Episodes
How AI Is Decoding Genetic Variants for Rare Diseases
In this episode of Healthtech Talks, Lucas and Luna explore how artificial intelligence is tackling one of medicine's hardest problems: diagnosing rare genetic diseases. With over 7,000 known rare conditions affecting roughly 300 million people worldwide, patients often wait years for a correct diagnosis. Lucas shares the story of a machine learning model from a major research hospital that analyzes whole-genome sequences in under 24 hours, flagging disease-causing variants with a reported…
How AI Is Personalizing Hospital Discharge Instructions
In this episode, Lucas and Luna explore how artificial intelligence is transforming the way hospitals create and deliver discharge instructions. They focus on a 2026 pilot at a large U.S. health system that used large language models to turn dense medical jargon into plain-language summaries tailored to each patient's literacy level and cognitive state. The conversation digs into the specific problem: traditional discharge paperwork is often written at a college reading level, while the average…
How AI Is Predicting Patient No-Shows
In this episode of Healthtech Talks, Lucas and Luna explore how artificial intelligence is helping hospitals predict which patients are likely to miss their appointments—before they become costly no-shows. They dive into the real-world problem: missed appointments cost the U.S. healthcare system an estimated $150 billion a year, and traditional reminder calls only chip away at the issue. Lucas breaks down the data science behind predictive models, from the surprising predictors (weather…
How AI Is Predicting Hospital-Acquired Infections
Hospitals are fighting a silent enemy: infections patients pick up during their stay. We explore how AI is stepping in to predict these events before they happen, using electronic health records and real-time monitoring. We look at the case of a major health system that cut its catheter-associated urinary tract infection rate by 45 percent using an AI early-warning system. We also discuss the challenges of implementation, from data quality to clinician trust, and what this means for patient…
How AI Is Helping Hospitals Predict Patient No-Shows
Missed appointments cost the US healthcare system an estimated $150 billion a year. In this episode of Healthtech Talks with Fexingo, Lucas and Luna explore how machine learning models are helping hospitals predict which patients are most likely to skip their visits—and what they're doing about it. They walk through one hospital system's pilot program that cut no-shows by 20 percent using a model trained on historical attendance, weather data, and local transit disruptions. The conversation…
How AI Is Predicting Hospital Readmissions Before Discharge
Every year, hospitals face billions in penalties for patients who return within thirty days of discharge. In this episode, Lucas and Luna explore how machine learning models are changing that calculus. They break down the shift from simple risk scores to AI that analyzes a patient's entire electronic health record, including notes, labs, and vitals, to predict readmission risk with striking accuracy. The conversation zooms in on a 2025 study from a large academic medical center that reduced…
How AI Is Mapping the Human Microbiome for Personalized Medicine
In this episode of Healthtech Talks, Lucas and Luna explore how AI is turning the human microbiome into a precise diagnostic tool. They look at the work of companies like uBiome (before its troubles) and the Thryve microbiome testing platform, and they explain how machine learning models are now predicting how individuals will respond to different diets, probiotics, and even cancer treatments based on their gut bacteria. The conversation centers on a specific recent study that used AI to…
How AI Is Keeping Confidence High in Surgical Robots
Surgical robots have been around for decades, but the AI layer is new. In this episode, Lucas and Luna explore how machine learning is making robotic surgery safer and more trustworthy — from real-time tissue tracking on the da Vinci system to the quiet work of predictive maintenance that keeps a robot from failing mid-procedure. They get specific about the numbers: how AI-powered vision systems are improving anastomotic leak detection, how camera motion tracking is cutting tissue damage…
How AI Is Making Hospital Discharge Summaries Safer
