callisia)
- Storage, processing, and GUI components
- Data pipeline:
- Raw data -> DB -> Streaming via Apache Kafka (High Frequency) -> Extracted features -> AI models
- Multi-LEAF devices (devices on patient)
- General database integration for patient data
- GUI: Dashboard, AI models visualization accessible on Web, Mobile, Desktop
Hardware and clinical-grade sensors
- In-house built personalized hardware device for clinical use
- Clinical-grade biosensor ensemble on a personalized board
- Emphasis on safety, interoperability, and clinician usability
Competitive landscape and market metrics
- Competitive map indicators (IT context):
- TAM: 4.7\text{ B} (EU)
- SAM: 468\text{ M€} (IT)
- SOM: 4\text{ M€} (IT)
- Beach Head: 700{,}000 (IT)
- Source for market sizing: Future Market Insights (continuous wireless patient monitoring market)
Maturity, personalization, and usability
- Maturity: Callisia positions as a mature, validated technology with continuous monitoring capabilities.
- Personalization: Emphasizes customization and tailoring to a wide range of user needs.
- User friendliness: Focus on ease of use for clinicians and patients.
- Customization: High degree of adaptability to different clinical workflows and settings.
Team and governance
- Core team and co-founders:
- Dianel Ago – CEO, Data & AI
- Alessio Ancillai – CFO, Finance & risk management
- Simone Murazzo – CTO, Software development
- Jonathan Montomoli – MD, PhD
- Floriano Bonfigli – Dott. Ing. MSc, President
- Prof.ssa Claudia Diamantini – CdA, DII - UNIVPM
- Prof. Domenico Potena – CRO; R&D, DII - UNIVPM
- Ing. Fernando Negozi – Vice-President, CdA, Eletica SRL
- Rifat Seferi – CoFounder, CdA, LIS SRL
- Board and advisory roles reflect collaboration with university and industry partners.
Roadmap (timeline highlights)
- 2023: MVP ready; EU/USA Series A fundraising target of €20M; Potential exit; LEAF hardware development; Company registration. Pre-seed milestones include €130k (✅).
- 2024: LEAF hardware development continues; company registration completed; further pre-seed activities.
- 2025: Pilot projects; development of predictive models.
- 2026: Seed round targeted (€5M value) and funding needs (€1M specified).
- 2028–2030: Longer-term milestones referenced but not detailed in the source text.
Collaborative ecosystem and partnerships
- AIMED-EU & partner networks for advancing AI-driven care across Europe.
- Notable collaborators listed (illustrative): Vidavo, Steinbeis Europa Zentrum, Aristotile, University of Marche, University of Thessaloniki, Ivano-Frankivsk National Medical University, IRCCS INRCA, E EUINNOVA, ARIF/AR… (note: the source text includes a dense list with acronyms and affiliations; these represent a broad European innovation ecosystem participation)
- The collaboration underscores regulatory, cybersecurity, and innovation support for deploying AI-enabled medical devices in Europe.
- Brand site: www.callisia.health
- Contact email: tech@callisia.health
Notable sources and claims to verify
- Rowland BA, Motamedi V, Michard F, et al. Br J Anaesth. 2024;132:519–27 – cited for clinical risk statistics.
- Slight, Sarah P. et al. The return on investment of implementing a continuous monitoring system in general medical-surgical units. Critical Care Medicine 2014 – cited for ROI context of continuous monitoring.
- Market sizing source: Future Market Insights report on wireless patient monitoring (cited for TAM/SAM/SOM context).
Quick reference (key numbers in LaTeX)
- Postoperative fatalities potentially avoidable: >50\%
- Serious post-surgical complications: 30\%
- Global post-surgical complications: 50{,}000{,}000
- Mortality increase with delayed detection: 33\%
- U.S. post-surgical complication costs: €43{,}000{,}000{,}000\text{ to }€73{,}000{,}000{,}000 \text{ or }\$43-\$73\,\text{B}
- ICU stay cost reduction: -€2{,}000/\text{day} per patient
- Hospital stay cost reduction: -€700/\text{day} per patient
- Annual savings (mid-sized hospital): \$6.8\,\text{M}
- Data rates: f{ECG} \le 500\,\text{Hz}; f{PPG} = 100\,\text{Hz}
- Population and market sizing (EU): TAM 4.7\text{ B}; SAM 468\text{ M€}; SOM 4\text{ M€}; Beach Head 700{,}000
- Roadmap financials (selected): Pre-seed €130{,}000; Series A €20{,}000{,}000; Seed €5{,}000{,}000; Post-seed needs €1{,}000{,}000