One suite for the patient's journey: before harm, through the acute event, and into recovery.
PARIS AI, the Polypharmacy Advanced Risk Intelligence System, is a clinical decision-support suite in three components. PARIS AI Poly addresses medication risk, PARIS AI AEP gives advance warning of acute events across fourteen clinical domains, and PARIS-Ai Rehab follows recovery after the acute phase.
Delivered as software as a medical device and built to clinical evidence standards. The suite is designed to sit in one clinical workflow with SMedRx3, MDY's prescription and adherence platform.
Three components, one suite
Each component is a product in its own right; together they cover the patient journey from medication risk, through the acute event, to recovery.
PARIS AI Poly
PolypharmacyPolypharmacy risk intelligence for people with multiple conditions and concurrent medicines. Built on regulatory adverse-event evidence, it gives the clinician a single actionable risk tier with a defensible recommendation.
- Medication review and optimisation
- Risk stratification in complex polypharmacy
PARIS AI AEP
Acute Events PreventionAdvance warning that a patient's condition is heading for a clinically defined threshold, and evidence of stability when it is not. One engine configured to fourteen clinical domains. Also referred to as PARIS AI ACUTE.
- Fourteen clinical domain applications, 106 use cases
- Featured product: PARIS AI Sepsis AEP
PARIS-Ai Rehab
RehabilitationRehabilitation trajectory monitoring for post-acute care: recovery tracked across eleven rehabilitation pathways and five functional domains, with setbacks identified before they occur.
- Post-stroke, cardiac, post-surgical and complex medical pathways
- Timing of intervention across recovery
One engine that warns before the threshold, across acute care
PARIS AI AEP reads the observations hospitals already record and gives care teams advance warning that a patient's condition is heading for a clinically defined threshold: the point at which a treatment decision, an escalation or a transfer becomes necessary. When a patient is confirmed stable, the same engine gives evidence to step care down safely. It is configured to each clinical specialty as a domain application; the first to reach product form is Sepsis and Critical Care, delivered as PARIS AI Sepsis AEP.
Cardiovascular and Cardiology
Cardiac intensive care, cardiac surgery and post-arrest pathwaysWarns of haemodynamic deterioration in patients with cardiogenic shock, decompensating heart failure and post-operative instability, so that vasopressor initiation, mechanical support and step-down decisions can be planned rather than reacted to.
8 use cases
- Cardiogenic shock: pre-emptive detection and stage transition prediction
- Acute heart failure decompensation in the cardiac ICU
- Post-cardiac surgery ICU monitoring
- Haemodynamic instability across the cardiac care continuum
- Cardiac ICU mortality trajectory detection
- Cardiovascular research and evidence generation for precision cardiology
- Post-cardiac arrest syndrome: ICU haemodynamic trajectory
- Acute pulmonary embolism: haemodynamic trajectory prediction
Diabetes, Endocrinology and Metabolism
Endocrine emergencies and inpatient diabetes care, from the ICU to the general wardWarns ahead of glucose and the physiological markers of endocrine crisis reaching treatment thresholds, supporting earlier intervention in diabetic ketoacidosis, thyroid storm and adrenal crisis, and safer glycaemic management and discharge on the wards.
8 use cases
- Diabetic ketoacidosis and hyperglycaemic hyperosmolar state
- Thyroid storm and hyperthyroid crisis
- Adrenal crisis and cortisol emergency
- Inpatient glucose monitoring and glycaemic management
- Metabolic cardiovascular disease
- Hypoglycaemia prevention in vulnerable populations
- Steroid-induced hyperglycaemia in the ICU
- Sodium dysregulation: SIADH and diabetes insipidus
Oncology
Chemotherapy, transplant and cellular therapy pathwaysFor cancer patients, whose immunosuppression masks the usual warning signs of deterioration. Gives early trajectory warning and the stability evidence needed to discharge or step down immunocompromised patients with confidence.