When a patient leaves the hospital, the discharge summary is the handoff that can make or break recovery. In this episode, Lucas and Luna unpack how AI is quietly transforming that final document — catching missing medications, flagging unclear follow-up instructions, and even predicting which patients are likely to bounce back within thirty days. They break down a real-world example from an academic medical center where a natural language processing tool cut readmission risk by 18 percent, and…
How AI Is Cutting Hospital Alarm False Alarms
In this special 150th episode of Healthtech Talks, Lucas and Luna shift focus from prediction to prevention: how artificial intelligence is filtering the relentless barrage of monitor alarms that desensitize clinicians and endanger patients. They explore the 'cry wolf' effect, where up to 90 percent of alarms are false, and how machine learning models now analyze waveform patterns to prioritize true emergencies—cutting alarm burden by nearly half in some pilot units. The conversation centers on…
How AI Is Predicting Hospital Bed Demand Before Surges
Hospitals have always struggled with bed shortages, but AI is changing the game. In this episode, Lucas and Luna explore how machine learning models are forecasting patient demand with remarkable accuracy. They dive into a real-world case where a large health system used AI to predict bed occupancy a week in advance, cutting wait times and improving patient flow. From the data sources—admissions, seasonality, weather, even social media trends—to the operational hurdles of integrating AI into…
How AI Is Decoding Sleep Data for Cardiologists
In this episode of Healthtech Talks, Lucas and Luna explore how AI is transforming sleep studies — moving diagnosis from overnight lab stays to wearable sensors and home monitoring. They focus on the case of a 52-year-old patient whose undiagnosed sleep apnea was flagged not by a traditional sleep lab, but by an Apple Watch alert during a routine night. The episode breaks down how machine learning models trained on millions of hours of sleep data can now detect apnea, hypopnea, and even early…
How AI Is Streamlining Organ Transplant Matching
In this episode of Healthtech Talks, Lucas and Luna explore how artificial intelligence is transforming organ transplant matching. They dive into the complexity of the current allocation system, the role of machine learning in predicting organ viability and recipient compatibility, and the ethical considerations of using AI in life-and-death decisions. With a focus on a recent pilot at a major transplant center, they discuss how AI is helping to reduce waitlist times and improve outcomes, while…
How AI Is Predicting Postpartum Depression Before Symptoms Start
In this episode of Healthtech Talks, Lucas and Luna explore how machine learning is spotting postpartum depression risk from electronic health records before symptoms appear. They dive into a 2025 study from Mass General Brigham that used data from over 100,000 births to flag risk months in advance, with an area under the curve of 0.82. They discuss the tricky balance between privacy and prevention, why EHR data is a blunt but powerful tool, and how this could reshape screening in OB-GYN…
AI Is Automating Medical Coding Errors Out of Billing
In this episode of Healthtech Talks, Lucas and Luna explore how AI is quietly transforming medical billing by catching coding errors before claims are submitted. They focus on a 2026 pilot at a mid-sized hospital system where an AI-assisted coding tool reduced claim denials by 18 percent and saved roughly $2.3 million in the first quarter. The conversation digs into the mechanics: how the AI parses physician notes, maps them to ICD-10 codes, and flags ambiguous language that human coders often…
How AI Is Decoding Physician Notes at the Point of Care
In this episode of Healthtech Talks, Lucas and Luna explore the quiet revolution happening inside the electronic health record: AI that reads unstructured physician notes and turns them into structured, coded data in real time. They examine the technology behind ambient clinical intelligence, the shift from scribes that listen to systems that understand, and the impact on diagnostic accuracy, billing compliance, and physician burnout. Using the example of a large health system that implemented…
How AI Is Making Clinical Trial Recruitment Fairer and Faster
Clinical trials have a hidden bottleneck: finding the right patients. More than eighty percent of trials fail to hit their enrollment deadlines, and the patients who do get in are far from representative of the broader population. In this episode, Lucas and Luna look at how AI is quietly rewriting the recruitment playbook. They walk through a concrete example from a mid-sized oncology network where a predictive matching tool cut screening time from weeks to days and doubled the share of…
