Independent research · sole author · 2025 – present

Risk-aware healthcare cost prediction

A care team can only reach a small share of its members. The useful question is not what someone will cost on average, but who belongs in that small share.

Evaluation code on GitHub

the high-cost spending captured at top-0.5% capacity, against a calibrated logistic baseline (p = 0.018): 2.0×
quantile crossings in 745,560 pairs, against 1.54% for baselines: 0
expected calibration error: 0.006
manuscript numbers machine-verified against run outputs: 98 / 98

$19.9M

In budget terms

of additional high-cost spending captured per 100K enrollees at top-0.5% capacity

Illustrative and approximate. 95% CI $3.7M to $40.1M.

The question

Healthcare spending is heavy-tailed: a small number of people account for a large part of the total. Most cost models are tuned for the average. This research asks what a model should predict when capacity is fixed and only the top of the distribution can be acted on.

The model is a multi-task FT-Transformer in PyTorch. From 72,818 person-years of US national survey data (MEPS, 2018–2023) it predicts expected cost, 7 tail quantiles and nested high-cost risk in one model, and its quantiles never cross.

The shape of the model

One record per person-year

US national survey data, MEPS 2018–2023

One multi-task model

FT-Transformer, PyTorch

Expected cost
7 tail quantiles
Nested high-cost risk

What did not reach significance

The gain is significant across the top 0.5–2% of capacity. At the 5% endpoint the difference is +1.89 points with p = 0.072, and it is reported as non-significant.

Headline result

Share of total spending captured by the people flagged

model calibrated logistic baseline not significant

Flagging the top 0.5% of people, the model captures 6.24% of total spending against 3.11% for the baseline (2.01×, p = 0.018).

Count-based top-k% selection, model against a calibrated logistic baseline. Paired cluster bootstrap, B = 2,000.

Built to be checked

60 seeded, reproducible runs (15 core, 45 external) with 0 failed steps, and a 35-run ablation.
Survey-weighted paired bootstrap inference with B = 2,000.
The crossing comparison is against a bank of LightGBM quantile regressors and logistic classifiers, the strongest classical method for each task. On raw accuracy the two are close; the difference is that this model's outputs never contradict each other.
Rebuilt inputs are byte-identical to the originals: 13 of 13 file hashes match.
A 98-point automated check binds every number in the manuscript to hashed evidence.
Reported to TRIPOD+AI and PROBAST+AI standards.

Beyond the first paper

External validity: the fixed model tested on 6 external datasets (up to 1.8M records), reporting where it does and does not transfer.
Timing: predicting cost earlier in the year, when less is known.
From prediction to action: how predicted risk can guide who is reached when capacity and budget are fixed.

Manuscripts

Sole author, as Zehui Zhang. Not yet published, so each is listed by topic.

01
Healthcare cost prediction when capacity is fixed: one model for expected cost, tail quantiles and high-cost risk
Prepared for submission to JAMIA
02
How far a fixed cost model transfers to external data
In preparation
03
Predicting cost earlier in the year, when less is known
In preparation
04
Describing the high-cost population beyond a single risk score
In preparation
05
Deciding who to reach when capacity and budget are fixed
In preparation

Patent applications (China, CNIPA; filed 2026, pending)

A method for predicting healthcare spending.
A method for grouping a population by predicted risk.
A method for allocating care resources from predicted risk.

The manuscripts are not yet published, so this page stays at the level of the question and the headline results. I am glad to walk through the methods in conversation.