7 use cases
- Febrile neutropenia and neutropenic sepsis
- Chemotherapy toxicity monitoring and cycle management
- Oncology ICU management and unplanned admissions
- Haematological cancer and bone marrow transplant monitoring
- Post-chemotherapy discharge confidence and safe step-down
- Palliative oncology and goals-of-care planning
- CAR-T cytokine release syndrome and ICANS trajectory prediction
Neurology and Neurocritical Care
Neuro-intensive care and stroke servicesWarns before blood pressure, temperature and related parameters leave the target ranges set by neurocritical guidelines, so that neuroprotective intervention can be timed ahead of the crisis.
7 use cases
- Traumatic brain injury: intracranial pressure crisis prevention
- Ischaemic stroke: blood pressure management trajectory
- Haemorrhagic stroke: haematoma expansion and rebleeding prediction
- Status epilepticus: physiological trajectory and seizure burden monitoring
- Post-neurosurgery ICU monitoring
- Meningitis and encephalitis: physiological deterioration monitoring
- Post-cardiac arrest neuroprognostication and trajectory-guided recovery
Sepsis and Critical Care
The general ICU and acute medicineWarns before a septic patient's physiology crosses the thresholds that define septic shock and organ dysfunction, and supports the timing of resuscitation bundles, vasopressor de-escalation, antibiotic stewardship and step-down from intensive care.
7 use cases
- Septic shock: lactate trajectory prediction
- Multi-organ dysfunction syndrome: SOFA score evolution prediction
- Sepsis bundle timing: optimising the first three hours
- Sepsis recovery: vasopressor de-escalation and step-down confidence
- Antibiotic stewardship: procalcitonin-guided de-escalation
- Infection surveillance: predicting nosocomial deterioration
- Sepsis-associated acute kidney injury: early detection and sub-phenotyping
Nephrology and Acute Kidney Injury
Renal pathways in the ICU, on the wards, in transplant follow-up and the catheter laboratoryWarns of progression through the stages of acute kidney injury, the approach of dangerous potassium levels and the need for renal replacement therapy, and extends to longer-horizon prediction of chronic kidney disease progression.
8 use cases
- Acute kidney injury stage transition prediction
- Hyperkalaemia and cardiac arrest prevention
- Urine output as the earliest signal of kidney injury
- Renal replacement therapy timing
- Post-transplant renal monitoring
- Chronic kidney disease progression in non-ICU settings
- Contrast-associated acute kidney injury
- Sepsis-associated acute kidney injury
Haematology and Coagulation
Haematology, transfusion and cellular therapy servicesWarns of coagulopathy, falling platelet counts and haemorrhage before they reach the thresholds that define haemostatic collapse or transfusion need, giving time to prepare blood products and escalate specialist care.
7 use cases
- Disseminated intravascular coagulation: coagulopathy cascade prediction
- Thrombocytopenia: platelet nadir prediction
- Heparin-induced thrombocytopenia: early detection
- Haemorrhage detection: haemoglobin trajectory
- Massive transfusion protocol activation
- Stem cell transplant complications and veno-occlusive disease
- CAR-T cytokine release syndrome and ICANS
Respiratory and ARDS
Respiratory intensive care, ventilation and oxygen therapy servicesWarns ahead of the next severity boundary in respiratory failure, so that proning, ventilator adjustment and escalation can be planned, and confirms readiness for extubation and step-down.
7 use cases
- ARDS severity progression
- Ventilator-induced lung injury prevention
- Weaning and extubation readiness
- COPD hypercapnic respiratory failure
- Pulmonary embolism
- Post-operative respiratory monitoring
- High-flow nasal oxygen and non-invasive ventilation failure prediction
Hepatology and Liver Failure
Liver units and transplant centresWarns before the markers of hepatic decompensation reach the criteria for transplant listing, encephalopathy escalation or organ-failure grading, giving transplant coordinators, hepatologists and intensivists the timing that current scoring systems do not provide.
7 use cases
- Acute liver failure: transplant criteria threshold prediction
- Hepatic encephalopathy: ammonia trajectory
- Cirrhosis decompensation: acute-on-chronic liver failure prediction
- Variceal bleeding: post-haemorrhage monitoring
- Drug-induced liver injury: severity trajectory
- Post-liver transplant monitoring
- Hepatorenal syndrome: kidney injury trajectory
Trauma
Major trauma centres and resuscitation teamsWarns of the progression of haemorrhagic shock and coagulopathy from the moment of arrival, supporting earlier activation of transfusion protocols, the timing of damage-control surgery and the selection of patients for aortic occlusion.