How AI Is Making Sense of Wearable Health Data
Lucas and Luna drill into a specific problem: your smartwatch says your resting heart rate is up, but what does that actually mean? With millions of people wearing devices that beam out continuous health signals, AI is stepping in to translate raw sensor data into something clinicians can act on — without drowning them in alerts. The episode centers on a 2025 Stanford study where an AI model identified early signs of respiratory infection from smartwatch data days before symptoms appeared, and…
How AI Therapy Chatbots Are Expanding Mental Health Access
Lucas and Luna explore the rise of AI-powered mental health chatbots, focusing on a 2025 study where users of an AI therapy bot reported a 35% drop in depression symptoms over eight weeks. They break down how these bots use cognitive behavioral therapy techniques, natural language processing, and safety protocols to triage users in crisis. The conversation covers real-world adoption by employers, privacy concerns, and whether chatbots should complement or replace human therapists. A case study…
How AI Is Cutting Medical Billing Denial Rates
Medical billing is a $40 billion administrative headache for US hospitals, with an average of 1 in 4 claims denied on first submission. But AI is changing that. In this episode, Lucas and Luna explore how Northwell Health partnered with an AI startup to slash denial rates from 18% to 4% in just six months — saving $12 million annually. They break down the machine learning models that parse payer-specific rules, flag missing documentation, and even predict which claims are likely to be denied…
How AI Is Reducing ICU Alarm Fatigue
Every ICU patient triggers up to 190 alarms per day, and up to 90% are false or clinically irrelevant. This episode explores how machine learning algorithms are filtering out non-actionable alerts, allowing nurses to focus on true emergencies. We break down the specific technologies used by hospitals like Johns Hopkins — combining patient vital signs, electronic health record data, and trend analysis to reduce false alarms by over 50%. Lucas and Luna discuss the real-world impact on clinician…
How AI Is Cutting Prior Authorization Wait Times From Days to Minutes
Prior authorization has long been one of healthcare's most frustrating administrative bottlenecks, forcing doctors to wait days or weeks for insurance approval on treatments. In this episode, Lucas and Luna explore how a large Midwestern health system deployed an AI-powered natural language processing system that slashed average prior auth decision times from 3.2 days to just 14 minutes. They discuss how the AI reads clinical notes, extracts medical necessity criteria, and submits pre-filled…
How AI Scribes Are Cutting Physician Documentation Time by 75 Percent
Physicians spend nearly two hours on paperwork for every hour with patients. In episode 137 of Healthtech Talks, Lucas and Luna explore how AI-powered ambient scribes are slashing clinical documentation time. They examine the rollout at the University of Kansas Health System, where 400 doctors saw note-writing drop from 12 minutes to 3 minutes per patient. The conversation covers how the technology works — natural language processing models trained on medical conversations to generate SOAP…
How AI Is Predicting Cardiac Arrest Hours Before It Happens
In this episode of Healthtech Talks with Fexingo, Lucas and Luna dive into a Florida hospital's deployment of an AI system that predicts cardiac arrest on general medical-surgical units. Within six months, unplanned cardiac arrests dropped by 28 percent. They explore how the dynamic risk score outperforms traditional early warning scores, the design that minimizes alert fatigue, and the real impact on nursing workflow and patient outcomes. Plus, a look at scalability challenges and the…
How AI Is Detecting Diabetic Retinopathy From Retinal Scans
Diabetic retinopathy is the leading cause of blindness among working-age adults, yet many cases go undetected until vision loss begins. In this episode, Lucas and Luna explore how artificial intelligence is changing that by analyzing retinal scans with accuracy rivaling top ophthalmologists. They spotlight IDx-DR, the first FDA-authorized autonomous AI system for diabetic retinopathy screening, which can be used in primary care settings without a specialist present. The conversation covers how…
How AI Is Catching Hidden Atrial Fibrillation From a Simple ECG
Every year, millions of ECGs are recorded, yet atrial fibrillation—the most common serious heart arrhythmia—remains underdiagnosed because its episodes are often brief or silent. In this episode, we look at a deep learning model developed at the Mayo Clinic and validated in a 2025 trial of over 10,000 patients. The algorithm detected Afib in 1 in 5 patients whom cardiologists had cleared as normal. Lucas and Luna discuss how the tool is being integrated into routine primary-care screening, the…
How AI Is Accelerating Drug Discovery
In 2025, an AI model screened 12,000 compounds in just 48 hours and identified a potent new antibiotic against MRSA, a drug-resistant superbug that kills tens of thousands each year. This isn't science fiction — it's the new frontier of pharmaceutical development. In this episode, Lucas and Luna explore how artificial intelligence is compressing the decade-long drug discovery timeline into months. They break down the three key ways AI is transforming the pipeline: generative chemistry for…
How AI Personalizes Depression Treatment Plans
Millions of patients endure months of trial-and-error to find an antidepressant that works. In this episode, Lucas and Luna explore how a machine learning model at a major academic medical center uses EEG data and clinical history to predict individual SSRI response with over 70% accuracy — nearly doubling the success rate of standard prescribing. They walk through the study design, the surprising features the model prioritizes, and the practical hurdles to wider deployment, including data…
How AI Predicts Adverse Drug Reactions Before Prescription
In this episode of Healthtech Talks, Lucas and Luna explore how machine learning models are being used to predict adverse drug reactions before a prescription is written. They focus on a specific case: MedSafety AI, a platform developed by startup RxGuardian, which analyzes a patient's genetic markers, current medications, and lab results to flag potential dangerous interactions and side effects. Lucas shares that in a trial at the Mayo Clinic, the system reduced adverse drug reactions by 31…
How AI Is Predicting Hospital Readmissions Before Discharge
Episode 130 of Healthtech Talks with Fexingo dives into AI-driven readmission prediction — a tool that identifies which patients are likely to bounce back within 30 days, often before they even leave the hospital. Lucas and Luna examine a real-world implementation at a 400-bed community hospital in Ohio that cut readmissions by 22 percent using a machine learning model trained on electronic health record data, social determinants like housing stability, and real-time vitals. They break down the…
How AI Is Matching Patients to the Right Specialist
Episode 129 of Healthtech Talks with Fexingo explores how artificial intelligence is solving a frustrating healthcare problem: getting patients to the right specialist the first time. Lucas and Luna dig into a real-world deployment at a large academic medical center where an AI triage system reduced specialist mismatch by 32 percent in its first six months. They discuss how natural language processing parses referral notes and patient histories to suggest the best specialist, and why this…
How AI Is Reducing Unnecessary ER Visits
In this episode, Lucas and Luna explore how artificial intelligence is being used to triage patients before they even step into the emergency room. They focus on a specific case: a pilot program at a large urban hospital system that uses machine learning to analyze symptoms, vitals, and historical data from a patient's health record to predict whether an ER visit is truly necessary. The system recommends alternative care pathways—like urgent care or a telemedicine consult—for low-acuity cases…
How AI Is Detecting Early-Stage Alzheimer's Through Speech Patterns
In this episode of Healthtech Talks, Lucas and Luna explore how researchers are training AI models to detect early-stage Alzheimer's disease by analyzing subtle changes in speech patterns — years before traditional symptoms appear. They break down a 2025 study from Boston University showing that a vocal-analysis model achieved 88 percent accuracy in identifying mild cognitive impairment from a 30-second voice recording. The hosts discuss how acoustic biomarkers work, why this approach could…
How AI Is Diagnosing Skin Cancer Through Smartphone Photos