7 use cases
- Haemorrhagic shock: stage transition prediction
- Massive transfusion protocol pre-activation
- Traumatic brain injury: physiological target adherence
- Trauma-induced coagulopathy: the lethal triad
- Damage control surgery: haemostasis confirmation
- Burns: fluid resuscitation and inhalation injury
- REBOA decision support and aortic occlusion trajectory
Pharmacy, Pharmacokinetics and Therapeutic Drug Monitoring
Hospital pharmacy and therapeutic drug monitoring servicesDrug concentrations follow trajectories in the same way as vital signs. The application warns before a drug level reaches a toxic or subtherapeutic threshold and pairs that with the patient's physiological course, adding a temporal layer to the dosing software already in use.
7 use cases
- Vancomycin nephrotoxicity prevention
- Aminoglycoside peak and trough prediction
- Anticoagulation management
- Calcineurin inhibitor monitoring after transplant
- Digoxin toxicity
- Antiepileptic loading and toxicity monitoring
- Opioid patient-controlled analgesia: respiratory depression
Obstetrics and Maternal Critical Care
Maternity units and maternal high-dependency careObstetric emergencies have precisely defined intervention thresholds. The application warns before a woman's blood pressure, haemodynamics or laboratory markers reach them, giving the obstetric team a preparation window for treatment, delivery decisions, haemorrhage management and sepsis recognition.
7 use cases
- Pre-eclampsia: blood pressure trajectory
- HELLP syndrome: biochemical cascade prediction
- Postpartum haemorrhage
- Maternal sepsis differentiation
- Peripartum cardiomyopathy
- Eclampsia prevention
- Obstetric venous thromboembolism and pulmonary embolism
Emergency Medicine and Resuscitation
Emergency departments, ambulance services and resuscitation teamsThe most time-compressed setting in the portfolio. Provides multi-parameter trajectory warning before in-hospital cardiac arrest, during emergency department waits and in overdose and mass-casualty scenarios, and an objective trajectory layer for escalation under Martha's Rule.
7 use cases
- In-hospital cardiac arrest prediction
- End-tidal CO2-guided CPR and return of spontaneous circulation forecasting
- Post-cardiac arrest syndrome
- Emergency department triage: deterioration during the wait
- Overdose and acute poisoning
- Mass-casualty physiological triage
- Martha's Rule: family escalation support
Global Health and Resource-Limited Settings
District hospitals, health posts and outbreak wards in low- and middle-income countriesBecause the platform works from routine bedside observations and needs no laboratory input, it can run on the equipment every facility already has. Covers the infectious, maternal, neonatal and paediatric conditions behind most preventable mortality in these settings, with an offline deployment architecture for tablet and handheld use.
12 use cases
- Malaria: fever trajectory and cerebral malaria
- Dengue and arboviral haemorrhagic fevers
- Typhoid and enteric fever complications
- Tuberculosis-related sepsis and drug-resistant tuberculosis
- Maternal critical care: pre-eclampsia, haemorrhage and sepsis
- Neonatal sepsis and vital-sign monitoring
- Childhood pneumonia and severe acute respiratory infection
- Cholera and acute watery diarrhoea
- Viral haemorrhagic fevers
- Snakebite envenoming
- Bacterial meningitis in the African meningitis belt
- District hospital deployment architecture
Around the suite
Two further MDY innovations inherit or integrate with PARIS AI.
- YOARLYThe wearable form of the PARIS AI AEP engine: graduated warnings from continuous sensor streams, before the crisis.In the portfolio
- SMedRx3Digital prescription, dispensation and adherence, designed to integrate with the PARIS AI suite in the clinical workflow.In the portfolio
Work with PARIS AI
PARIS AI Sepsis AEP is in clinical validation with NHS and university partners. We welcome further partners across the suite and its domain applications. Evidence packs and validation reports are available under NDA.