Artificial intelligence is turning the smartphone into a dermatology tool. Lucas and Luna examine how a deep learning model trained on over 100,000 dermoscopic images is detecting melanoma and basal cell carcinoma with accuracy matching board-certified dermatologists. They walk through a real-world deployment at a California clinic where the tool cut referral wait times from two weeks to under two hours. They also discuss the regulatory path cleared by the FDA's De Novo classification in early…
How AI Is Predicting Alzheimer's Years Before Symptoms
In this episode of Healthtech Talks, Lucas and Luna explore how artificial intelligence is being trained to detect early biomarkers of Alzheimer's disease — years before clinical symptoms appear. They focus on a landmark 2024 study from the University of California San Francisco, where an AI model analyzed routine brain MRI scans and electronic health records to predict Alzheimer's onset with 92 percent accuracy up to six years in advance. The hosts break down how the model works, what…
How AI Is Tuning Cochlear Implants for Better Hearing
In this episode of Healthtech Talks, Lucas and Luna dive into a surprising use of artificial intelligence: optimizing cochlear implant programming. Cochlear implants have transformed hearing for hundreds of thousands of people worldwide, but fitting them traditionally requires multiple painful visits to an audiologist—and outcomes vary widely. Now, a team at the University of Texas at Dallas has developed an AI system that can tune implant parameters based on patient feedback in real time…
How AI Is Matching Patients to the Right Hospital Bed
In this episode of Healthtech Talks, Lucas and Luna explore how AI-powered bed management is transforming hospital operations. They focus on a specific case: how Johns Hopkins Hospital used machine learning to predict bed demand and reduce emergency department boarding times by 37 percent. The hosts break down the algorithm's inputs, the cultural resistance from nursing staff, and the unexpected outcome that AI actually improved nurse satisfaction. They also touch on the economics: how a…
How AI Is Uncovering Hidden Patterns in Electronic Health Records
In this episode of Healthtech Talks, Lucas and Luna explore how artificial intelligence is being used to find patterns in electronic health records that humans routinely miss. They focus on a specific case from Boston Children's Hospital, where an AI model analyzing 1.5 million patient records identified a previously unknown link between postpartum depression and a specific vitamin D deficiency marker — seven years before standard screening would have caught it. The hosts discuss the challenges…
How AI Is Preventing Medication Errors in Hospitals
Lucas and Luna explore how artificial intelligence is being deployed to catch dangerous medication errors before they reach patients. They examine a 2025 study from Johns Hopkins showing that AI-powered clinical decision support systems can intercept 84% of potentially harmful drug-drug interactions and dosage miscalculations. The episode drills into a specific case: how Vanderbilt University Medical Center's AI system reduced adverse drug events by 37% in its first year of deployment. They…
How AI Is Matching Clinical Trials to Patients in Minutes
Every year, thousands of cancer patients never learn about clinical trials that could save their lives. In this episode of Healthtech Talks, Lucas and Luna dive into the quiet revolution of AI-powered clinical trial matching. They focus on a specific case: how Tempus, a Chicago-based healthtech company, built an algorithm that scans electronic health records against trial eligibility criteria in under 60 seconds — a process that used to take a human research coordinator six to eight hours per…
How AI Is Predicting Post-Surgery Infections With Wearables
Lucas and Luna explore how AI-powered wearable sensors are being used to predict surgical site infections days before visible symptoms appear. They focus on a real-world deployment at a major US hospital system where patients wear a small adhesive patch post-surgery that tracks heart rate, respiration, skin temperature, and gait. The algorithm, trained on thousands of recovery trajectories, issues alerts when subtle deviations signal an emerging infection. The episode dives into the numbers…
How AI Is Predicting Sepsis Hours Before Blood Cultures Turn Positive
Sepsis is the silent killer that accounts for one in five deaths worldwide. By the time blood cultures come back positive, the patient is often already in crisis. But a new wave of AI-driven early warning systems is changing the timeline. In this episode of Healthtech Talks, Lucas and Luna explore how machine learning models trained on real-time vitals, lab results, and nursing notes can predict sepsis up to 12 hours before traditional diagnostics. They dive into the Epic Sepsis Model…
How AI Is Predicting Kidney Injury Before Dialysis
In this episode of Healthtech Talks, Lucas and Luna explore how artificial intelligence is predicting acute kidney injury (AKI) up to 48 hours before it becomes critical. They focus on a specific deployment at a large academic medical center where an AI model reduced dialysis starts by 25% and cut ICU length of stay. The hosts break down how the model works—using lab trends, vital signs, and medication data in real time—and discuss the challenges of false alarms, clinician alert fatigue, and…
How AI Is Streamlining Hospital Prior Authorization
Lucas and Luna dive into how artificial intelligence is transforming prior authorization in healthcare—a bureaucratic process that costs hospitals billions annually and delays patient care. They examine a real-world case: a mid-sized hospital system in Ohio that deployed an AI platform from a startup called Cohere Health, reducing authorization turnaround time from 11 days to under 48 hours. The hosts break down how natural language processing reads clinical notes and matches them to payer…
How AI Is Personalizing Cancer Treatment Plans
In this episode of Healthtech Talks, Lucas and Luna explore how artificial intelligence is personalizing cancer treatment plans at scale. They focus on a specific case: Memorial Sloan Kettering's collaboration with IBM Watson Health (now part of Merative) and how the platform analyzes thousands of medical papers, clinical trials, and patient records in minutes to suggest tailored therapies. The hosts discuss the challenges of data integration, clinician buy-in, and the recent shift toward…
How AI Is Detecting Early-Stage Pancreatic Cancer
Pancreatic cancer is notoriously hard to detect early, but AI is changing that. In this episode, Lucas and Luna explore how machine learning models are analyzing CT scans, electronic health records, and even routine blood tests to flag patients at high risk before symptoms appear. They discuss a recent study from MIT and Harvard that used an AI model trained on millions of patient records to predict pancreatic cancer risk up to three years before diagnosis. The hosts also look at how systems…
How AI Is Reducing Diagnostic Errors in Radiology
A deep dive into how artificial intelligence is being deployed to cut diagnostic errors in radiology. We examine a landmark 2025 study from the University of Pittsburgh Medical Center showing a 23% reduction in missed findings when AI acts as a second reader on chest X-rays. Lucas and Luna discuss why radiologists are embracing AI as a partner, not fearing replacement, and how the technology is being integrated into real clinical workflows. The episode zooms in on the specific case of pulmonary…
How AI Is Monitoring Patient Falls Before They Happen
Every year in the US, between 700,000 and 1 million hospitalized patients fall. Many result in broken hips, head injuries, and longer stays. Traditional fall-risk assessments rely on nurses manually scoring patients—subjective, inconsistent, and slow. Now, a wave of AI-powered camera systems is changing that. Lucas and Luna explore how companies like CareAI and Walabot are using computer vision and radar to detect when a patient is about to get out of bed or wobble, alerting staff seconds…
How AI Is Predicting Patient Deterioration in Real Time
Lucas and Luna dive into how hospitals are using AI to predict patient deterioration in real time, before a code blue is called. They examine a specific deployment at a major academic medical center that reduced escalations by 25 percent by analyzing vital signs, lab results, and nurse charting every five minutes. The episode walks through how the model works, the operational challenges of getting clinicians to trust a black box, and why this is different from the sepsis prediction tools that…
How AI Is Predicting Heart Failure Before Symptoms Start
Hospitals miss about 20% of heart failure cases until the patient is already in crisis. This episode dives into how machine learning models—trained on electronic health records, lab trends, and subtle vital sign shifts—can flag heart failure risk weeks before symptoms appear. Lucas and Luna examine a specific algorithm deployed at the Mayo Clinic that reduced missed diagnoses by 38% in a 2025 study. They discuss the data inputs that matter most (ejection fraction trends, BNP levels, weight…
Showing the latest 50 episodes. The full archive of 159 is on Apple Podcasts, Spotify and every major podcast app — or via the RSS feed above.